diff --git a/feed_weekly.xml b/feed_weekly.xml index a8bfbf9..8fa1e8d 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 04 May 2026 00:28:28 +0000 + Mon, 11 May 2026 00:30:42 +0000 - DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation - https://arxiv.org/abs/2604.20857 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.20857.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingwen Zhang, Ling Yue, Zhen Xu, Shaowu Pan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in autonomous ``AI scientist'' systems have demonstrated the ability to automatically write scientific manuscripts and codes with execution. However, producing a publication-grade scientific diagram (e.g., teaser figure) is still a major bottleneck in the ``end-to-end'' paper generation process. For example, a teaser figure acts as a strategic visual interface and serves a different purpose than derivative data plots. It demands conceptual synthesis and planning to translate complex logic workflow into a compelling graphic that guides intuition and sparks curiosity. Existing AI scientist systems usually omit this component or fall back to an inferior alternative. To bridge this gap, we present DiagramBank, a large-scale dataset consisting of 89,422 schematic diagrams curated from existing top-tier scientific publications, designed for multimodal retrieval and exemplar-driven scientific figure generation. DiagramBank is developed through our automated curation pipeline that extracts figures and corresponding in-text references, and uses a CLIP-based filter to differentiate schematic diagrams from standard plots or natural images. Each instance is paired with rich context from abstract, caption, to figure-reference pairs, enabling information retrieval under different query granularities. We release DiagramBank in a ready-to-index format and provide a retrieval-augmented generation codebase to demonstrate exemplar-conditioned synthesis of teaser figures. DiagramBank is publicly available at https://huggingface.co/datasets/zhangt20/DiagramBank with code at https://github.com/csml-rpi/DiagramBank.</p> - https://arxiv.org/abs/2604.20857 - Sat, 28 Feb 2026 00:00:00 +0000 + StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing + https://arxiv.org/abs/2605.02904 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02904.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto Tacconelli</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present StateSMix, a fully self-contained lossless compressor that couples an online-trained Mamba-style State Space Model (SSM) with sparse n-gram context mixing and arithmetic coding. The model is initialised from scratch and trained token-by-token on the file being compressed, requiring no pre-trained weights, no GPU, and no external dependencies. The SSM (DM=32, NL=2, approximately 120K active parameters per file) provides a continuously-updated probability estimate over BPE tokens, while nine sparse n-gram hash tables (bigram through 32-gram, 16M slots each) add exact local and long-range pattern memorisation via a softmax-invariant logit-bias mechanism that updates only non-zero-count tokens. An entropy-adaptive scaling mechanism modulates the n-gram contribution based on the SSM's predictive confidence, preventing over-correction when the neural model is already well-calibrated. On the standard enwik8 benchmark, StateSMix achieves 2.123 bpb on 1 MB, 2.149 bpb on 3 MB, and 2.162 bpb on 10 MB, beating xz -9e (LZMA2) by 8.7%, 5.4%, and 0.7% respectively. Ablation experiments establish the SSM as the dominant compression engine: it alone accounts for a 46.6% size reduction over a frequency-count baseline and beats xz without any n-gram component, while n-gram tables provide a complementary 4.1% gain through exact context memorisation. OpenMP parallelisation of the training loop yields 1.9x speedup on 4 cores. The system is implemented in pure C with AVX2 SIMD and processes approximately 2,000 tokens per second on commodity x86-64 hardware.</p> + https://arxiv.org/abs/2605.02904 + Sun, 05 Apr 2026 00:00:00 +0000 - AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval - https://arxiv.org/abs/2604.16353 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16353.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuvam Banerji Seal, Aheli Poddar, Alok Mishra, Dwaipayan Roy</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This paper introduces AgriIR, a configurable retrieval augmented generation (RAG) framework designed to deliver grounded, domain-specific answers while maintaining flexibility and low computational cost. Instead of relying on large, monolithic models, AgriIR decomposes the information access process into declarative modular stages -- query refinement, sub-query planning, retrieval, synthesis, and evaluation. This design allows practitioners to adapt the framework to new knowledge verticals without modifying the architecture. Our reference implementation targets Indian agricultural information access, integrating 1B-parameter language models with adaptive retrievers and domain-aware agent catalogues. The system enforces deterministic citation, integrates telemetry for transparency, and includes automated deployment assets to ensure auditable, reproducible operation. By emphasizing architectural design and modular control, AgriIR demonstrates that well-engineered pipelines can achieve domain-accurate, trustworthy retrieval even under constrained resources. We argue that this approach exemplifies ``AI for Agriculture'' by promoting accessibility, sustainability, and accountability in retrieval-augmented generation systems.</p> - https://arxiv.org/abs/2604.16353 - Tue, 17 Mar 2026 00:00:00 +0000 + Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning + https://arxiv.org/abs/2605.02913 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rohan Surana, Gagan Mundada, Xunyi Jiang, Chuhan Wang, Zhenwei Tang, Difan Jiao, Zihan Huang, Yuxin Xiong, Junda Wu, Sheldon Yu, Xintong Li, Raghav Jain, Nikki Kuang, Sizhe Zhou, Bowen Jin, Zhendong Chu, Tong Yu, Ryan Rossi, Kuan-Hao Huang, Jingbo Shang, Jiawei Han, Julian McAuley</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajectory sampled from a prompt to termination, including intermediate reasoning steps and optional tool or environment interactions, determines the data the optimizer learns from, yet rollout design is often underreported. This survey provides an optimizer-agnostic view of rollout strategies for RL-based post-training of reasoning LLMs. We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR), a lifecycle taxonomy that decomposes rollout pipelines into four modular stages: Generate proposes candidate trajectories and topologies; Filter constructs intermediate signals via verifiers, judges, critics; Control allocates compute and makes continuation/branching/stopping decisions under budgets; and Replay retains and reuses artifacts across rollouts without weight updates, including self-evolving curricula that autonomously generate new training tasks. We complement GFCR with a criterion taxonomy of reliability, coverage, and cost sensitivity that characterizes rollout trade-offs. Using this framework, we synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement. We ground the framework with case studies in math, code/SQL, multimodal reasoning, tool-using agents, and agentic skill benchmarks that evaluate skill induction, reuse, and cross-task transfer. Finally, we provide a diagnostic index that maps common rollout pathologies to GFCR modules and mitigation levers, alongside open challenges for building reproducible, compute-efficient, and trustworthy rollout pipelines.</p> + https://arxiv.org/abs/2605.02913 + Wed, 08 Apr 2026 00:00:00 +0000 - Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining - https://arxiv.org/abs/2604.16391 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.16391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyao Zhang, Bozhou Zhang, Zekun Qi, Wenjun Zeng, Xin Jin, Li Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image forecasting and 3D action prediction. Besides, such a vision-action entangled training manner limits model learning from large-scale, action-free web video data. To address these issues, we propose DeFI, a novel framework that Decouples visual Forward and Inverse dynamics pretraining to exploit respective data sources, wherein video generation and action prediction are disentangled. We introduce the General Forward Dynamics Model (GFDM), pretrained on diverse human and robot videos for future prediction, and the General Inverse Dynamics Model (GIDM), trained via self-supervised learning to infer latent actions from unlabeled video transitions. These models are then integrated into a unified architecture for end-to-end finetuning on downstream tasks. In this manner, GFDM and GIDM first shine separately and then cooperate for mutual benefit. Extensive experiments on CALVIN ABC-D and SimplerEnv demonstrate state-of-the-art performance, with DeFI achieving an average task length of 4.51 for CALVIN, 51.2% success rate on SimplerEnv-Fractal benchmark and 81.3% success rate in real-world deployment, significantly outperforming prior methods.</p> - https://arxiv.org/abs/2604.16391 - Fri, 27 Mar 2026 00:00:00 +0000 + Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO + https://arxiv.org/abs/2605.04077 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin, Jiashuo Liu, Ziniu Li, Bingrui Li, Yuhao Wu, Yining Zheng, Ge Zhang, Wenhao Huang, Xipeng Qiu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: how token-level policy gradient terms are aggregated within each sampled group. Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative. We show that these two rules induce different optimization biases: token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses through sequence-level equal weighting. To address this tension, we propose Balanced Aggregation (BA), a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improves training stability and final performance over standard token and sequence aggregation. Our analysis further shows that the relative effectiveness of token and sequence aggregation is largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.</p> + https://arxiv.org/abs/2605.04077 + Tue, 14 Apr 2026 00:00:00 +0000 - Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing - https://arxiv.org/abs/2604.22782 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22782.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anastasiia Filippova, David Grangier, Marco Cuturi, João Monteiro</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs. This work proposes to lessen these memory requirements. While recent work has largely addressed KV cache reduction via compression and eviction along the temporal axis, we argue that the depth dimension offers an orthogonal and robust avenue for optimization. Although prior research suggests that a full cache for every layer is redundant, implementing cross-layer cache sharing remains a practical challenge; existing methods typically suffer from reduced throughput or increased time-to-first-token. In this paper, we demonstrate that dropping a layer's cache offers efficient optimization without information loss. We propose a simple training approach: random cross-layer attention. During training, layers randomly choose to attend either to their own KV states or those of a preceding layer. This stochastic process adapts the model to be robust to various depth-wise cache sharing strategies, ensuring flexibility for unknown hardware constraints at deployment time. Our evaluations show that applying this scheme during pre-training or fine-tuning enables depth-wise cache sharing for various model families. Furthermore, for larger models in data-constrained settings, this approach is suggestive of a regularization-like effect, frequently preserving or improving performance while significantly reducing the cache's memory footprint.</p> - https://arxiv.org/abs/2604.22782 - Fri, 03 Apr 2026 00:00:00 +0000 - - - Why Fine-Tuning Encourages Hallucinations and How to Fix It - https://arxiv.org/abs/2604.15574 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.15574.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guy Kaplan, Zorik Gekhman, Zhen Zhu, Lotem Rozner, Yuval Reif, Swabha Swayamdipta, Derek Hoiem, Roy Schwartz</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t. knowledge acquired during pre-training. In this work, we explore whether SFT-induced hallucinations can be mitigated using established tools from the continual learning literature, since they arise as a by-product of knowledge degradation during training. We propose a self-distillation-based SFT method that facilitates effective factual learning while minimizing hallucinations w.r.t. pre-existing knowledge by regularizing output-distribution drift. We also show that, in settings where new knowledge acquisition is unnecessary, suppressing factual plasticity by freezing parameter groups, can preserve task performance while reducing hallucinations. Lastly, we investigate the mechanism behind SFT-induced hallucinations through three hypotheses: capacity limitations, behavior cloning, and localized interference. Our experiments show that a main driver is interference among overlapping semantic representations, and that self-distillation succeeds by mitigating this interference.</p> - https://arxiv.org/abs/2604.15574 - Thu, 16 Apr 2026 00:00:00 +0000 - - - UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models - https://arxiv.org/abs/2604.17565 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.17565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hong Jiang, Wensong Song, Zongxing Yang, Ruijie Quan, Yi Yang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geometric consistency. However, existing methods typically rely on fragmented geometric guidance, such as only injecting point clouds at the representation level despite models containing multiple levels, and are mainly based on image diffusion models that operate on discrete view mappings. These two limitations jointly lead to geometric drift and structural degradation under continuous camera motion. We observe that while leveraging video models provides continuous viewpoint priors for camera-controllable image editing, they still struggle to form stable geometric understanding if geometric guidance remains fragmented. To systematically address this, we inject unified geometric guidance across three levels that jointly determine the generative output: representation, architecture, and loss function. To this end, we propose UniGeo, a novel camera-controllable editing framework. Specifically, at the representation level, UniGeo incorporates a frame-decoupled geometric reference injection mechanism to provide robust cross-view geometry context. At the architecture level, it introduces geometric anchor attention to align multi-view features. At the loss function level, it proposes a trajectory-endpoint geometric supervision strategy to explicitly reinforce the structural fidelity of target views. Comprehensive experiments across multiple public benchmarks, encompassing both extensive and limited camera motion settings, demonstrate that UniGeo significantly outperforms existing methods in both visual quality and geometric consistency.</p> - https://arxiv.org/abs/2604.17565 - Sun, 19 Apr 2026 00:00:00 +0000 - - - Towards Understanding the Robustness of Sparse Autoencoders - https://arxiv.org/abs/2604.18756 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18756.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain underexplored. We present a study of integrating pretrained SAEs into transformer residual streams at inference time, without modifying model weights or blocking gradients. Across four model families (Gemma, LLaMA, Mistral, Qwen) and two strong white-box attacks (GCG, BEAST) plus three black-box benchmarks, SAE-augmented models achieve up to a 5x reduction in jailbreak success rate relative to the undefended baseline and reduce cross-model attack transferability. Parametric ablations reveal (i) a monotonic dose-response relationship between L0 sparsity and attack success rate, and (ii) a layer-dependent defense-utility tradeoff, where intermediate layers balance robustness and clean performance. These findings are consistent with a representational bottleneck hypothesis: sparse projection reshapes the optimization geometry exploited by jailbreak attacks.</p> - https://arxiv.org/abs/2604.18756 - Mon, 20 Apr 2026 00:00:00 +0000 - - - LLM Safety From Within: Detecting Harmful Content with Internal Representations - https://arxiv.org/abs/2604.18519 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18519.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Difan Jiao, Yilun Liu, Ye Yuan, Zhenwei Tang, Linfeng Du, Haolun Wu, Ashton Anderson</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across internal layers. We present SIREN, a lightweight guard model that harnesses these internal features. By identifying safety neurons via linear probing and combining them through an adaptive layer-weighted strategy, SIREN builds a harmfulness detector from LLM internals without modifying the underlying model. Our comprehensive evaluation shows that SIREN substantially outperforms state-of-the-art open-source guard models across multiple benchmarks while using 250 times fewer trainable parameters. Moreover, SIREN exhibits superior generalization to unseen benchmarks, naturally enables real-time streaming detection, and significantly improves inference efficiency compared to generative guard models. Overall, our results highlight LLM internal states as a promising foundation for practical, high-performance harmfulness detection.</p> - https://arxiv.org/abs/2604.18519 - Mon, 20 Apr 2026 00:00:00 +0000 - - - EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment - https://arxiv.org/abs/2604.22842 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Andrea Atzori, Fadi Boutros, Naser Damer</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Face Image Quality Assessment is crucial for reliable face recognition systems, yet existing Vision Transformer-based approaches rely exclusively on final-layer representations, ignoring quality-relevant information captured at intermediate network depths. This paper presents the first comprehensive investigation of how intermediate representations within ViTs contribute to face quality assessment through early exit mechanisms and score fusion strategies. We systematically analyze all twelve transformer blocks of ViT-FIQA architectures, demonstrating that different depths capture distinct and complementary quality-relevant information, as evidenced by varying attention patterns and performance characteristics across network layers. We propose a score fusion framework that combines quality predictions from multiple transformer blocks without architectural modifications or additional training. Our early exit analysis reveals optimal performance-efficiency trade-offs, enabling significant computational savings while maintaining competitive performance. Through extensive evaluation across eight benchmark datasets using four FR models, we demonstrate that our fusion strategy improves upon single-exit approaches. Our proposed quality fusion approach employs depth-weighted averaging that assigns progressively higher importance to deeper transformer blocks, achieving the best quality assessment performance by effectively leveraging the hierarchical nature of feature learning in ViTs. Our work challenges the conventional wisdom that only deep features matter for face analysis, revealing that intermediate representations contain valuable information for quality assessment. The proposed framework offers practical benefits for real-world biometric systems by enabling adaptive computation based on resource constraints while maintaining competitive quality assessment capabilities.</p> - https://arxiv.org/abs/2604.22842 - Tue, 21 Apr 2026 00:00:00 +0000 - - - EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training - https://arxiv.org/abs/2604.20012 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.20012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyang Du, Zhanqiu Guo, Xin Ye, Liu Ren, Chenyan Xiong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream performance. In this work, we propose EmbodiedMidtrain to bridge the gap between VLMs and VLAs. We first characterize the data distribution gap between them, showing that VLA data occupy compact regions that are largely separated from the broader VLM distribution, while the degree of alignment varies substantially both across and within VLM data sources. Then, we build a mid-training data engine that leverages a lightweight learnable proximity estimator to select the most VLA-aligned candidates from a large VLM pool, and mid-trains the VLM on this curated mixture before downstream VLA fine-tuning. Experiments on three robot manipulation benchmarks show that mid-training consistently improves performance across different VLM backbones, achieving results competitive with expert VLAs and off-the-shelf VLMs trained with larger model scale and training budgets. Further analysis reveals that mid-training provides a stronger initialization for VLA fine-tuning, with gains emerging from the earliest steps and widening throughout training. Moreover, the data engine captures both dataset-level and sample-level alignment signals, favoring spatial reasoning over text-centric tasks while preserving the diversity of the VLM data. We will release all code, data and models for future research.</p> - https://arxiv.org/abs/2604.20012 - Tue, 21 Apr 2026 00:00:00 +0000 - - - ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers - https://arxiv.org/abs/2604.22841 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22841.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Marco Huber, Andrea Atzori, Naser Damer, Fadi Boutros</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems. Existing approaches require computationally expensive procedures such as multiple forward passes, backpropagation, or additional training, and only recent work has focused on the use of Vision Transformers. Recent studies highlighted that these architectures inherently function as saliency learners with attention patterns naturally encoding spatial importance. This work proposes ATTN-FIQA, a novel training-free approach that investigates whether pre-softmax attention scores from pre-trained Vision Transformer-based face recognition models can serve as quality indicators. We hypothesize that attention magnitudes intrinsically encode quality: high-quality images with discriminative facial features enable strong query-key alignments producing focused, high-magnitude attention patterns, while degraded images generate diffuse, low-magnitude patterns. ATTN-FIQA extracts pre-softmax attention matrices from the final transformer block, aggregate multi-head attention information across all patches, and compute image-level quality scores through simple averaging, requiring only a single forward pass through pre-trained models without architectural modifications, backpropagation, or additional training. Through comprehensive evaluation across eight benchmark datasets and four FR models, this work demonstrates that attention-based quality scores effectively correlate with face image quality and provide spatial interpretability, revealing which facial regions contribute most to quality determination.</p> - https://arxiv.org/abs/2604.22841 - Tue, 21 Apr 2026 00:00:00 +0000 - - - Sessa: Selective State Space Attention - https://arxiv.org/abs/2604.18580 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.18580.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liubomyr Horbatko</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate information through an explicit recurrent state. These mechanisms face different limitations on long contexts: when attention is diffuse, the influence of individual tokens is diluted across the effective support, while recurrent state propagation can lose long-range sensitivity unless information is actively preserved. As a result, both mechanisms face challenges in preserving and selectively retrieving information over long contexts. We propose Sessa, a decoder that places attention inside a recurrent feedback path. This creates many attention-based paths through which past tokens can influence future states, rather than relying on a single attention read or a single recurrent chain. We prove that, under explicit assumptions and matched regimes, Sessa admits power-law memory tails O(ell^{-β}) for 0 < β< 1, with slower decay than in the corresponding Transformer and Mamba-style baselines. We further give an explicit construction that achieves this power-law rate. Under the same assumptions, Sessa is the only model class among those considered that realizes flexible selective retrieval, including profiles whose influence does not decay with distance. Consistent with this theoretical advantage, across matched experiments, Sessa achieves the strongest performance on long-context benchmarks while remaining competitive with Transformer and Mamba-style baselines on short-context language modeling.</p> - https://arxiv.org/abs/2604.18580 - Tue, 21 Apr 2026 00:00:00 +0000 - - - Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment - https://arxiv.org/abs/2604.19548 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.19548.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bobo Li, Rui Wu, Zibo Ji, Meishan Zhang, Hao Fei, Min Zhang, Mong-Li Lee, Wynne Hsu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing. While such role-playing effectively leverages domain expert knowledge, we find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry (AOA). Specifically, an agent acting as an actor (during self-reflection) tends to attribute failures to external factors, whereas an observer (during mutual auditing) attributes the same errors to internal faults. We quantify this using our new Ambiguous Failure Benchmark, which reveals that simply swapping perspectives triggers the AOA effect in over 20% of cases for most models. To tame this bias, we introduce ReTAS (Reasoning via Thesis-Antithesis-Synthesis), a model trained through dialectical alignment to enforce perspective-invariant reasoning. By integrating dialectical chain-of-thought with Group Relative Policy Optimization, ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus. Experiments demonstrate that ReTAS effectively mitigates attribution inconsistency and significantly improves fault resolution rates in ambiguous scenarios.</p> - https://arxiv.org/abs/2604.19548 - Tue, 21 Apr 2026 00:00:00 +0000 - - - The Last Harness You'll Ever Build - https://arxiv.org/abs/2604.21003 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21003.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haebin Seong, Li Yin, Haoran Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, automating code review across unfamiliar repositories, and handling customer escalations that demand nuanced domain knowledge. Each new task domain requires painstaking, expert-driven harness engineering: designing the prompts, tools, orchestration logic, and evaluation criteria that make a foundation model effective. We present a two-level framework that automates this process. At the first level, the Harness Evolution Loop optimizes a worker agent's harness H for a single task: a Worker Agent W_{H} executes the task, an Evaluator Agent V adversarially diagnoses failures and scores performance, and an Evolution Agent E modifies the harness based on the full history of prior attempts. At the second level, the Meta-Evolution Loop optimizes the evolution protocol Λ= (W_{H}, H^{(0)}, V, E) itself across diverse tasks, learning a protocol Λ^{(text{best)} that enables rapid harness convergence on any new task -- so that adapting an agent to a novel domain requires no human harness engineering at all.} We formalize the correspondence to meta-learning and present both algorithms. The framework shifts manual harness engineering into automated harness engineering, and takes one step further -- automating the design of the automation itself.</p> - https://arxiv.org/abs/2604.21003 + MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills + https://arxiv.org/abs/2604.20441 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.20441.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yingyong Hou, Xinyuan Lao, Huimei Wang, Qianyu Yao, Wei Chen, Bocheng Huang, Fei Sun, Yuxian Lv, Weiqi Lei, Xueqian Wen, Pengfei Xia, Zhujun Tan, Shengyang Xie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.</p> + https://arxiv.org/abs/2604.20441 Wed, 22 Apr 2026 00:00:00 +0000 - Building a Precise Video Language with Human-AI Oversight - https://arxiv.org/abs/2604.21718 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21718.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiqiu Lin, Chancharik Mitra, Siyuan Cen, Isaac Li, Yuhan Huang, Yu Tong Tiffany Ling, Hewei Wang, Irene Pi, Shihang Zhu, Ryan Rao, George Liu, Jiaxi Li, Ruojin Li, Yili Han, Yilun Du, Deva Ramanan</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, grounded by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce CHAI (Critique-based Human-AI Oversight), a framework where trained experts critique and revise model-generated pre-captions into improved post-captions. This division of labor improves annotation accuracy and efficiency by offloading text generation to models, allowing humans to better focus on verification. Additionally, these critiques and preferences between pre- and post-captions provide rich supervision for improving open-source models (Qwen3-VL) on caption generation, reward modeling, and critique generation through SFT, DPO, and inference-time scaling. Our ablations show that critique quality in precision, recall, and constructiveness, ensured by our oversight framework, directly governs downstream performance. With modest expert supervision, the resulting model outperforms closed-source models such as Gemini-3.1-Pro. Finally, we apply our approach to re-caption large-scale professional videos (e.g., films, commercials, games) and fine-tune video generation models such as Wan to better follow detailed prompts of up to 400 words, achieving finer control over cinematography including camera motion, angle, lens, focus, point of view, and framing. Our results show that precise specification and human-AI oversight are key to professional-level video understanding and generation. Data and code are available on our project page: https://linzhiqiu.github.io/papers/chai/</p> - https://arxiv.org/abs/2604.21718 - Wed, 22 Apr 2026 00:00:00 +0000 - - - Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models - https://arxiv.org/abs/2604.21523 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammed Safi Ur Rahman Khan, Sanjay Suryanarayanan, Tushar Anand, Mitesh M. Khapra</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Vision-Language Models (VLMs) are increasingly used to evaluate outputs of other models, for image-to-text (I2T) tasks such as visual question answering, and text-to-image (T2I) generation tasks. Despite this growing reliance, the reliability of these Evaluator VLMs remains under explored. In this work, we systematically evaluate the reliability of Evaluator VLMs across both I2T and T2I tasks. We introduce targeted perturbations that degrade output quality along key error dimensions, including object hallucinations, spatial reasoning, factual grounding, and visual fidelity. These perturbations test whether Evaluator VLMs can reliably account for these quality degrading errors in their evaluations. Using a comprehensive benchmark of over 4000 perturbed instances spanning 40 perturbation dimensions, we evaluate 4 prominent VLMs using single-answer scoring, pairwise comparison, and reference-guided paradigms. Our findings reveal that current VLM evaluators exhibit substantial blind spots: they often fail to detect perturbed outputs - in some cases exceeding 50%, struggle particularly with fine-grained compositional and spatial errors, and are often insensitive to hallucinated content that contradicts the input image. Pairwise comparison proves more reliable, though failure rates persist. These results highlight the unreliable nature of current Evaluator VLMs and urge caution in their deployment for benchmarking and development decisions. Code and data have been made publicly available.</p> - https://arxiv.org/abs/2604.21523 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages - https://arxiv.org/abs/2604.21481 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21481.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Srija Anand, Ashwin Sankar, Ishvinder Sethi, Aaditya Pareek, Kartik Rajput, Gaurav Yadav, Nikhil Narasimhan, Adish Pandya, Deepon Halder, Mohammed Safi Ur Rahman Khan, Praveen S V, Shobhit Banga, Mitesh M Khapra</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introduces high variance due to linguistic diversity and multidimensional nature of speech perception. We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation. Using 5K+ native and code-mixed sentences across 10 Indic languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters. In addition to overall preference, raters provide judgments across 6 perceptual dimensions: intelligibility, expressiveness, voice quality, liveliness, noise, and hallucinations. Using Bradley-Terry modeling, we construct a multilingual leaderboard, interpret human preference using SHAP analysis and analyze leaderboard reliability alongside model strengths and trade-offs across perceptual dimensions.</p> - https://arxiv.org/abs/2604.21481 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework - https://arxiv.org/abs/2604.22119 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tharindu Kumarage, Lisa Bauer, Yao Ma, Dan Rosen, Yashasvi Raghavendra Guduri, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecified objectives). Systematically understanding and benchmarking these risks remains an open challenge. To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation. We construct an extensible risk taxonomy of 7 categories, which is decomposed into 20 subcategories. ESRRSim generates evaluation scenarios designed to elicit faithful reasoning, paired with dual rubrics assessing both model responses and reasoning traces, in a judge-agnostic and scalable architecture. Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation contexts.</p> - https://arxiv.org/abs/2604.22119 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents - https://arxiv.org/abs/2604.22085 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22085.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel, Neel Patel, Majid Fekri, Tara Khani</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies largely depend on hybrid semantic graph architectures, which impose substantial computational overhead during both ingestion and retrieval. These systems typically require large language model mediated entity extraction, explicit graph schema maintenance, and multi query retrieval pipelines. This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidelity agent memory. Memanto integrates a typed semantic memory schema comprising thirteen predefined memory categories, an automated conflict resolution mechanism, and temporal versioning. These components are enabled by Moorcheh's Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while eliminating ingestion delay. Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively. These results surpass all evaluated hybrid graph and vector based systems while requiring only a single retrieval query, incurring no ingestion cost, and maintaining substantially lower operational complexity. A five stage progressive ablation study is presented to quantify the contribution of each architectural component, followed by a discussion of the implications for scalable deployment of agentic memory systems.</p> - https://arxiv.org/abs/2604.22085 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Efficient Agent Evaluation via Diversity-Guided User Simulation - https://arxiv.org/abs/2604.21480 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21480.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itay Nakash, George Kour, Ateret Anaby-Tavor</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large language models (LLMs) are increasingly deployed as customer-facing agents, yet evaluating their reliability remains challenging due to stochastic, multi-turn interactions. Current evaluation protocols rely on linear Monte Carlo rollouts of complete agent-user conversations to estimate success. However, this approach is computationally inefficient, repeatedly regenerating identical early prefixes, and often fails to uncover deep failure modes that arise from rare user behaviors. We introduce DIVERT (Diversity-Induced Evaluation via Branching of Trajectories), an efficient, snapshot-based, coverage-guided user simulation framework for systematic exploration of agent-user interactions. DIVERT captures the full agent-environment state at critical decision points and resumes execution from these snapshots, enabling reuse of shared conversation prefixes and reducing redundant computation. From each junction, the framework branches using targeted, diversity-inducing user responses, allowing directed exploration of alternative interaction paths. By focusing evaluation on semantically diverse and underexplored trajectories, DIVERT improves both efficiency and coverage. Empirical results show that it discovers more failures per token compared to standard linear rollout protocols, while expanding the set of tasks on which failures are identified.</p> - https://arxiv.org/abs/2604.21480 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Sapiens2 - https://arxiv.org/abs/2604.21681 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rawal Khirodkar, He Wen, Julieta Martinez, Yuan Dong, Su Zhaoen, Shunsuke Saito</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> We present Sapiens2, a model family of high-resolution transformers for human-centric vision focused on generalization, versatility, and high-fidelity outputs. Our model sizes range from 0.4 to 5 billion parameters, with native 1K resolution and hierarchical variants that support 4K. Sapiens2 substantially improves over its predecessor in both pretraining and post-training. First, to learn features that capture low-level details (for dense prediction) and high-level semantics (for zero-shot or few-label settings), we combine masked image reconstruction with self-distilled contrastive objectives. Our evaluations show that this unified pretraining objective is better suited for a wider range of downstream tasks. Second, along the data axis, we pretrain on a curated dataset of 1 billion high-quality human images and improve the quality and quantity of task annotations. Third, architecturally, we incorporate advances from frontier models that enable longer training schedules with improved stability. Our 4K models adopt windowed attention to reason over longer spatial context and are pretrained with 2K output resolution. Sapiens2 sets a new state-of-the-art and improves over the first generation on pose (+4 mAP), body-part segmentation (+24.3 mIoU), normal estimation (45.6% lower angular error) and extends to new tasks such as pointmap and albedo estimation. Code: https://github.com/facebookresearch/sapiens2</p> - https://arxiv.org/abs/2604.21681 - Thu, 23 Apr 2026 00:00:00 +0000 - - - DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction - https://arxiv.org/abs/2604.21518 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyan Su, Ruyi Zha, Danli Shi, Hongdong Li, Xuelian Cheng</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Neural representations (NRs), such as neural fields and 3D Gaussians, effectively model volumetric data in computed tomography (CT) but suffer from severe artifacts under sparse-view settings. To address this, we propose DiffNR, a novel framework that enhances NR optimization with diffusion priors. At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices. We integrate specialized conditioning layers into the network and develop tailored data curation strategies to support model finetuning. During reconstruction, SliceFixer periodically generates pseudo-reference volumes, providing auxiliary 3D perceptual supervision to fix underconstrained regions. Compared to prior methods that embed CT solvers into time-consuming iterative denoising, our repair-and-augment strategy avoids frequent diffusion model queries, leading to better runtime performance. Extensive experiments show that DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.</p> - https://arxiv.org/abs/2604.21518 - Thu, 23 Apr 2026 00:00:00 +0000 - - - SketchVLM: Vision language models can annotate images to explain thoughts and guide users - https://arxiv.org/abs/2604.22875 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Brandon Collins, Logan Bolton, Hung Huy Nguyen, Mohammad Reza Taesiri, Trung Bui, Anh Totti Nguyen</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models (VLMs) such as Gemini-3-Pro and GPT-5 only respond with text, which can be difficult for users to verify. We present SketchVLM, a training-free, model-agnostic framework that enables VLMs to produce non-destructive, editable SVG overlays on the input image to visually explain their answers. Across seven benchmarks spanning visual reasoning (maze navigation, ball-drop trajectory prediction, and object counting) and drawing (part labeling, connecting-the-dots, and drawing shapes around objects), SketchVLM improves visual reasoning task accuracy by up to +28.5 percentage points and annotation quality by up to 1.48x relative to image-editing and fine-tuned sketching baselines, while also producing annotations that are more faithful to the model's stated answer. We find that single-turn generation already achieves strong accuracy and annotation quality, and multi-turn generation opens up further opportunities for human-AI collaboration. An interactive demo and code are at https://sketchvlm.github.io/.</p> - https://arxiv.org/abs/2604.22875 - Thu, 23 Apr 2026 00:00:00 +0000 - - - Learning Evidence Highlighting for Frozen LLMs - https://arxiv.org/abs/2604.22565 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Jian Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers. HiLight avoids compressing or rewriting the input, which can discard or distort evidence, by training a lightweight Emphasis Actor to insert minimal highlight tags around pivotal spans in the unaltered context. A frozen Solver then performs downstream reasoning on the emphasized input. We cast highlighting as a weakly supervised decision-making problem and optimize the Actor with reinforcement learning using only the Solver's task reward, requiring no evidence labels and no access to or modification of the Solver. Across sequential recommendation and long-context question answering, HiLight consistently improves performance over strong prompt-based and automated prompt-optimization baselines. The learned emphasis policy transfers zero-shot to both smaller and larger unseen Solver families, including an API-based Solver, suggesting that the Actor captures genuine, reusable evidence structure rather than overfitting to a single backbone.</p> - https://arxiv.org/abs/2604.22565 - Fri, 24 Apr 2026 00:00:00 +0000 - - - dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model - https://arxiv.org/abs/2604.22152 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaxuan Li, Zhongyi Zhou, Yefei Chen, Yaokai Xue, Yichen Zhu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Evaluating robotics policies across thousands of environments and thousands of tasks is infeasible with existing approaches. This motivates the need for a new methodology for scalable robotics policy evaluation. In this paper, we propose dWorldEval, which uses a discrete diffusion world model as a scalable evaluation proxy for robotics policies. Specifically, dWorldEval maps all modalities - including vision, language, and robotic actions - into a unified token space, modeling them via a single transformer-based denoising network. In this paper, we propose dWorldEval, using a discrete diffusion world model as a scalable evaluation proxy for robotics policy. Specifically, it maps all modalities, including vision, language, and robotics action into a unified token space, then denoises them with a single transformer network. Building on this architecture, we employ a sparse keyframe memory to maintain spatiotemporal consistency. We also introduce a progress token that indicates the degree of task completion. At inference, the model jointly predicts future observations and progress token, allowing automatically determine success when the progress reaches 1. Extensive experiments demonstrate that dWorldEval significantly outperforms previous approaches, i.e., WorldEval, Ctrl-World, and WorldGym, on LIBERO, RoboTwin, and multiple real-robot tasks. It paves the way for a new architectural paradigm in building world simulators for robotics evaluation at scale.</p> - https://arxiv.org/abs/2604.22152 - Fri, 24 Apr 2026 00:00:00 +0000 - - - TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction - https://arxiv.org/abs/2604.22880 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengye Wang, Lin Fu, Zexi Kuang, Yilun Zhao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Existing document OCR largely targets plain text or Markdown, discarding the structural and executable properties that make LaTeX essential for scientific publishing. We study page-level reconstruction of scientific PDFs into compilable LaTeX and introduce TexOCR-Bench, a benchmark, and TexOCR-Train, a large-scale training corpus, for this task. TexOCR-Bench features a multi-dimensional evaluation suite that jointly assesses transcription fidelity, structural faithfulness, and end-to-end compilability. Leveraging TexOCR-Train, we train a 2B-parameter model, TexOCR, using supervised fine-tuning (SFT) and reinforcement learning (RL) with verifiable rewards derived from LaTeX unit tests that directly enforce compilability and referential integrity. Experiments across 21 frontier models on TexOCR-Bench show that existing systems frequently violate key document invariants, including consistent section structure, correct float placement, and valid label-reference links, which undermines compilation reliability and downstream usability. Our analysis further reveals that RL with verifiable rewards yields consistent improvements over SFT alone, particularly on structural and compilation metrics.</p> - https://arxiv.org/abs/2604.22880 - Fri, 24 Apr 2026 00:00:00 +0000 - - - AgentSearchBench: A Benchmark for AI Agent Search in the Wild - https://arxiv.org/abs/2604.22436 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22436.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Wu, Arastun Mammadli, Xiaoyu Zhang, Emine Yilmaz</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often compositional and execution-dependent, making them difficult to assess from textual descriptions alone. However, existing research and benchmarks typically assume well-specified functionalities, controlled candidate pools, or only executable task queries, leaving realistic agent search scenarios insufficiently studied. We introduce AgentSearchBench, a large-scale benchmark for agent search in the wild, built from nearly 10,000 real-world agents across multiple providers. The benchmark formalizes agent search as retrieval and reranking problems under both executable task queries and high-level task descriptions, and evaluates relevance using execution-grounded performance signals. Experiments reveal a consistent gap between semantic similarity and actual agent performance, exposing the limitations of description-based retrieval and reranking methods. We further show that lightweight behavioral signals, including execution-aware probing, can substantially improve ranking quality, highlighting the importance of incorporating execution signals into agent discovery. Our code is available at https://github.com/Bingo-W/AgentSearchBench.</p> - https://arxiv.org/abs/2604.22436 - Fri, 24 Apr 2026 00:00:00 +0000 - - - FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing - https://arxiv.org/abs/2604.22586 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ze Chen, Lan Chen, Yuanhang Li, Qi Mao</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We propose FlowAnchor, a training-free framework for stable and efficient inversion-free, flow-based video editing. Inversion-free editing methods have recently shown impressive efficiency and structure preservation in images by directly steering the sampling trajectory with an editing signal. However, extending this paradigm to videos remains challenging, often failing in multi-object scenes or with increased frame counts. We identify the root cause as the instability of the editing signal in high-dimensional video latent spaces, which arises from imprecise spatial localization and length-induced magnitude attenuation. To overcome this challenge, FlowAnchor explicitly anchors both where to edit and how strongly to edit. It introduces Spatial-aware Attention Refinement, which enforces consistent alignment between textual guidance and spatial regions, and Adaptive Magnitude Modulation, which adaptively preserves sufficient editing strength. Together, these mechanisms stabilize the editing signal and guide the flow-based evolution toward the desired target distribution. Extensive experiments demonstrate that FlowAnchor achieves more faithful, temporally coherent, and computationally efficient video editing across challenging multi-object and fast-motion scenarios. The project page is available at https://cuc-mipg.github.io/FlowAnchor.github.io/.</p> - https://arxiv.org/abs/2604.22586 - Fri, 24 Apr 2026 00:00:00 +0000 - - - Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets - https://arxiv.org/abs/2604.22294 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22294.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harshit Joshi, Priyank Shethia, Jadelynn Dao, Monica S. Lam</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A common workaround is to decompose documents into chunks and assemble answers from chunk-level outputs, but this introduces an aggregation bottleneck: as the number of chunks grows, systems must still combine and reason over an increasingly large body of extracted evidence. We present SLIDERS, a framework for question answering over long document collections through structured reasoning. SLIDERS extracts salient information into a relational database, enabling scalable reasoning over persistent structured state via SQL rather than concatenated text. To make this locally extracted representation globally coherent, SLIDERS introduces a data reconciliation stage that leverages provenance, extraction rationales, and metadata to detect and repair duplicated, inconsistent, and incomplete records. SLIDERS outperforms all baselines on three existing long-context benchmarks, despite all of them fitting within the context window of strong base LLMs, exceeding GPT-4.1 by 6.6 points on average. It also improves over the next best baseline by ~19 and ~32 points on two new benchmarks at 3.9M and 36M tokens, respectively.</p> - https://arxiv.org/abs/2604.22294 - Fri, 24 Apr 2026 00:00:00 +0000 - - - Video Analysis and Generation via a Semantic Progress Function - https://arxiv.org/abs/2604.22554 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gal Metzer, Sagi Polaczek, Ali Mahdavi-Amiri, Raja Giryes, Daniel Cohen-Or</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.</p> - https://arxiv.org/abs/2604.22554 - Fri, 24 Apr 2026 00:00:00 +0000 - - - From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company - https://arxiv.org/abs/2604.22446 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxu Yu, Yu Fu, Zhiyuan He, Yuxuan Huang, Lee Ka Yiu, Meng Fang, Weilin Luo, Jun Wang</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this reflects a deeper absence: a principled organisational layer that governs how a workforce of agents is assembled, governed, and improved over time, decoupled from what individual agents know. To fill this gap, we introduce OneManCompany (OMC), a framework that elevates multi-agent systems to the organisational level. OMC encapsulates skills, tools, and runtime configurations into portable agent identities called Talents, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven Talent Market enables on-demand recruitment, allowing the organisation to close capability gaps and reconfigure itself dynamically during execution. Organisational decision-making is operationalised through an Explore-Execute-Review (E^2R) tree search, which unifies planning, execution, and evaluation in a single hierarchical loop: tasks are decomposed top-down into accountable units and execution outcomes are aggregated bottom-up to drive systematic review and refinement. This loop provides formal guarantees on termination and deadlock freedom while mirroring the feedback mechanisms of human enterprises. Together, these contributions transform multi-agent systems from static, pre-configured pipelines into self-organising and self-improving AI organisations capable of adapting to open-ended tasks across diverse domains. Empirical evaluation on PRDBench shows that OMC achieves an 84.67% success rate, surpassing the state of the art by 15.48 percentage points, with cross-domain case studies further demonstrating its generality.</p> - https://arxiv.org/abs/2604.22446 - Fri, 24 Apr 2026 00:00:00 +0000 - - - Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond - https://arxiv.org/abs/2604.22748 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.22748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin, Lingdong Kong, Jize Zhang, Teng Tu, Weijian Ma, Ziqi Huang, Senqiao Yang, Wei Huang, Yeying Jin, Zhefan Rao, Jinhui Ye, Xinyu Lin, Xichen Zhang, Qisheng Hu, Shuai Yang, Leyang Shen, Wei Chow, Yifei Dong, Fengyi Wu, Quanyu Long, Bin Xia, Shaozuo Yu, Mingkang Zhu, Wenhu Zhang, Jiehui Huang, Haokun Gui, Haoxuan Che, Long Chen, Qifeng Chen, Wenxuan Zhang, Wenya Wang, Xiaojuan Qi, Yang Deng, Yanwei Li, Mike Zheng Shou, Zhi-Qi Cheng, See-Kiong Ng, Ziwei Liu, Philip Torr, Jiaya Jia</p><p><b>Upvotes:</b> 221</p><p><b>Summary:</b> As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate.</p> - https://arxiv.org/abs/2604.22748 - Fri, 24 Apr 2026 00:00:00 +0000 - - - IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance - https://arxiv.org/abs/2604.23446 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chathurangi Shyalika, Dhaval Patel, Amit Sheth</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Industrial maintenance environments increasingly rely on AI systems to assist operators in understanding asset behavior, diagnosing failures, and evaluating interventions. Although large language models (LLMs) enable fluent natural-language interaction, deployed maintenance assistants routinely produce generic explanations that are weakly grounded in telemetry, omit verifiable provenance, and offer no testable support for counterfactual or action-oriented reasoning that undermine trust in safety-critical settings. We present IndustryAssetEQA, a neurosymbolic operational intelligence system that combines episodic telemetry representations with a Failure Mode Effects Analysis Knowledge Graph (FMEA-KG) to enable Embodied Question Answering (EQA) over industrial assets. We evaluate on four datasets covering four industrial asset types, including rotating machinery, turbofan engines, hydraulic systems, and cyber-physical production systems. Compared to LLM-only baselines, IndustryAssetEQA improves structural validity by up to 0.51, counterfactual accuracy by up to 0.47, and explanation entailment by 0.64, while reducing severe expert-rated overclaims from 28% to 2% (approximately 93% reduction). Code, datasets, and the FMEA-KG are available at https://github.com/IBM/AssetOpsBench/tree/IndustryAssetEQA/IndustryAssetEQA.</p> - https://arxiv.org/abs/2604.23446 + OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models + https://arxiv.org/abs/2605.00877 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yida Xue, Ningyu Zhang, Tingwei Wu, Zhe Ma, Daxiong Ji, Zhao Wang, Guozhou Zheng, Huajun Chen</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and weakly labeled characteristics, lacking unified schemas and semantic alignment. Although Multimodal Large Language Models (MLLMs) have achieved remarkable success in general domains, their application to ocean science remains severely constrained by the absence of large-scale, well-aligned multimodal datasets tailored to marine environments. To bridge this gap, we introduce OceanPile, a large-scale multimodal corpus designed for ocean foundation models. It comprises three key components: OceanCorpus, a unified collection integrating sonar data, underwater imagery, marine science visuals, and scientific text from diverse authoritative sources; OceanInstruction, a high-quality instruction dataset synthesized via a novel pipeline guided by a hierarchical Ocean Concept Knowledge Graph; and OceanBenchmark, a manually curated evaluation benchmark for rigorous assessment. We establish a multi-stage quality control process to ensure scientific validity and alignment across modalities. Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs.</p> + https://arxiv.org/abs/2605.00877 Sat, 25 Apr 2026 00:00:00 +0000 - Discovering Agentic Safety Specifications from 1-Bit Danger Signals - https://arxiv.org/abs/2604.23210 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23210.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Víctor Gallego</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iteratively generates action plans, receives sparse binary danger warnings, and evolves a natural language behavioral specification through reflection. Unlike standard LLM reflection methods that rely on rich textual feedback (e.g., compiler errors or detailed environment responses), EPO-Safe demonstrates that LLMs can perform safety reasoning from a strictly impoverished signal in structured, low-dimensional environments: the agent never observes the hidden performance function R^*, only a single bit per timestep indicating that an action was unsafe. We evaluate on five AI Safety Gridworlds (Leike et al., 2017) and five text-based scenario analogs where visible reward R may diverge from R^*. EPO-Safe discovers safe behavior within 1-2 rounds (5-15 episodes), producing human-readable specifications with correct explanatory hypotheses about hazards (e.g., "X cells are directionally hazardous: entering from the north is dangerous"). Critically, we show that standard reward-driven reflection actively degrades safety: agents reflecting on reward alone use the loop to justify and accelerate reward hacking, proving that reflection must be paired with a dedicated safety channel to discover hidden constraints. We further evaluate robustness to noisy oracles: even when 50% of non-dangerous steps produce spurious warnings, mean safety performance degrades by only 15% on average, though sensitivity is environment-dependent, as cross-episode reflection naturally filters inconsistent signals. Each evolved specification functions as an auditable set of grounded behavioral rules discovered autonomously through interaction, rather than authored by humans as in Constitutional AI (Bai et al., 2022).</p> - https://arxiv.org/abs/2604.23210 - Sat, 25 Apr 2026 00:00:00 +0000 - - - ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation - https://arxiv.org/abs/2604.23099 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizheng Huang, Wenjun Zeng, Aditi Kumaresan, Zi Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models and benchmarks. We propose ProEval, a proactive evaluation framework that leverages transfer learning to efficiently estimate performance and identify failure cases. ProEval employs pre-trained Gaussian Processes (GPs) as surrogates for the performance score function, mapping model inputs to metrics such as the severity of errors or safety violations. By framing performance estimation as Bayesian quadrature (BQ) and failure discovery as superlevel set sampling, we develop uncertainty-aware decision strategies that actively select or synthesize highly informative inputs for testing. Theoretically, we prove that our pre-trained GP-based BQ estimator is unbiased and bounded. Empirically, extensive experiments on reasoning, safety alignment, and classification benchmarks demonstrate that ProEval is significantly more efficient than competitive baselines. It requires 8-65x fewer samples to achieve estimates within 1% of the ground truth, while simultaneously revealing more diverse failure cases under a stricter evaluation budget.</p> - https://arxiv.org/abs/2604.23099 - Sat, 25 Apr 2026 00:00:00 +0000 - - - V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think - https://arxiv.org/abs/2604.23380 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23380.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingda Tang, Yuhui Zhang, Xiaohan Wang, Jiayuan Mao, Ludwig Schmidt, Serena Yeung-Levy</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is hindered by the intractable likelihoods of these models. Prior work therefore either optimizes an induced Markov decision process (MDP) over sampling trajectories, which is stable but inefficient, or uses likelihood surrogates based on the diffusion evidence lower bound (ELBO), which have so far underperformed on visual generation. Our key insight is that the ELBO-based approach can, in fact, be made both stable and efficient. By reducing surrogate variance and controlling gradient steps, we show that this approach can beat MDP-based methods. To this end, we introduce Variational GRPO (V-GRPO), a method that integrates ELBO-based surrogates with the Group Relative Policy Optimization (GRPO) algorithm, alongside a set of simple yet essential techniques. Our method is easy to implement, aligns with pretraining objectives, and avoids the limitations of MDP-based methods. V-GRPO achieves state-of-the-art performance in text-to-image synthesis, while delivering a 2times speedup over MixGRPO and a 3times speedup over DiffusionNFT.</p> - https://arxiv.org/abs/2604.23380 - Sat, 25 Apr 2026 00:00:00 +0000 - - - For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs - https://arxiv.org/abs/2508.10180 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2508.10180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenlong Deng, Qi Zeng, Jiaming Zhang, Minghui Chen, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Data valuation is essential for enhancing the transparency and accountability of large language models (LLMs) and vision-language models (VLMs). However, existing methods typically rely on gradient computations, making them computationally prohibitive for billion-parameter models and precluding batch parallelization. In this work, we introduce For-Value, a forward-only data valuation framework that enables efficient batch-scalable value estimation while maintaining effectiveness. Leveraging the expressive power of pretrained LLMs/VLMs, we theoretically demonstrate that data valuation can be captured by the alignment between the final hidden representations and prediction errors at the last layer. In light of this insight, For-Value computes data value using a simple closed-form expression with a single forward pass, eliminating the need for costly backpropagation and enabling efficient batch calculating at scale. Extensive experiments show that For-Value matches or outperforms gradient-based baselines in detecting influential data and mislabeled data, while achieving significant efficiency improvements.</p> - https://arxiv.org/abs/2508.10180 - Sat, 25 Apr 2026 00:00:00 +0000 - - - Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation - https://arxiv.org/abs/2604.23600 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tanay Kumar, Shreya Gautam, Aman Chadha, Vinija Jain, Francesco Pierri</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where models are prompted to adopt specific personas when interacting with users. While persona conditioning can improve user experience and engagement, it also raises concerns about how personality cues may interact with gender biases and stereotypes. In this work, we present a controlled study of persona-conditioned story generation in English and Hindi, where each story portrays a working professional in India producing context-specific artifacts (e.g., lesson plans, reports, letters) under systematically varied persona gender, occupational role, and personality traits from the HEXACO and Dark Triad frameworks. Across 23,400 generated stories from six state-of-the-art LLMs, we find that personality traits are significantly associated with both the magnitude and direction of gender bias. In particular, Dark Triad personality traits are consistently associated with higher gender-stereotypical representations compared to socially desirable HEXACO traits, though these associations vary across models and languages. Our findings demonstrate that gender bias in LLMs is not static but context-dependent. This suggests that persona-conditioned systems used in real-world applications may introduce uneven representational harms, reinforcing gender stereotypes in generated educational, professional, or social content.</p> - https://arxiv.org/abs/2604.23600 - Sun, 26 Apr 2026 00:00:00 +0000 - - - RaV-IDP: A Reconstruction-as-Validation Framework for Faithful Intelligent Document Processing - https://arxiv.org/abs/2604.23644 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pritesh Jha</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of existing pipelines is that extraction output is produced without any intrinsic mechanism to verify whether it faithfully represents the source. Model-internal confidence scores measure inference certainty, not correspondence to the document, and extraction errors pass silently into downstream consumers. We present Reconstruction as Validation (RaV-IDP), a document processing pipeline that introduces reconstruction as a first-class architectural component. After each entity is extracted, a dedicated reconstructor renders the extracted representation back into a form comparable to the original document region, and a comparator scores fidelity between the reconstruction and the unmodified source crop. This fidelity score is a grounded, label-free quality signal. When fidelity falls below a per-entity-type threshold, a structured GPT-4.1 vision fallback is triggered and the validation loop repeats. We enforce a bootstrap constraint: the comparator always anchors against the original document region, never against the extraction, preventing the validation from becoming circular. We further propose a per-stage evaluation framework pairing each pipeline component with an appropriate benchmark. The code pipeline is publicly available at https://github.com/pritesh-2711/RaV-IDP for experimentation and use.</p> - https://arxiv.org/abs/2604.23644 - Sun, 26 Apr 2026 00:00:00 +0000 - - - Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation - https://arxiv.org/abs/2604.23604 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Simone Mosco, Daniel Fusaro, Alberto Pretto</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly Segmentation. However, research in the 3D field remains limited, with most existing approaches applying post-processing techniques from 2D vision. To cover this lack, we propose a new efficient approach that directly operates in the feature space, modeling the feature distribution of inlier classes to constrain anomalous samples. Moreover, the only publicly available 3D LiDAR anomaly segmentation dataset contains simple scenarios, with few anomaly instances, and exhibits a severe domain gap due to its sensor resolution. To bridge this gap, we introduce a set of mixed real-synthetic datasets for 3D LiDAR anomaly segmentation, built upon established semantic segmentation benchmarks, with multiple out-of-distribution objects and diverse, complex environments. Extensive experiments demonstrate that our approach achieves state-of-the-art and competitive results on the existing real-world dataset and the newly introduced mixed datasets, respectively, validating the effectiveness of our method and the utility of the proposed datasets. Code and datasets are available at https://simom0.github.io/lido-page/.</p> - https://arxiv.org/abs/2604.23604 - Sun, 26 Apr 2026 00:00:00 +0000 - - - PageGuide: Browser extension to assist users in navigating a webpage and locating information - https://arxiv.org/abs/2604.23772 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23772.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tin Nguyen, Thang T. Truong, Runtao Zhou, Trung Bui, Chirag Agarwal, Anh Totti Nguyen</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Users browsing the web daily struggle to quickly locate relevant information in cluttered pages, complete unfamiliar multi-step tasks, and stay focused amid distracting content. State-of-the-art AI assistants (e.g., ChatGPT, Gemini, Claude) and browser agents (e.g., OpenAI Operator, Browser Use) can answer questions and automate actions, yet they return answers without showing where the information comes from on the page, forcing users to manually verify results and blindly trust every automated steps. We present PageGuide, a browser extension that grounds LLM answers directly in the HTML DOM via visual overlays, addressing three core user needs: (a) Find-locating and highlighting relevant evidence in-situ so users can instantly verify answers on the page; (b) Guide-showing step-by-step instructions (e.g. how to change password) one at a time so users can follow and perform actions by themselves; and (c) Hide-hiding distracting content-giving users a chance to decide to hide an element or not. In a user study (N=94), PageGuide outperform unaided browsing across all modes: Hide accuracy improve by 26 percentage points (86.7% relative gain) and task completion time drops by 70%; Guide completion rate increases by 30 percentage points; and Find reduces manual search effort, with Ctrl+F usage falling by 80% and task time decreasing by 19%. Code and demo is at: pageguide.github.io.</p> - https://arxiv.org/abs/2604.23772 - Sun, 26 Apr 2026 00:00:00 +0000 - - - ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents - https://arxiv.org/abs/2604.23781 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23781.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanqing Meng, Lingxiao Du, Zijian Wu, Guanzheng Chen, Xiangyan Liu, Jiaqi Liao, Chonghe Jiang, Zhenglin Wan, Jiawei Gu, Pengfei Zhou, Rui Huang, Ziqi Zhao, Shengyuan Ding, Ailing Yu, Bo Peng, Bowei Xia, Hao Sun, Haotian Liang, Ji Xie, Jiajun Chen, Jiajun Song, Liu Yang, Ming Xu, Qionglin Qiu, Runhao Fu, Shengfang Zhai, Shijian Wang, Tengfei Ma, Tianyi Wu, Weiyang Jin, Yan Wang, Yang Dai, Yao Lai, Youwei Shu, Yue Liu, Yunzhuo Hao, Yuwei Niu, Jinkai Huang, Jiayuan Zhuo, Zhennan Shen, Linyu Wu, Cihang Xie, Yuyin Zhou, Jiaheng Zhang, Zeyu Zheng, Mengkang Hu, Michael Qizhe Shieh</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change independently of the agent: new emails arrive, calendar entries shift, knowledge-base records are updated, and evidence appears across images, scanned PDFs, audio, video, and spreadsheets. Existing benchmarks do not adequately evaluate this setting because they typically run within a single static episode and remain largely text-centric. We introduce , a benchmark for coworker agents built around multi-turn multi-day tasks, a stateful sandboxed service environment whose state evolves between turns, and rule-based verification. The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services (filesystem, email, calendar, knowledge base, spreadsheet) and scored by 1537 deterministic Python checkers over post-execution service state; no LLM-as-judge is invoked during scoring. We benchmark seven frontier agent systems. The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0\%, indicating that partial progress is common while complete end-to-end workflow completion remains rare. Turn-level analysis shows that performance drops after the first exogenous environment update, highlighting adaptation to changing state as a key open challenge. We release the benchmark, evaluation harness, and construction pipeline to support reproducible coworker-agent evaluation.</p> - https://arxiv.org/abs/2604.23781 - Sun, 26 Apr 2026 00:00:00 +0000 - - - Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms - https://arxiv.org/abs/2604.23775 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23775.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Li, Bo Yin, Weiqi Huang, Ruhao Liu, Bojun Zou, Runpeng Yu, Jingwen Ye, Weihao Yu, Xinchao Wang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied nature of VLA systems, including irreversible physical consequences, a multimodal attack surface across vision, language, and state, real-time latency constraints on defense, error propagation over long-horizon trajectories, and vulnerabilities in the data supply chain. Yet the literature remains fragmented across robotic learning, adversarial machine learning, AI alignment, and autonomous systems safety. This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models. We organize the field along two parallel timing axes, attack timing (training-time vs. inference-time and defense timing (training-time vs. inference-time, linking each class of threat to the stage at which it can be mitigated. We first define the scope of VLA safety, distinguishing it from text-only LLM safety and classical robotic safety, and review the foundations of VLA models, including architectures, training paradigms, and inference mechanisms. We then examine the literature through four lenses: Attacks, Defenses, Evaluation, and Deployment. We survey training-time threats such as data poisoning and backdoors, as well as inference-time attacks including adversarial patches, cross-modal perturbations, semantic jailbreaks, and freezing attacks. We review training-time and runtime defenses, analyze existing benchmarks and metrics, and discuss safety challenges across six deployment domains. Finally, we highlight key open problems, including certified robustness for embodied trajectories, physically realizable defenses, safety-aware training, unified runtime safety architectures, and standardized evaluation.</p> - https://arxiv.org/abs/2604.23775 - Sun, 26 Apr 2026 00:00:00 +0000 - - - Improving Vision-language Models with Perception-centric Process Reward Models - https://arxiv.org/abs/2604.24583 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24583.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yingqian Min, Kun Zhou, Yifan Li, Yuhuan Wu, Han Peng, Yifan Du, Wayne Xin Zhao, Min Yang, Ji-Rong Wen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and correct errors within the reasoning chain. To this end, we propose Perceval, a process reward model (PRM) that enables token-level error grounding, which can extract image-related claims from the response and compare them one by one with the visual evidence in the image, ultimately returning claims that contain perceptual errors. Perceval is trained with perception-intensive supervised training data. We then integrate Perceval into the RL training process to train the policy models. Specifically, compared to traditional GRPO, which applies sequence-level advantages, we apply token-level advantages by targeting penalties on hallucinated spans identified by Perceval, thus enabling fine-grained supervision signals. In addition to augmenting the training process, Perceval can also assist VLMs during the inference stage. Using Perceval, we can truncate the erroneous portions of the model's response, and then either have the model regenerate the response directly or induce the model to reflect on its previous output. This process can be repeated multiple times to achieve test-time scaling. Experiments show significant improvements on benchmarks from various domains across multiple reasoning VLMs trained with RL, highlighting the promise of perception-centric supervision as a general-purpose strategy. For test-time scaling, it also demonstrates consistent performance gains over other strategies, such as major voting. Our code and data will be publicly released at https://github.com/RUCAIBox/Perceval.</p> - https://arxiv.org/abs/2604.24583 + Diffusion Model as a Generalist Segmentation Learner + https://arxiv.org/abs/2604.24575 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24575.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoxiao Wang, Antao Xiang, Haiyang Sun, Peilin Sun, Changhao Pan, Yifu Chen, Minjie Hong, Weijie Wang, Shuang Chen, Yue Chen, Zhou Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditioned semantic and open-vocabulary segmentation, and this approach can be generalized to various downstream tasks to make a general-purpose diffusion segmentation framework. Concretely, we introduce DiGSeg (Diffusion Models as a Generalist Segmentation Learner), which repurposes a pretrained diffusion model into a unified segmentation framework. Our approach encodes the input image and ground-truth mask into the latent space and concatenates them as conditioning signals for the diffusion U-Net. A parallel CLIP-aligned text pathway injects language features across multiple scales, enabling the model to align textual queries with evolving visual representations. This design transforms an off-the-shelf diffusion backbone into a universal interface that produces structured segmentation masks conditioned on both appearance and arbitrary text prompts. Extensive experiments demonstrate state-of-the-art performance on standard semantic segmentation benchmarks, as well as strong open-vocabulary generalization and cross-domain transfer to medical, remote sensing, and agricultural scenarios-without domain-specific architectural customization. These results indicate that modern diffusion backbones can serve as generalist segmentation learners rather than pure generators, narrowing the gap between visual generation and visual understanding.</p> + https://arxiv.org/abs/2604.24575 Mon, 27 Apr 2026 00:00:00 +0000 - Improving Robustness of Tabular Retrieval via Representational Stability - https://arxiv.org/abs/2604.24040 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao, Soham Dan, Vivek Gupta</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain unchanged. We show that semantically equivalent serializations, such as csv, tsv, html, markdown, and ddl, can produce substantially different embeddings and retrieval results across multiple benchmarks and retriever families. To address this instability, we treat serialization embedding as noisy views of a shared semantic signal and use its centroid as a canonical target representation. We show that centroid averaging suppresses format-specific variation and can recover the semantic content common to different serializations when format-induced shifts differ across tables. Empirically, centroid representations outrank individual formats in aggregate pairwise comparisons across MPNet, BGE-M3, ReasonIR, and SPLADE. We further introduce a lightweight residual bottleneck adapter on top of a frozen encoder that maps single-serialization embeddings towards centroid targets while preserving variance and enforcing covariance regularization. The adapter improves robustness for several dense retrievers, though gains are model-dependent and weaker for sparse lexical retrieval. These results identify serialization sensitivity as a major source of retrieval variance and show the promise of post hoc geometric correction for serialization-invariant table retrieval. Our code, datasets, and models are available at https://github.com/KBhandari11/Centroid-Aligned-Table-Retrieval{https://github.com/KBhandari11/Centroid-Aligned-Table-Retrieval}.</p> - https://arxiv.org/abs/2604.24040 + Soft Anisotropic Diagrams for Differentiable Image Representation + https://arxiv.org/abs/2604.21984 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Laki Iinbor, Zhiyang Dou, Wojciech Matusik</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. In SAD, each site specifies an anisotropic metric and an additively weighted distance score, and we compute pixel colors as a softmax blend over a small per-pixel top-K subset of sites. We induce a soft anisotropic additively weighted Voronoi partition (i.e., an Apollonius diagram) with learnable per-site temperatures, preserving informative gradients while allowing clear, content-aligned boundaries and explicit ownership. Such a formulation enables efficient rendering by maintaining a per-query top-K map that approximates nearest neighbors under the same shading score, allowing GPU-friendly, fixed-size local computation. We update this list using our top-K propagation scheme inspired by jump flooding, augmented with stochastic injection to provide probabilistic global coverage. Training follows a GPU-first pipeline with gradient-weighted initialization, Adam optimization, and adaptive budget control through densification and pruning. Across standard benchmarks, SAD consistently outperforms Image-GS and Instant-NGP at matched bitrate. On Kodak, SAD reaches 46.0 dB PSNR with 2.2 s encoding time (vs. 28 s for Image-GS), and delivers 4-19 times end-to-end training speedups over state-of-the-art baselines. We demonstrate the effectiveness of SAD by showcasing the seamless integration with differentiable pipelines for forward and inverse problems, efficiency of fast random access, and compact storage.</p> + https://arxiv.org/abs/2604.21984 Mon, 27 Apr 2026 00:00:00 +0000 - AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark - https://arxiv.org/abs/2604.24441 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24441.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongxin Li, Xiping Wang, Jingran Su, Zheng Ju, Yuntao Chen, Qing Li, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Autonomous agents capable of navigating Graphical User Interfaces (GUIs) hold the potential to revolutionize digital productivity. However, achieving true digital autonomy extends beyond reactive element matching; it necessitates a predictive mental model of interface dynamics and the ability to foresee the "digital world state" resulting from interactions. Despite the perceptual capabilities of modern Vision-Language Models (VLMs), existing benchmarks remain bifurcated (focusing either on black-box task completion or static, shallow grounding), thereby failing to assess whether agents truly comprehend the implicit functionality and transition logic of GUIs. To bridge this gap, we introduce AutoGUI-v2, a comprehensive benchmark designed to evaluate deep GUI functionality understanding and interaction outcome prediction. We construct the benchmark using a novel VLM-human collaborative pipeline that recursively parses multi-platform screenshots into hierarchical functional regions to generate diverse evaluation tasks. Providing 2,753 tasks across six operating systems, AutoGUI-v2 rigorously tests agents on region and element-level semantics, grounding, and dynamic state prediction. Our evaluation reveals a striking dichotomy in VLMs: while open-source models fine-tuned on agent data (e.g., Qwen3-VL) excel at functional grounding, commercial models (e.g., Gemini-2.5-Pro-Thinking) dominate in functionality captioning. Crucially, all models struggle with complex interaction logic of uncommon actions, highlighting that deep functional understanding remains a significant hurdle. By systematically measuring these foundational capabilities, AutoGUI-v2 offers a new lens for advancing the next generation of GUI agents.</p> - https://arxiv.org/abs/2604.24441 + From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills + https://arxiv.org/abs/2604.24026 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiliang Liang, Hansi Wang, Zhong Liang, Yang Liu</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL.md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.</p> + https://arxiv.org/abs/2604.24026 Mon, 27 Apr 2026 00:00:00 +0000 - Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization - https://arxiv.org/abs/2604.24952 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24952.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinxin Liu, Ming Li, Zonglin Lyu, Yuzhang Shang, Chen Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that excel in some dimensions but are deficient in others are simply marked as winner or loser. We theoretically demonstrate that compressing multi-dimensional preferences into binary labels generates conflicting gradient signals that misguide Diffusion Direct Preference Optimization (DPO). To address this, we propose Semi-DPO, a semi-supervised approach that treats consistent pairs as clean labeled data and conflicting ones as noisy unlabeled data. Our method starts by training on a consensus-filtered clean subset, then uses this model as an implicit classifier to generate pseudo-labels for the noisy set for iterative refinement. Experimental results demonstrate that Semi-DPO achieves state-of-the-art performance and significantly improves alignment with complex human preferences, without requiring additional human annotation or explicit reward models during training. We will release our code and models at: https://github.com/L-CodingSpace/semi-dpo</p> - https://arxiv.org/abs/2604.24952 + X2SAM: Any Segmentation in Images and Videos + https://arxiv.org/abs/2605.00891 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00891.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Wang, Limeng Qiao, Chi Zhang, Lin Ma, Guanglu Wan, Xiangyuan Lan, Xiaodan Liang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM series produce high-quality masks, but they rely on low-level visual prompts and cannot natively interpret complex conversational instructions. Existing segmentation MLLMs narrow this gap, but are usually specialized for either images or videos and rarely support both textual and visual prompts in one interface. We introduce X2SAM, a unified segmentation MLLM that extends any-segmentation capabilities from images to videos. Given conversational instructions and visual prompts, X2SAM couples an LLM with a Mask Memory module that stores guided vision features for temporally consistent video mask generation. The same formulation supports generic, open-vocabulary, referring, reasoning, grounded conversation generation, interactive, and visual grounded segmentation across image and video inputs. We further introduce the Video Visual Grounded (V-VGD) segmentation benchmark, which evaluates whether a model can segment object tracks in videos from interactive visual prompts. With a unified joint training strategy over heterogeneous image and video datasets, X2SAM delivers strong video segmentation performance, remains competitive on image segmentation benchmarks, and preserves general image and video chat ability.</p> + https://arxiv.org/abs/2605.00891 Mon, 27 Apr 2026 00:00:00 +0000 - GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction - https://arxiv.org/abs/2604.23941 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongxin Li, Yuntao Chen, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Graphical User Interface (GUI) element grounding (precisely locating elements on screenshots based on natural language instructions) is fundamental for agents interacting with GUIs. Deploying this capability directly on resource-constrained devices like mobile phones is increasingly critical for GUI agents requiring low latency. However, this goal faces a significant challenge, as current visual grounding methods typically employ large vision-language model (VLM) (more than 2.5B parameters), making them impractical for on-device execution due to memory and computational constraints. To address this, this paper introduces GoClick, a lightweight GUI element grounding VLM with only 230M parameters that achieves excellent visual grounding accuracy, even on par with significantly larger models. Simply downsizing existing decoder-only VLMs is a straightforward way to design a lightweight model, but our experiments reveal that this approach yields suboptimal results. Instead, we select an encoder-decoder architecture, which outperforms decoder-only alternatives at small parameter scales for GUI grounding tasks. Additionally, the limited capacity of small VLMs encourages us to develop a Progressive Data Refinement pipeline that utilizes task type filtering and data ratio adjustment to extract a high-quality 3.8M-sample core set from a 10.8M raw dataset. Training GoClick using this core set brings notable grounding accuracy gains. Our experiments show that GoClick excels on multiple GUI element grounding benchmarks while maintaining a small size and high inference speed. GoClick also enhances GUI agent performance when integrated into a device-cloud collaboration framework, where GoClick helps cloud-based task planners perform precise element localization and achieve higher success rates. We hope our method serves as a meaningful exploration within the GUI agent community.</p> - https://arxiv.org/abs/2604.23941 - Mon, 27 Apr 2026 00:00:00 +0000 - - - How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models - https://arxiv.org/abs/2604.21106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.21106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We measure how much one extra recurrence is worth to a looped (depth-recurrent) language model, in equivalent unique parameters. From an iso-depth sweep of 116 pretraining runs across recurrence counts r in {1, 2, 4, 8} spanning {sim}50times in training compute, we fit a joint scaling law L = E + A,(N_once + r^φ N_rec)^{-α} + B,D^{-β} and recover a new recurrence-equivalence exponent φ= 0.46. Intuitively, φ tells us whether looping a block r times is equivalent in validation loss to r unique blocks of a non-looped model (full equivalence, φ{=}1) or to a single block run repeatedly with no capacity gain (φ{=}0). Our φ= 0.46 sits in between, so each additional recurrence predictably increases validation loss at matched training compute. For example, at r{=}4 a 410M looped model performs on par with a 580M non-looped model, but incurs the training cost of a 1B non-looped one. We demonstrate the utility of φ as a measurement tool on two probes. Truncated backpropagation lowers φ to 0.38, indicating that the loop mechanism is poorly trained under truncation, even though validation loss decreases. Conversely, hyperconnections raise φ to 0.65, a genuine capacity gain. Our method applies to any looped LM and separates true loop improvements from token-budget gains.</p> - https://arxiv.org/abs/2604.21106 - Mon, 27 Apr 2026 00:00:00 +0000 - - - TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents - https://arxiv.org/abs/2604.24005 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Wang, Wenhao Zhang, Weijie Shi, Yaliang Li, James Cheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings remains underexplored. In this work, we identify a key limitation of vanilla OPD in such settings, which we term Trajectory-Level KL Instability. Specifically, we observe that KL divergence increases together with a drop in success rate, and even after convergence, the KL remains high, leading to unstable training. This instability arises from inter-turn error compounding: as errors accumulate, the student is driven beyond the teacher's effective support, rendering the supervision signal unreliable. To address this, we propose TCOD (Temporal Curriculum On-Policy Distillation), a simple yet effective framework that controls the trajectory depth exposed to the student and progressively expands it from short to long with a curriculum schedule.Experimental results across four student-teacher pairs on three multi-turn agent benchmarks (ALFWorld, WebShop, ScienceWorld) show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD. Further evaluations show that TCOD can even surpass the teacher's performance and generalize to tasks on which the teacher fails.</p> - https://arxiv.org/abs/2604.24005 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Stabilizing Efficient Reasoning with Step-Level Advantage Selection - https://arxiv.org/abs/2604.24003 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24003.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Wang, Xiaodong Yu, Jialian Wu, Jiang Liu, Ximeng Sun, Mohit Bansal, Zicheng Liu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead through length-based rewards or pruning, many approaches are post-trained under a much shorter context window than base-model training, a factor whose effect has not been systematically isolated. We first show that short-context post-training alone, using standard GRPO without any length-aware objective, already induces substantial reasoning compression-but at the cost of increasingly unstable training dynamics and accuracy degradation. To address this, we propose Step-level Advantage Selection (SAS), which operates at the reasoning-step level and assigns a zero advantage to low-confidence steps in correct rollouts and to high-confidence steps in verifier-failed rollouts, where failures often arise from truncation or verifier issues rather than incorrect reasoning. Across diverse mathematical and general reasoning benchmarks, SAS improves average Pass@1 accuracy by 0.86 points over the strongest length-aware baseline while reducing average reasoning length by 16.3%, yielding a better accuracy-efficiency trade-off.</p> - https://arxiv.org/abs/2604.24003 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data - https://arxiv.org/abs/2604.24479 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammadmehdi Ataei, Farzaneh Askari, Kamal Rahimi Malekshan, Pradeep Kumar Jayaraman</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Computer-Aided Design (CAD) models are defined by their construction history: a parametric recipe that encodes design intent. However, existing large-scale 3D datasets predominantly consist of boundary representations (B-Reps) or meshes, stripping away this critical procedural information. To address this scarcity, we introduce Zero-to-CAD, a scalable framework for synthesizing executable CAD construction sequences. We frame synthesis as an agentic search problem: by embedding a large language model (LLM) within a feedback-driven CAD environment, our system iteratively generates, executes, and validates code using tools and documentation lookup to promote geometric validity and operation diversity. This agentic approach enables the synthesis of approximately one million executable, readable, editable CAD sequences, covering a rich vocabulary of operations beyond sketch-and-extrude workflows. We also release a curated subset of 100,000 high-quality models selected for geometric diversity. To demonstrate the dataset's utility, we fine-tune a vision-language model on our synthetic data to reconstruct editable CAD programs from multi-view images, outperforming strong baselines, including GPT-5.2, and effectively bootstrapping sequence generation capabilities without real construction-history training data. Zero-to-CAD bridges the gap between geometric scale and parametric interpretability, offering a vital resource for the next generation of CAD AI.</p> - https://arxiv.org/abs/2604.24479 - Mon, 27 Apr 2026 00:00:00 +0000 - - - A Survey on LLM-based Conversational User Simulation - https://arxiv.org/abs/2604.24977 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24977.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo Ni, Leyao Wang, Yu Wang, Branislav Kveton, Franck Dernoncourt, Yu Xia, Hongjie Chen, Reuben Leura, Samyadeep Basu, Subhojyoti Mukherjee, Puneet Mathur, Nesreen Ahmed, Junda Wu, Li Li, Huixin Zhang, Ruiyi Zhang, Tong Yu, Sungchul Kim, Jiuxiang Gu, Zhengzhong Tu, Alexa Siu, Zichao Wang, David Seunghyun Yoon, Nedim Lipka, Namyong Park, Zihao Lin, Trung Bui, Yue Zhao, Tyler Derr, Ryan A. Rossi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communication, forms the foundation of social interaction and behavior. Consequently, simulating conversational behavior has become a key area of study. Recent advancements in large language models (LLMs) have significantly catalyzed progress in this domain by enabling high-fidelity generation of synthetic user conversation. In this paper, we survey recent advancements in LLM-based conversational user simulation. We introduce a novel taxonomy covering user granularity and simulation objectives. Additionally, we systematically analyze core techniques and evaluation methodologies. We aim to keep the research community informed of the latest advancements in conversational user simulation and to further facilitate future research by identifying open challenges and organizing existing work under a unified framework.</p> - https://arxiv.org/abs/2604.24977 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion - https://arxiv.org/abs/2604.24351 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongjie Duan, Hong Zhang, Yingda Chen</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse infrastructure across tasks, transfer capabilities across backbones, or compose multiple controls within a single generation pipeline. We present Diffusion Templates, a unified and open plugin framework that decouples base-model inference from controllable capability injection. The framework is organized around three components: Template models that map arbitrary task-specific inputs to an intermediate capability representation, a Template cache that functions as a standardized interface for capability injection, and a Template pipeline that loads, merges, and injects one or more Template caches into the base diffusion runtime. Because the interface is defined at the systems level rather than tied to a specific control architecture, heterogeneous capability carriers such as KV-Cache and LoRA can be supported under the same abstraction. Based on this design, we build a diverse model zoo spanning structural control, brightness adjustment, color adjustment, image editing, super-resolution, sharpness enhancement, aesthetic alignment, content reference, local inpainting, and age control. These case studies show that Diffusion Templates can unify a broad range of controllable generation tasks while preserving modularity, composability, and practical extensibility across rapidly evolving diffusion backbones. All resources will be open sourced, including code, models, and datasets.</p> - https://arxiv.org/abs/2604.24351 - Mon, 27 Apr 2026 00:00:00 +0000 - - - OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer - https://arxiv.org/abs/2604.24762 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24762.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyang Wang, Guangyi Xu, Zhipeng Tang, Jiahui Zhang, Zezhou Cheng</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the literature, existing state-of-the-art methods often produce non-interpretable boundaries on transitions, miss subtle yet harmful discontinuities, and rely on noisy, low-diversity annotations and outdated benchmarks. To alleviate these limitations, we propose OmniShotCut to formulate SBD as structured relational prediction, jointly estimating shot ranges with intra-shot relations and inter-shot relations, by a shot query-based dense video Transformer. To avoid imprecise manual labeling, we adopt a fully synthetic transition synthesis pipeline that automatically reproduces major transition families with precise boundaries and parameterized variants. We also introduce OmniShotCutBench, a modern wide-domain benchmark enabling holistic and diagnostic evaluation.</p> - https://arxiv.org/abs/2604.24762 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Co-Director: Agentic Generative Video Storytelling - https://arxiv.org/abs/2604.24842 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yale Song, Yiwen Song, Nick Losier, Nathan Hodson, Ye Jin, Rhyard Zhu, Yan Xu, Daniel Vlasic, Carina Claassen, Jasmine Leon, Khanh G. LeViet, Zack Chomyn, Joe Timmons, Brett Slatkin, Scott Penberthy, Tomas Pfister</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> While diffusion models generate high-fidelity video clips, transforming them into coherent storytelling engines remains challenging. Current agentic pipelines automate this via chained modules but suffer from semantic drift and cascading failures due to independent, handcrafted prompting. We present Co-Director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem. To ensure semantic coherence, we introduce hierarchical parameterization: a multi-armed bandit globally identifies promising creative directions, while a local multimodal self-refinement loop mitigates identity drift and ensures sequence-level consistency. This balances the exploration of novel narrative strategies with the exploitation of effective creative configurations. For evaluation, we introduce GenAD-Bench, a 400-scenario dataset of fictional products for personalized advertising. Experiments demonstrate that Co-Director significantly outperforms state-of-the-art baselines, offering a principled approach that seamlessly generalizes to broader cinematic narratives. Project Page: https://co-director-agent.github.io/</p> - https://arxiv.org/abs/2604.24842 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence - https://arxiv.org/abs/2604.24954 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24954.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NVIDIA, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Arushi Goel, Mike Ranzinger, Greg Heinrich, Guo Chen, Lukas Voegtle, Philipp Fischer, Timo Roman, Karan Sapra, Collin McCarthy, Shaokun Zhang, Fuxiao Liu, Hanrong Ye, Yi Dong, Mingjie Liu, Yifan Peng, Piotr Zelasko, Zhehuai Chen, Nithin Rao Koluguri, Nune Tadevosyan, Lilit Grigoryan, Ehsan Hosseini Asl, Pritam Biswas, Leili Tavabi, Yuanhang Su, Zhiding Yu, Peter Jin, Alexandre Milesi, Netanel Haber, Yao Xu, Sarah Amiraslani, Nabin Mulepati, Eric Tramel, Jaehun Jung, Ximing Lu, Brandon Cui, Jin Xu, Zhiqi Li, Shihao Wang, Yuanguo Kuang, Shaokun Zhang, Huck Yang, Boyi Li, Hongxu Yin, Song Han, Pavlo Molchanov, Adi Renduchintala, Charles Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Sreyan Ghosh, Yian Zhang, Alexander Bukharin, Venkat Srinivasan, Johnny Greco, Andre Manoel, Maarten Van Segbroeck, Suseella Panguliri, Rohit Watve, Divyanshu Kakwani, Shubham Pachori, Jeffrey Glick, Radha Sri-Tharan, Aileen Zaman, Khanh Nguyen, Shi Chen, Jiaheng Fang, Qing Miao, Wenfei Zhou, Yu Wang, Zaid Pervaiz Bhat, Varun Praveen, Arihant Jain, Ramanathan Arunachalam, Tomasz Kornuta, Ashton Sharabiani, Amy Shen, Wei Huang, Yi-Fu Wu, Ali Roshan Ghias, Huiying Li, Brian Yu, Nima Tajbakhsh, Chen Cui, Wenwen Gao, Li Ding, Terry Kong, Manoj Kilaru, Anahita Bhiwandiwalla, Marek Wawrzos, Daniel Korzekwa, Pablo Ribalta, Grzegorz Chlebus, Besmira Nushi, Ewa Dobrowolska, Maciej Jakub Mikulski, Kunal Dhawan, Steve Huang, Jagadeesh Balam, Yongqiang Wang, Nikolay Karpov, Valentin Mendelev, George Zelenfroynd, Meline Mkrtchyan, Qing Miao, Omri Almog, Bhavesh Pawar, Rameshwar Shivbhakta, Sudeep Sabnis, Ashrton Sharabiani, Negar Habibi, Geethapriya Venkataramani, Pamela Peng, Prerit Rodney, Serge Panev, Richard Mazzarese, Nicky Liu, Michael Fukuyama, Andrii Skliar, Roger Waleffe, Duncan Riach, Yunheng Zou, Jian Hu, Hao Zhang, Binfeng Xu, Yuhao Yang, Zuhair Ahmed, Alexandre Milesi, Carlo del Mundo, Chad Voegele, Zhiyu Cheng, Nave Assaf, Andrii Skliar, Daniel Afrimi, Natan Bagrov, Ran Zilberstein, Ofri Masad, Eugene Khvedchenia, Natan Bagrov, Borys Tymchenko, Tomer Asida, Daniel Afrimi, Parth Mannan, Victor Cui, Michael Evans, Katherine Luna, Jie Lou, Pinky Xu, Guyue Huang, Negar Habibi, Michael Boone, Pradeep Thalasta, Adeola Adesoba, Dina Yared, Christopher Parisien, Leon Derczynski, Shaona Ghosh, Wes Feely, Micah Schaffer, Radha Sri-Tharan, Jeffrey Glick, Barnaby Simkin, George Zelenfroynd, Tomasz Grzegorzek, Rishabh Garg, Aastha Jhunjhunwala, Sergei Kolchenko, Farzan Memarian, Haran Kumar, Shiv Kumar, Isabel Hulseman, Anjali Shah, Kari Briski, Padmavathy Subramanian, Joey Conway, Udi Karpas, Jane Polak Scowcroft, Annie Surla, Shilpa Ammireddy, Ellie Evans, Jesse Oliver, Tom Balough, Chia-Chih Chen, Sandip Bhaskar, Alejandra Rico, Bardiya Sadeghi, Seph Mard, Katherine Cheung, Meredith Price, Laya Sleiman, Saori Kaji, Wesley Helmholz, Wendy Quan, Michael Lightstone, Jonathan Cohen, Jian Zhang, Oleksii Kuchaiev, Boris Ginsburg, Jan Kautz, Eileen Long, Mohammad Shoeybi, Mostofa Patwary, Oluwatobi Olabiyi, Andrew Tao, Bryan Catanzaro, Udi Karpas</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.</p> - https://arxiv.org/abs/2604.24954 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis - https://arxiv.org/abs/2604.24198 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhisong Qiu, Shuofei Qiao, Kewei Xu, Yuqi Zhu, Lun Du, Ningyu Zhang, Huajun Chen</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static domains such as mathematics. However, their potential in dynamic data analysis tasks remains underexplored. In this work, we first present a empirical study revealing that general-domain PRMs struggle to supervise data analysis agents. Specifically, they fail to detect silent errors, logical flaws that yield incorrect results without triggering interpreter exceptions, and erroneously penalize exploratory actions, mistaking necessary trial-and-error exploration for grounding failures. To bridge this gap, we introduce DataPRM, a novel environment-aware generative process reward model that (1) can serve as an active verifier, autonomously interacting with the environment to probe intermediate execution states and uncover silent errors, and (2) employs a reflection-aware ternary reward strategy that distinguishes between correctable grounding errors and irrecoverable mistakes. We design a scalable pipeline to construct over 8K high-quality training instances for DataPRM via diversity-driven trajectory generation and knowledge-augmented step-level annotation. Experimental results demonstrate that DataPRM improves downstream policy LLMs by 7.21% on ScienceAgentBench and 11.28% on DABStep using Best-of-N inference. Notably, with only 4B parameters, DataPRM outperforms strong baselines, and exhibits robust generalizability across diverse Test-Time Scaling strategies. Furthermore, integrating DataPRM into Reinforcement Learning yields substantial gains over outcome-reward baselines, achieving 78.73% on DABench and 64.84% on TableBench, validating the effectiveness of process reward supervision. Code is available at https://github.com/zjunlp/DataMind.</p> - https://arxiv.org/abs/2604.24198 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Meta-CoT: Enhancing Granularity and Generalization in Image Editing - https://arxiv.org/abs/2604.24625 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24625.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiyi Zhang, Yiji Cheng, Tiankai Hang, Zijin Yin, Runze He, Yu Xu, Wenxun Dai, Yunlong Lin, Chunyu Wang, Qinglin Lu, Yansong Tang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into their Chain-of-Thought (CoT) process. However, a critical question remains underexplored: what forms of CoT and training strategy can jointly enhance both the understanding granularity and generalization? To address this, we propose Meta-CoT, a paradigm that performs a two-level decomposition of any single-image editing operation with two key properties: (1) Decomposability. We observe that any editing intention can be represented as a triplet - (task, target, required understanding ability). Inspired by this, Meta-CoT decomposes both the editing task and the target, generating task-specific CoT and traversing editing operations on all targets. This decomposition enhances the model's understanding granularity of editing operations and guides it to learn each element of the triplet during training, substantially improving the editing capability. (2) Generalizability. In the second decomposition level, we further break down editing tasks into five fundamental meta-tasks. We find that training on these five meta-tasks, together with the other two elements of the triplet, is sufficient to achieve strong generalization across diverse, unseen editing tasks. To further align the model's editing behavior with its CoT reasoning, we introduce the CoT-Editing Consistency Reward, which encourages more accurate and effective utilization of CoT information during editing. Experiments demonstrate that our method achieves an overall 15.8% improvement across 21 editing tasks, and generalizes effectively to unseen editing tasks when trained on only a small set of meta-tasks. Our code, benchmark, and model are released at https://shiyi-zh0408.github.io/projectpages/Meta-CoT/</p> - https://arxiv.org/abs/2604.24625 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Large Language Models Explore by Latent Distilling - https://arxiv.org/abs/2604.24927 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24927.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanhao Zeng, Ao Lu, Lufei Li, Zheng Zhang, Yexin Li, Kan Ren</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-level lexical variation, limiting semantic exploration. In this paper, we propose Exploratory Sampling (ESamp), a decoding approach that explicitly encourages semantic diversity during generation. ESamp is motivated by the well-known observation that neural networks tend to make lower-error predictions on inputs similar to those encountered before, and incur higher prediction error on novel ones. Building on this property, we train a lightweight Distiller at test time to predict deep-layer hidden representations of the LLM from its shallow-layer representations to model the LLM's depth-wise representation transitions. During decoding, the Distiller continuously adapts to the mappings induced by the current generation context. ESamp uses the prediction error as a novelty signal to reweight candidate token extensions conditioned on the current prefix, thereby biasing decoding toward less-explored semantic patterns. ESamp is implemented with an asynchronous training--inference pipeline, with less than 5% worst case overhead (1.2% in the optimized release). Empirical results show that ESamp significantly boosts the Pass@k efficiency of reasoning models, showing superior or comparable performance to strong stochastic and heuristic baselines. Notably, ESamp achieves robust generalization across mathematics, science, and code generation benchmarks and breaks the trade-off between diversity and coherence in creative writing. Our code has released at: https://github.com/LinesHogan/tLLM.</p> - https://arxiv.org/abs/2604.24927 - Mon, 27 Apr 2026 00:00:00 +0000 - - - ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning - https://arxiv.org/abs/2604.24300 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Zhang, Jiacheng Chen, Jiaqi Tan, Yongsen Mao, Wenhu Chen, Angel X. Chang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated for traditional 3D perception. When such annotations are treated as ground truth for video-based evaluation, reconstruction and annotation artifacts can miss objects that are clearly visible in the video, mislabel object identities, or corrupt geometry-dependent answers (e.g., size), yielding incorrect or ambiguous QA pairs. Second, evaluations often assume full-scene access, while many VLMs operate on sparsely sampled frames (e.g., 16-64), making many questions effectively unanswerable under the actual model inputs. We improve evaluation validity by introducing ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs. To this end, we re-annotate objects and geometry across 381 scenes from 5 datasets to improve data quality, and regenerate all QA pairs with rigorous bias mitigation and human verification using professional 3D annotation tools. We further enhance evaluation controllability by providing variants across multiple frame budgets (16/32/64/all) and fine-grained object visibility metadata, enabling controlled diagnostic analyses. Evaluations of general and domain-specific VLMs on ReVSI reveal systematic failure modes that are obscured by prior benchmarks, yielding a more reliable and diagnostic assessment of spatial intelligence.</p> - https://arxiv.org/abs/2604.24300 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation - https://arxiv.org/abs/2604.24763 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24763.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Liu, Weiming Ren, Xiaoke Huang, Shoufa Chen, Tianhong Li, Mengzhao Chen, Yatai Ji, Sen He, Jonas Schult, Belinda Zeng, Tao Xiang, Wenhu Chen, Ping Luo, Luke Zettlemoyer, Yuren Cong</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.</p> - https://arxiv.org/abs/2604.24763 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora - https://arxiv.org/abs/2604.24819 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24819.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenkai Pan, Xinglong Xu, Yuhang Xu, Yujun Wu, Siyuan Li, Jintao Chen, Conghui He, Jingxuan Wei, Cheng Tan</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Reliably transferring specialized human knowledge from text into large language models remains a fundamental challenge in artificial intelligence. Fine-tuning on domain corpora has enabled substantial capability gains, but the process operates without feedback: when a model fails on a domain task, there is no method to diagnose what is deficient in the training data, and the only recourse is to add more data indiscriminately. Here we show that when a structured knowledge representation extracted from the source corpus serves as the shared foundation for both training data and evaluation, the complete data-engineering lifecycle maps onto the software development lifecycle in a precise and operative way: training data becomes source code specifying what the model should learn, model training becomes compilation, benchmarking becomes unit testing, and failure-driven data repair becomes debugging. Under this correspondence, model failures decompose into concept-level gaps and reasoning-chain breaks that can be traced back to specific deficiencies in the data and repaired through targeted patches, with each repair cycle producing consistent improvements across model scales and architectures without degrading general capabilities. We formalize this principle as Programming with Data and instantiate it across sixteen disciplines spanning the natural sciences, engineering, biomedicine, and the social sciences, releasing a structured knowledge base, benchmark suite, and training corpus as open resources. By demonstrating that the relationship between training data and model behaviour is structurally traceable and systematically repairable, this work establishes a principled foundation for the reliable engineering of human expertise into language models.</p> - https://arxiv.org/abs/2604.24819 - Mon, 27 Apr 2026 00:00:00 +0000 - - - World-R1: Reinforcing 3D Constraints for Text-to-Video Generation - https://arxiv.org/abs/2604.24764 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24764.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Wang, Xiaoxuan He, Youping Gu, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high computational costs and limit scalability. We propose World-R1, a framework that aligns video generation with 3D constraints through reinforcement learning. To facilitate this alignment, we introduce a specialized pure text dataset tailored for world simulation. Utilizing Flow-GRPO, we optimize the model using feedback from pre-trained 3D foundation models and vision-language models to enforce structural coherence without altering the underlying architecture. We further employ a periodic decoupled training strategy to balance rigid geometric consistency with dynamic scene fluidity. Extensive evaluations reveal that our approach significantly enhances 3D consistency while preserving the original visual quality of the foundation model, effectively bridging the gap between video generation and scalable world simulation.</p> - https://arxiv.org/abs/2604.24764 - Mon, 27 Apr 2026 00:00:00 +0000 - - - Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data - https://arxiv.org/abs/2604.26116 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26116.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Emre Ardıç, Yakup Genç</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Federated learning is a machine learning paradigm in which multiple devices collaboratively train a model under the supervision of a central server while ensuring data privacy. However, its performance is often hindered by redundant, malicious, or abnormal samples, leading to model degradation and inefficiency. To overcome these issues, we propose novel sample selection methods for image classification, employing a multitask autoencoder to estimate sample contributions through loss and feature analysis. Our approach incorporates unsupervised outlier detection, using one-class support vector machine (OCSVM), isolation forest (IF), and adaptive loss threshold (AT) methods managed by a central server to filter noisy samples on clients. We also propose a multi-class deep support vector data description (SVDD) loss controlled by a central server to enhance feature-based sample selection. We validate our methods on CIFAR10 and MNIST datasets across varying numbers of clients, non-IID distributions, and noise levels up to 40%. The results show significant accuracy improvements with loss-based sample selection, achieving gains of up to 7.02% on CIFAR10 with OCSVM and 1.83% on MNIST with AT. Additionally, our federated SVDD loss further improves feature-based sample selection, yielding accuracy gains of up to 0.99% on CIFAR10 with OCSVM. These results show the effectiveness of our methods in improving model accuracy across various client counts and noise conditions.</p> - https://arxiv.org/abs/2604.26116 + Prior-Aligned Data Cleaning for Tabular Foundation Models + https://arxiv.org/abs/2604.25154 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25154.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Laure Berti-Equille</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for practitioners who cannot afford large annotated corpora. However, their in-context learning mechanism assumes approximately clean inputs: missing values, outliers, and duplicates in the real-world data create a prior mismatch that degrades both accuracy and confidence calibration simultaneously. Correcting this mismatch requires sequential decisions over cleaning operators whose interactions no static preprocessing rule can anticipate -a natural fit for reinforcement learning~(RL). We introduce L2C2, the first deep RL framework framing tabular data cleaning as prior alignment: a learned policy sequences operators to minimize the distributional gap between dirty input and the TFM's synthetic prior. Six experiments on ten OpenML benchmark datasets establish: 1) three of seven reward designs collapse to degenerate trivial cleaning strategies -- principled reward engineering is scientifically non-trivial; 2) the novel TFMAwareReward reward we propose selects structurally distinct pipelines on 4/10 datasets and achieves higher TabPFN accuracy on those diverging cases (mean 0.851 vs. 0.843; Wilcoxon p=0.063, n=4) while never underperforming; 3) parameterized cleaning actions improve best-found pipeline reward on 9/10 datasets (Wilcoxon p=0.004); and 4) a policy pre-trained on one single source dataset exceeds scratch training at the 2,000-step fine-tuning checkpoint on all three held-out datasets (up to +28.8% after full fine-tuning) demonstrating cross-dataset transfer of prior-alignment knowledge. These findings establish that prior alignment is a principled data preparation strategy for TFM deployment on real-world tabular data.</p> + https://arxiv.org/abs/2604.25154 Tue, 28 Apr 2026 00:00:00 +0000 - A Systematic Post-Train Framework for Video Generation - https://arxiv.org/abs/2604.25427 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyue Xue, Siming Fu, Jie Huang, Shuai Lu, Haoran Li, Yijun Liu, Yuming Li, Xiaoxuan He, Mengzhao Chen, Haoyang Huang, Nan Duan, Ping Luo</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment requirements due to critical issues such as prompt sensitivity, temporal inconsistency, and prohibitive inference costs. To bridge this gap, we propose a comprehensive post-training framework that systematically aligns pretrained models with user intentions through four synergistic stages: we first employ Supervised Fine-Tuning (SFT) to transform the base model into a stable instruction-following policy, followed by a Reinforcement Learning from Human Feedback (RLHF) stage that utilizes a novel Group Relative Policy Optimization (GRPO) method tailored for video diffusion to enhance perceptual quality and temporal coherence; subsequently, we integrate Prompt Enhancement via a specialized language model to refine user inputs, and finally address system efficiency through Inference Optimization. Together, these components provide a systematic approach to improving visual quality, temporal coherence, and instruction following, while preserving the controllability learned during pretraining. The result is a practical blueprint for building scalable post-training pipelines that are stable, adaptable, and effective in real-world deployment. Extensive experiments demonstrate that this unified pipeline effectively mitigates common artifacts and significantly improves controllability and visual aesthetics while adhering to strict sampling cost constraints.</p> - https://arxiv.org/abs/2604.25427 + How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum + https://arxiv.org/abs/2604.25907 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chu-Cheng Lin, Eugene Ie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewards (RLVR) when the initial success probability p_0 is small. Using the Tsallis q-logarithm, we define a loss family J_Q that interpolates between RLVR (at q{=}0, the exploitation pole) and the log-marginal-likelihood over latent trajectories (at q{=}1, the density-estimation pole). All members share the same per-example gradient direction, differing only by a scalar amplification P_{θ^{-q}} that reweights each instance independently of the learning rate. This amplification is the mechanism that addresses cold-start stalling: under gradient flow, the exploitation pole requires Ω(1{p_0}) time to escape cold start, while the density-estimation pole escapes in Θbig(log(1{p_0})big); intermediate q trades escape speed against noise memorization. Because P_θ is intractable, we derive two Monte Carlo estimators from the two factorizations of the gradient: Gradient-Amplified RL (GARL) samples from the prior and amplifies the RL gradient, and Posterior-Attenuated Fine-Tuning (PAFT) importance-resamples from the posterior and runs standard SFT. Both have bias Obig(q{M P_θ^{q+1}}big); GARL has lower variance, PAFT has semantically coherent gradients. On FinQA, HotPotQA, and MuSiQue, GARL at q{=}0.75 substantially mitigates cold-start stalling, escaping cold start where GRPO fails entirely. In warm start, GARL at low q dominates FinQA where training is stable; on HotPotQA and MuSiQue, GARL destabilizes during training, and PAFT at q{=}0.75 provides stable gradients (best overall on HotPotQA at 47.9 maj@16, +14.4 over GRPO).</p> + https://arxiv.org/abs/2604.25907 Tue, 28 Apr 2026 00:00:00 +0000 - IAM: Identity-Aware Human Motion and Shape Joint Generation - https://arxiv.org/abs/2604.25164 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25164.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqi Jia, Zekun Li, Abhay Mittal, Chengcheng Tang, Chuan Guo, Lezi Wang, James Matthew Rehg, Lingling Tao, Size An</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM</p> - https://arxiv.org/abs/2604.25164 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital - https://arxiv.org/abs/2604.26091 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26091.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> T. J. Barton, Chris Constantakis, Patti Hauseman, Annie Mous, Alaska Hoffman, Brian Bergeron, Hunter Goodreau</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents traded real ETH in a bounded onchain market. Users configured vaults through structured controls and natural-language strategies, but only agents could choose normal buy/sell trades. The system produced 7.5M agent invocations, roughly 300K onchain actions, about $20M in volume, more than 5,000 ETH deployed, roughly 70B inference tokens, and 99.9% settlement success for policy-valid submitted transactions. Long-running agents accumulated thousands of sequential decisions, including 6,000+ prompt-state-action cycles for continuously active agents, yielding a large-scale trace from user mandate to rendered prompt, reasoning, validation, portfolio state, and settlement. Reliability did not come from the base model alone; it emerged from the operating layer around the model: prompt compilation, typed controls, policy validation, execution guards, memory design, and trace-level observability. Pre-launch testing exposed failures that text-only benchmarks rarely measure, including fabricated trading rules, fee paralysis, numeric anchoring, cadence trading, and misread tokenomics. Targeted harness changes reduced fabricated sell rules from 57% to 3%, reduced fee-led observations from 32.5% to below 10%, and increased capital deployment from 42.9% to 78.0% in an affected test population. We show that capital-managing agents should be evaluated across the full path from user mandate to prompt, validated action, and settlement.</p> - https://arxiv.org/abs/2604.26091 - Tue, 28 Apr 2026 00:00:00 +0000 - - - BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate - https://arxiv.org/abs/2604.25203 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arnon Mazza, Elad Levi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent boundary-case performance and high inference costs. Training custom classifiers achieves both accuracy and efficiency, yet demands substantial labeled data that is costly to obtain. We present BARRED (Boundary Alignment Refinement through REflection and Debate), a framework for generating faithful and diverse synthetic training data using only a task description and a small set of unlabeled examples. Our approach decomposes the domain space into dimensions to ensure comprehensive coverage, and employs multi-agent debate to verify label correctness, yielding a high-fidelity training corpus. Experiments across diverse custom policies demonstrate that small language models finetuned on our synthetic data consistently outperform state-of-the-art proprietary LLMs (including reasoning models) and dedicated guardrail models. Ablation studies confirm that both dimension decomposition and debate-based verification are critical for ensuring the diversity and label fidelity required for effective fine-tuning. The BARRED framework eliminates the reliance on extensive human annotation, offering a scalable solution for accurate custom guardrails.</p> - https://arxiv.org/abs/2604.25203 - Tue, 28 Apr 2026 00:00:00 +0000 - - - MAIC-UI: Making Interactive Courseware with Generative UI - https://arxiv.org/abs/2604.25806 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25806.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shangqing Tu, Yanjia Li, Keyu Chen, Sichen Zhang, Jifan Yu, Daniel Zhang-Li, Lei Hou, Juanzi Li, Yu Zhang, Huiqin Liu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Creating interactive STEM courseware traditionally requires HTML/CSS/JavaScript expertise, leaving barriers for educators. While generative AI can produce HTML codes, existing tools generate static presentations rather than interactive simulations, struggle with long documents, and lack pedagogical accuracy mechanisms. Furthermore, full regeneration for modifications requires 200--600 seconds, disrupting creative flow. We present MAIC-UI, a zero-code authoring system that enables educators to create and rapidly edit interactive courseware from textbooks, PPTs, and PDFs. MAIC-UI employs: (1) structured knowledge analysis with multi-modal understanding to ensure pedagogical rigor; (2) a two-stage generate-verify-optimize pipeline separating content alignment from visual refinement; and (3) Click-to-Locate editing with Unified Diff-based incremental generation achieving sub-10-second iteration cycles. A controlled lab study with 40 participants shows MAIC-UI reduces editing iterations (4.9 vs. 7.0) and significantly improves learnability and controllability compared to direct Text-to-HTML generation. A three-month classroom deployment with 53 high school students demonstrates that MAIC-UI fosters learning agency and reduces outcome disparities -- the pilot class achieved 9.21-point gains in STEM subjects compared to -2.32 points in control classes. Our code is available at https://github.com/THU-MAIC/MAIC-UI.</p> - https://arxiv.org/abs/2604.25806 - Tue, 28 Apr 2026 00:00:00 +0000 - - - FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments - https://arxiv.org/abs/2604.25135 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25135.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay, Gaowen Liu, Ali Payani, Jayanth Srinivasa, Chitta Baral</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue resolution scenarios, these agents frequently fail due to the cascading effects of incorrect decision-making. These challenges are particularly pronounced for open-source LLMs with smaller parameter sizes, limited context windows, and constrained inference budgets, which contribute to increased error accumulation in agentic settings. To tackle these challenges, we present the Failure-Aware Meta-Agentic (FAMA) framework. FAMA operates in two stages: first, it analyzes failure trajectories from baseline agents to identify the most prevalent errors; second, it employs an orchestration mechanism that activates a minimal subset of specialized agents tailored to address these failures by injecting a targeted context for the tool-use agent before the decision-making step. Experiments across open-source LLMs demonstrate performance gains up to 27% across evaluation modes over standard baselines. These results highlight that targeted curation of context through specialized agents to address common failures is a valuable design principle for building reliable, multi-turn tool-use LLM agents that simulate real-world conversational scenarios.</p> - https://arxiv.org/abs/2604.25135 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Toward Scalable Terminal Task Synthesis via Skill Graphs - https://arxiv.org/abs/2604.25727 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25727.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiyuan Fan, Tinghao Yu, Yuanjun Cai, Jiangtao Guan, Yun Yang, Dingxin Hu, Jiang Zhou, Xing Wu, Zhuo Han, Feng Zhang, Lilin Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories. Existing approaches mitigate this bottleneck by synthesizing large-scale terminal task instances for trajectory sampling. However, they primarily focus on scaling the number of tasks while providing limited control over the diversity of execution trajectories that agents actually experience during training. In this paper, we present SkillSynth, an automated framework for terminal task synthesis built on a scenario-mediated skill graph. SkillSynth first constructs a large-scale skill graph, where scenarios serve as intermediate transition nodes that connect diverse command-line skills. It then samples paths from this graph as abstractions of real-world workflows, and uses a multi-agent harness to instantiate them into executable task instances. By grounding task synthesis in graph-sampled workflow paths, SkillSynth explicitly controls the diversity of minimal execution trajectories required to solve the synthesized tasks. Experiments on Terminal-Bench demonstrate the effectiveness of SkillSynth. Moreover, task instances synthesized by SkillSynth have been adopted to train Hy3 Preview, contributing to its enhanced agentic capabilities in terminal-based settings.</p> - https://arxiv.org/abs/2604.25727 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Step-Audio-R1.5 Technical Report - https://arxiv.org/abs/2604.25719 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25719.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu, Fei Tian, Yayue Deng, Jun Chen, Qingjian Lin, Haoyang Zhang, Yuxin Li, Jinglan Gong, Yechang Huang, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Gang Yu, Xiangyu Zhang, Daxin Jiang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain, enabling models to tackle increasingly complex acoustic and spoken tasks. To elicit and sustain these extended reasoning chains, the prevailing paradigm -- driven by the success of text-based reasoning models -- overwhelmingly relies on Reinforcement Learning with Verified Rewards (RLVR). However, as models are strictly optimized to distill rich, continuous auditory contexts into isolated, verifiable text labels, a fundamental question arises: are we fostering true audio intelligence, or merely reducing a continuous sensory medium into a discrete puzzle? We identify this as the "verifiable reward trap." While RLVR yields remarkable scores on standardized objective benchmarks, it systematically degrades the real-world conversational feel of audio models. By prioritizing isolated correctness over acoustic nuance, RLVR reduces dynamic interactions to mechanical "answering machines," severely compromising prosodic naturalness, emotional continuity, and user immersion, particularly in long-turn dialogues. To bridge the gap between mechanical objective verification and genuine sensory empathy, we introduce Step-Audio-R1.5, marking a paradigm shift toward Reinforcement Learning from Human Feedback (RLHF) in audio reasoning. Comprehensive evaluations demonstrate that Step-Audio-R1.5 not only maintains robust analytical reasoning but profoundly transforms the interactive experience, redefining the boundaries of deeply immersive long-turn spoken dialogue.</p> - https://arxiv.org/abs/2604.25719 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation - https://arxiv.org/abs/2604.25819 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25819.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yupeng Zhou, Lianghua Huang, Zhifan Wu, Jiabao Wang, Yupeng Shi, Biao Jiang, Daquan Zhou, Yu Liu, Ming-Ming Cheng, Qibin Hou</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> In this work, we propose Mutual Forcing, a framework for fast autoregressive audio-video generation with long-horizon audio-video synchronization. Our approach addresses two key challenges: joint audio-video modeling and fast autoregressive generation. To ease joint audio-video optimization, we adopt a two-stage training strategy: we first train uni-modal generators and then couple them into a unified audio-video model for joint training on paired data. For streaming generation, we ask whether a native fast causal audio-video model can be trained directly, instead of following existing streaming distillation pipelines that typically train a bidirectional model first and then convert it into a causal generator through multiple distillation stages. Our answer is Mutual Forcing, which builds directly on native autoregressive model and integrates few-step and multi-step generation within a single weight-shared model, enabling self-distillation and improved training-inference consistency. The multi-step mode improves the few-step mode via self-distillation, while the few-step mode generates historical context during training to improve training-inference consistency; because the two modes share parameters, these two effects reinforce each other within a single model. Compared with prior approaches such as Self-Forcing, Mutual Forcing removes the need for an additional bidirectional teacher model, supports more flexible training sequence lengths, reduces training overhead, and allows the model to improve directly from real paired data rather than a fixed teacher. Experiments show that Mutual Forcing matches or surpasses strong baselines that require around 50 sampling steps while using only 4 to 8 steps, demonstrating substantial advantages in both efficiency and quality. The project page is available at https://mutualforcing.github.io.</p> - https://arxiv.org/abs/2604.25819 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models - https://arxiv.org/abs/2604.25636 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Guo, Linqing Wang, Jiangshan Wang, Yang Yue, Zeyu Liu, Zhiyuan Zhao, Qinglin Lu, Gao Huang, Chunyu Wang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Unified multimodal models (UMMs) integrate visual understanding and generation within a single framework. For text-to-image (T2I) tasks, this unified capability allows UMMs to refine outputs after their initial generation, potentially extending the performance upper bound. Current UMM-based refinement methods primarily follow a refinement-via-editing (RvE) paradigm, where UMMs produce editing instructions to modify misaligned regions while preserving aligned content. However, editing instructions often describe prompt-image misalignment only coarsely, leading to incomplete refinement. Moreover, pixel-level preservation, though necessary for editing, unnecessarily restricts the effective modification space for refinement. To address these limitations, we propose Refinement via Regeneration (RvR), a novel framework that reformulates refinement as conditional image regeneration rather than editing. Instead of relying on editing instructions and enforcing strict content preservation, RvR regenerates images conditioned on the target prompt and the semantic tokens of the initial image, enabling more complete semantic alignment with a larger modification space. Extensive experiments demonstrate the effectiveness of RvR, improving Geneval from 0.78 to 0.91, DPGBench from 84.02 to 87.21, and UniGenBench++ from 61.53 to 77.41.</p> - https://arxiv.org/abs/2604.25636 - Tue, 28 Apr 2026 00:00:00 +0000 - - - AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery - https://arxiv.org/abs/2604.25256 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Xiong, Kun Luo, Ziyi Xia, Wenbo Zhang, Jin-Ge Yao, Zheng Liu, Jingying Shao, Jianlyu Chen, Hongjin Qian, Xi Yang, Qian Yu, Hao Li, Chen Yue, Xiaan Du, Yuyang Wang, Yesheng Liu, Haiyu Xu, Zhicheng Dou</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents' capability in driving this process, we present AutoResearchBench, a dedicated benchmark for autonomous scientific literature discovery. AutoResearchBench consists of two complementary task types: (1) Deep Research, which requires tracking down a specific target paper through a progressive, multi-step probing process, and (2) Wide Research, which requires comprehensively collecting a set of papers satisfying given conditions. Compared to previous benchmarks on agentic web browsing, AutoResearchBench is distinguished along three dimensions: it is research-oriented, calling for in-depth comprehension of scientific concepts; literature-focused, demanding fine-grained utilization of detailed information; and open-ended, involving an unknown number of qualified papers and thus requiring deliberate reasoning and search throughout. These properties make AutoResearchBench uniquely suited for evaluating autonomous research capabilities, and extraordinarily challenging. Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research, while many other strong baselines fall below 5%. We publicly release the dataset and evaluation pipeline to facilitate future research in this direction. We publicly release the dataset, evaluation pipeline, and code at https://github.com/CherYou/AutoResearchBench.</p> - https://arxiv.org/abs/2604.25256 - Tue, 28 Apr 2026 00:00:00 +0000 - - - DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios - https://arxiv.org/abs/2604.25914 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25914.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinxiang Meng, Shaoping Huang, Fangyu Lei, Jingyu Guo, Haoxiang Liu, Jiahao Su, Sihan Wang, Yao Wang, Enrui Wang, Ye Yang, Hongze Chai, Jinming Lv, Anbang Yu, Huangjing Zhang, Yitong Zhang, Yiming Huang, Zeyao Ma, Shizhu He, Jun Zhao, Kang Liu</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at https://github.com/DA-Open/DV-World{this project page}.</p> - https://arxiv.org/abs/2604.25914 - Tue, 28 Apr 2026 00:00:00 +0000 - - - RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments - https://arxiv.org/abs/2604.26067 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26067.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zaid Nasser, Mikhail Iumanov, Tianhao Li, Maxim Popov, Jaafar Mahmoud, Sergey Kolyubin</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> We present RADIO-ViPE (Reduce All Domains Into One -- Video Pose Engine), an online semantic SLAM system that enables geometry-aware open-vocabulary grounding, associating arbitrary natural language queries with localized 3D regions and objects in dynamic environments. Unlike existing approaches that require calibrated, posed RGB-D input, RADIO-ViPE operates directly on raw monocular RGB video streams, requiring no prior camera intrinsics, depth sensors, or pose initialization. The system tightly couples multi-modal embeddings -- spanning vision and language -- derived from agglomerative foundation models (e.g., RADIO) with geometric scene information. This coupling takes place in initialization, optimization and factor graph connections to improve the consistency of the map from multiple modalities. The optimization is wrapped within adaptive robust kernels, designed to handle both actively moving objects and agent-displaced scene elements (e.g., furniture rearranged during ego-centric session). Experiments demonstrate that RADIO-ViPE achieves state-of-the-art results on the dynamic TUM-RGBD benchmark while maintaining competitive performance against offline open-vocabulary methods that rely on calibrated data and static scene assumptions. RADIO-ViPE bridges a critical gap in real-world deployment, enabling robust open-vocabulary semantic grounding for autonomous robotics and unconstrained in-the-wild video streams. Project page: https://be2rlab.github.io/radio_vipe</p> - https://arxiv.org/abs/2604.26067 - Tue, 28 Apr 2026 00:00:00 +0000 - - - Recursive Multi-Agent Systems - https://arxiv.org/abs/2604.25917 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.25917.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyuan Yang, Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus J. Buehler, Jingrui He, James Zou</p><p><b>Upvotes:</b> 244</p><p><b>Summary:</b> Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and learning dynamics establish that RecursiveMAS is more efficient than standard text-based MAS and maintains stable gradients during recursive training. Empirically, we instantiate RecursiveMAS under 4 representative agent collaboration patterns and evaluate across 9 benchmarks spanning mathematics, science, medicine, search, and code generation. In comparison with advanced single/multi-agent and recursive computation baselines, RecursiveMAS consistently delivers an average accuracy improvement of 8.3%, together with 1.2times-2.4times end-to-end inference speedup, and 34.6%-75.6% token usage reduction. Code and Data are provided in https://recursivemas.github.io.</p> - https://arxiv.org/abs/2604.25917 - Tue, 28 Apr 2026 00:00:00 +0000 - - - ViPO: Visual Preference Optimization at Scale - https://arxiv.org/abs/2604.24953 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Li, Jie Wu, Justin Cui, Xiaojie Li, Rui Wang, Chen Chen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn preferences, hindering effective scaling. To enhance robustness against noise, we propose Poly-DPO, which extends the DPO objective with an additional polynomial term that dynamically adjusts model confidence based on dataset characteristics, enabling effective learning across diverse data distributions. Beyond biased patterns, existing datasets suffer from low resolution, limited prompt diversity, and imbalanced distributions. To facilitate large-scale visual preference optimization by tackling data bottlenecks, we construct ViPO, a massive-scale preference dataset with 1M image pairs at 1024px across five categories and 300K video pairs at 720p+ across three categories. State-of-the-art generative models and diverse prompts ensure reliable preference signals with balanced distributions. Remarkably, when applying Poly-DPO to our high-quality dataset, the optimal configuration converges to standard DPO. This convergence validates dataset quality and Poly-DPO's adaptive nature: sophisticated optimization becomes unnecessary with sufficient data quality, yet remains valuable for imperfect datasets. We validate our approach across visual generation models. On noisy datasets like Pick-a-Pic V2, Poly-DPO achieves 6.87 and 2.32 gains over Diffusion-DPO on GenEval for SD1.5 and SDXL, respectively. For ViPO, models achieve performance far exceeding those trained on existing open-source preference datasets. These results confirm that addressing both algorithmic adaptability and data quality is essential for scaling visual preference optimization.</p> - https://arxiv.org/abs/2604.24953 + HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help? + https://arxiv.org/abs/2604.09408 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.09408.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamed Elfeki, Tu Trinh, Kelvin Luu, Guangze Luo, Nathan Hunt, Ernesto Montoya, Nandan Marwaha, Yannis He, Charles Wang, Fernando Crabedo, Alessa Castilo, Bing Liu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgment: knowing when to act autonomously and when to ask for help. Current benchmarks are blind to this failure mode. They supply unambiguous detailed instructions and solely reward execution correctness, so an agent that makes a lucky guess for a missing requirement will score identically to one that would have asked to be certain. We present HiL-Bench (Human-in-the-Loop Benchmark) to measure this selective escalation skill. Each task contains human-validated blockers (missing information, ambiguous requests, contradictory information) that surface only through progressive exploration, not upfront inspection. Our core metric, Ask-F1, the harmonic mean of question precision and blocker recall, captures the tension between over-asking and silent guessing; its structure architecturally prevents gaming through question spam. Evaluation across SWE and text-to-SQL domains reveals a large universal judgment gap: no frontier model recovers more than a fraction of its full-information performance when deciding whether to ask. Failure analysis identifies three key help-seeking patterns: overconfident wrong beliefs with no gap detection; high uncertainty detection yet persistent errors; broad, imprecise escalation without self-correction. These consistent patterns confirm poor help-seeking is a model-level flaw, not task-specific. RL training on shaped Ask-F1 reward shows judgment is trainable: a 32B model improves both help-seeking quality and task pass rate, with gains that transfer across domains. The model does not learn domain-specific heuristics for when to ask; it learns to detect unresolvable uncertainty and act on it.</p> + https://arxiv.org/abs/2604.09408 Wed, 29 Apr 2026 00:00:00 +0000 - FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing - https://arxiv.org/abs/2604.26186 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Fashion AI systems routinely encode the aesthetic logic of specific houses, editors, and historical moments without disclosing it. We present FASH-iCNN, a multimodal system trained on 87,547 Vogue runway images across 15 fashion houses spanning 1991-2024 that makes this cultural logic inspectable. Given a photograph of a garment, the system recovers which house produced it, which era it belongs to, and which color tradition it reflects. A clothing-only model identifies the fashion house at 78.2% top-1 across 14 houses, the decade at 88.6% top-1, and the specific year at 58.3% top-1 across 34 years with a mean error of just 2.2 years. Probing which visual channels carry this signal reveals a sharp dissociation: removing color costs only 10.6pp of house identity accuracy, while removing texture costs 37.6pp, establishing texture and luminance as the primary carriers of editorial identity. FASH-iCNN treats editorial culture as the signal rather than background noise, identifying which houses, eras, and color traditions shaped each output so that users can see not just what the system predicts but which houses, editors, and historical moments are encoded in that prediction.</p> - https://arxiv.org/abs/2604.26186 + Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models + https://arxiv.org/abs/2604.27124 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vijay Sadashivaiah, Georgios Dasoulas, Judith Mueller, Soumya Ghosh</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Training stable biological foundation models requires rethinking attention mechanisms: we find that using sigmoid attention as a drop in replacement for softmax attention a) produces better learned representations: on six diverse single-cell datasets, sigmoid achieves 25% higher cell-type separation, better cell-type cohesion metrics, and lower validation loss, b) faster training, models with sigmoid attention train up to 10% faster than their softmax counterparts, and c) more stable training by eliminating inherent sources of instability in softmax attention. We establish that sigmoid attention has globally bounded derivatives (leq 0.25) as opposed to softmax, and a diagonal Jacobian structure in contrast with softmax's dense coupling, which together help alleviate training instabilities. In stress tests on 160M-parameter bidirectional attention models trained without gradient clipping on 8K-token sequences, softmax diverges catastrophically, with gradients exploding by four orders of magnitude, while sigmoid remains stable. Finally, we implement and open-source TritonSigmoid, an efficient GPU kernel that achieves 515 TFLOPS on H100 GPUs, outperforming both FlashAttention-2 and FlashSigmoid, with native padding support, which is essential for biological sequences. Our results establish sigmoid attention as both theoretically grounded and empirically superior for biological foundation models. Code is available at https://github.com/MSDLLCpapers/triton-sigmoid</p> + https://arxiv.org/abs/2604.27124 Wed, 29 Apr 2026 00:00:00 +0000 - Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models - https://arxiv.org/abs/2604.27251 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27251.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata, Nikolaos Aletras</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning patterns, such as induction, deduction, and abduction, can be decoupled from specific problem instances remains a critical challenge for model controllability, and for shedding light on reasoning controllability. In this paper, we present the first systematic investigation of this problem through the lens of reasoning conflicts: an explicit tension between parametric and contextual information induced by mandating logical schemata that deviate from those expected for a target task. Our evaluation reveals that LLMs consistently prioritize sensibility over compliance, favoring task-appropriate reasoning patterns despite conflicting instructions. Notably, task accuracy is not strictly determined by sensibility, with models often maintaining high performance even when using conflicting patterns, suggesting a reliance on internalized parametric memory that increases with model size. We further demonstrate that reasoning conflicts are internally detectable, as confidence scores significantly drop during conflicting episodes. Probing experiments confirm that reasoning types are linearly encoded from middle-to-late layers, indicating the potential for activation-level controllability. Leveraging these insights, we steer models towards compliance, increasing instruction following by up to 29%. Overall, our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data, offering a path toward improved controllability, faithfulness, and generalizability.</p> - https://arxiv.org/abs/2604.27251 + ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models + https://arxiv.org/abs/2405.13729 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2405.13729.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes can be insufficiently covered by existing training schemes of diffusion generative models, potentially limiting test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them. Our code is available at: https://github.com/Xrvitd/ComboStoc</p> + https://arxiv.org/abs/2405.13729 Wed, 29 Apr 2026 00:00:00 +0000 - Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising - https://arxiv.org/abs/2604.26694 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26694.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jun Guo, Qiwei Li, Peiyan Li, Zilong Chen, Nan Sun, Yifei Su, Heyun Wang, Yuan Zhang, Xinghang Li, Huaping Liu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world models (e.g., UWM) that only model 2D pixel-space and fail to balance action efficiency and world modeling quality. To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos, and obtains spatial information efficiently through a lightweight structural adaptation: replicating the final few blocks of the pretrained Diffusion Transformer into a dedicated depth prediction branch for the reconstruction of future spatial information. Moreover, we propose Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency. ANS applies a specialized asynchronous denoising schedule during inference, which rapidly decodes actions with fewer steps to enable efficient real-time execution, while dedicating the full sequence of steps to generate high-fidelity video. Rather than entirely decoupling the timesteps during training, ANS samples from their joint distribution to align with the inference distribution. Pretrained on over 5,800 hours of robotic data, X-WAM achieves 79.2% and 90.7% average success rate on RoboCasa and RoboTwin 2.0 benchmarks, while producing high-fidelity 4D reconstruction and generation surpassing existing methods in both visual and geometric metrics.</p> - https://arxiv.org/abs/2604.26694 + Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions + https://arxiv.org/abs/2604.23774 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.23774.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Etai Sella, Hao Phung, Nitay Amiel, Or Litany, Or Patashnik, Hadar Averbuch-Elor</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Text-based 2D image editing models have recently reached an impressive level of maturity, motivating a growing body of work that heavily depends on these models to drive 3D edits. While effective for appearance-based modifications, such 2D-centric 3D editing pipelines often struggle with fine-grained 3D editing, where localized structural changes must be applied while strictly preserving an object's overall identity. To address this limitation, we propose Prox-E, a training-free framework that enables fine-grained 3D control through an explicit, primitive-based geometric abstraction. Our framework first abstracts an input 3D shape into a compact set of geometric primitives. A pretrained vision-language model (VLM) then edits this abstraction to specify primitive-level changes. These structural edits are subsequently used to guide a 3D generative model, enabling fine-grained, localized modifications while preserving unchanged regions of the original shape. Through extensive experiments, we demonstrate that our method consistently balances identity preservation, shape quality, and instruction fidelity more effectively than various existing approaches, including 2D-based 3D editors and training-based methods.</p> + https://arxiv.org/abs/2604.23774 Wed, 29 Apr 2026 00:00:00 +0000 - Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding - https://arxiv.org/abs/2604.26779 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hayate Iso, Tiyasa Mitra, Sudipta Mondal, Rasoul Shafipour, Venmugil Elango, Terry Kong, Yuki Huang, Seonjin Na, Izzy Putterman, Benjamin Chislett, Maor Ashkenazi, Joseph Guman, Gerald Shen, Tugrul Konuk, Ashwath Aithal, Ritika Borkar, Ran Zilberstein, Bita Rouhani</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the rollout or optimization regime, for example, through off-policy execution, replay, or lower-precision generation. We study speculative decoding as a lossless acceleration primitive for RL rollouts that preserves the target model's output distribution. We implement speculative decoding in NeMo-RL with a vLLM backend, supporting both synchronous and asynchronous pipelines and enabling speculation during RL rollouts. This benefit is realizable across speculation mechanisms, such as pretrained MTP heads, small external draft models or even techniques such as Eagle3, which are traditionally applied after RL phase. This yields a deployment path for state-of-the-art speculative decoding inside RL training. In a reasoning post-training workload at 8B scale under synchronous RL, speculative decoding improves rollout throughput by 1.8x. Using a high-fidelity performance simulator, we project that combining speculative decoding with asynchronous RL yields up to 2.5x end-to-end training speedup at 235B scale.</p> - https://arxiv.org/abs/2604.26779 + Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction + https://arxiv.org/abs/2604.27221 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27221.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Huang, Yihang Chen, Zhiyuan He, Yuxiang Chen, Ka Yiu Lee, Huichi Zhou, Weilin Luo, Meng Fang, Jun Wang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We introduce Web2BigTable, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into sub-problems and lower-level worker agents solve them in parallel. Through a closed-loop run--verify--reflect process, the framework jointly improves decomposition and execution over time via persistent, human-readable external memory, with self-evolving updates to each single-agent. During execution, workers coordinate through a shared workspace that makes partial findings visible, allowing them to reduce redundant exploration, reconcile conflicting evidence, and adapt to emerging coverage gaps. Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of 38.50 (7.5times the second best at 5.10), Row F1 of 63.53 (+25.03 over the second best), and Item F1 of 80.12 (+14.42 over the second best). It also generalises to depth-oriented search on XBench-DeepSearch, achieving 73.0 accuracy. Code is available at https://github.com/web2bigtable/web2bigtable.</p> + https://arxiv.org/abs/2604.27221 Wed, 29 Apr 2026 00:00:00 +0000 - The Last Human-Written Paper: Agent-Native Research Artifacts - https://arxiv.org/abs/2604.24658 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.24658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiachen Liu, Jiaxin Pei, Jintao Huang, Chenglei Si, Ao Qu, Xiangru Tang, Runyu Lu, Lichang Chen, Xiaoyan Bai, Haizhong Zheng, Carl Chen, Zhiyang Chen, Haojie Ye, Yujuan Fu, Zexue He, Zijian Jin, Zhenyu Zhang, Shangquan Sun, Maestro Harmon, John Dianzhuo Wang, Jianqiao Zeng, Jiachen Sun, Mingyuan Wu, Baoyu Zhou, Chenyu You, Shijian Lu, Yiming Qiu, Fan Lai, Yuan Yuan, Yao Li, Junyuan Hong, Ruihao Zhu, Beidi Chen, Alex Pentland, Ang Chen, Mosharaf Chowdhury, Zechen Zhang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs. Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste. On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities.</p> - https://arxiv.org/abs/2604.24658 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Step-level Optimization for Efficient Computer-use Agents - https://arxiv.org/abs/2604.27151 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinbiao Wei, Kangqi Ni, Yilun Zhao, Guo Gan, Arman Cohan</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent advances in benchmark performance, strong computer-use agents remain expensive and slow in practice, since most systems invoke large multimodal models at nearly every interaction step. We argue that this uniform allocation of compute is fundamentally inefficient for long-horizon GUI tasks. Such trajectories are highly heterogeneous: many steps are routine and can be handled reliably by smaller, cheaper policies, while errors tend to concentrate at a relatively small number of high-risk moments. Across computer-use benchmarks, these failures repeatedly take two forms: progress stalls, where the agent loops, repeats ineffective actions, or fails to make meaningful progress, and silent semantic drift, where the agent continues taking locally plausible actions after already deviating from the user's true goal. To address this inefficiency, we propose an event-driven, step-level cascade for computer-use agents that runs a small policy by default and escalates to a stronger model only when lightweight learned monitors detect elevated risk. Our framework combines two complementary signals: a Stuck Monitor that detects degraded progress from recent reasoning-action history and triggers recovery, and a Milestone Monitor that identifies semantically meaningful checkpoints where sparse verification is most informative for catching drift. This design turns always-on frontier-model inference into adaptive, on-demand compute allocation over the course of an evolving interaction. The framework is modular and deployment-oriented: it can be layered on top of existing computer-use agents without changing the underlying agent architecture or retraining the large model.</p> - https://arxiv.org/abs/2604.27151 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling - https://arxiv.org/abs/2604.27039 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Zhang, Changyi Yang, Zijie Xia, Zhen Yang, Chengzhi Liu, Zhaotiao Weng, Yepeng Liu, Haobo Chen, Jin Pan, Chenyang Zhao, Yuheng Bu, Alkesh Patel, Zhe Gan, Xin Eric Wang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Token serves as the fundamental unit of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches lack fine-grained length modeling, operating primarily at the coarse-grained sequence level. We introduce the Length Value Model (LenVM), a token-level framework that models the remaining generation length. By formulating length modeling as a value estimation problem and assigning a constant negative reward to each generated token, LenVM predicts a bounded, discounted return that serves as a monotone proxy for the remaining generation horizon. This formulation yields supervision that is annotation-free, dense, unbiased, and scalable. Experiments on LLMs and VLMs demonstrate LenVM provides a highly effective signal at inference time. On the LIFEBench exact length matching task, applying LenVM to a 7B model improves the length score from 30.9 to 64.8, significantly outperforming frontier closed-source models. Furthermore, LenVM enables continuous control over the trade off between performance and efficiency. On GSM8K at a budget of 200 tokens, LenVM maintains 63% accuracy compared to 6 percent for token budget baseline. It also accurately predicts total generation length from the prompt boundary. Finally, LenVM's token-level values offer an interpretable view of generation dynamics, revealing how specific tokens shift reasoning toward shorter or longer regimes. Results demonstrate that LenVM supports a broad range of applications and token length can be effectively modeled as a token-level value signal, highlighting the potential of LenVM as a general framework for length modeling and as a length-specific value signal that could support future RL training. Code is available at https://github.com/eric-ai-lab/Length-Value-Model.</p> - https://arxiv.org/abs/2604.27039 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Efficient Training on Multiple Consumer GPUs with RoundPipe - https://arxiv.org/abs/2604.27085 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27085.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Luo, Shiwei Gao, Huichuan Zheng, Youyou Lu, Jiwu Shu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Fine-tuning Large Language Models (LLMs) on consumer-grade GPUs is highly cost-effective, yet constrained by limited GPU memory and slow PCIe interconnects. Pipeline parallelism combined with CPU offloading mitigates these hardware bottlenecks by reducing communication overhead. However, existing PP schedules suffer from an inherent limitation termed the weight binding issue. Binding uneven model stages (e.g., the LM head is large) to GPUs limits the pipeline's throughput to that of the GPU with the heaviest load, leading to severe pipeline bubbles. In this paper, we propose RoundPipe, a novel pipeline schedule that breaks the weight binding constraint on consumer GPU servers. RoundPipe treats GPUs as a pool of stateless execution workers and dynamically dispatches computation stages across devices in a round-robin manner, achieving a near-zero-bubble pipeline. To ensure training correctness and system efficiency, RoundPipe integrates a priority-aware transfer scheduling engine, a fine-grained distributed event-based synchronization protocol, and an automated layer partitioning algorithm. Evaluations on an 8times RTX 4090 server demonstrate that RoundPipe achieves 1.48--2.16times speedups over state-of-the-art baselines when fine-tuning 1.7B to 32B models. Remarkably, RoundPipe enables LoRA fine-tuning of the Qwen3-235B model with 31K sequence length on a single server. RoundPipe is publicly available as an open-source Python library with comprehensive documentation.</p> - https://arxiv.org/abs/2604.27085 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models - https://arxiv.org/abs/2604.26951 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26951.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gongbo Zhang, Wen Wang, Ye Tian, Li Yuan</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference steps within a single architecture, none address cross-architecture knowledge transfer, in which the teacher and student differ in architecture, attention mechanism, and tokenizer. We present TIDE, the first framework for cross-architecture dLLM distillation, comprising three modular components: (1) TIDAL, which jointly modulates distillation strength across training progress and diffusion timestep to account for the teacher's noise-dependent reliability; (2) CompDemo, which enriches the teacher's context via complementary mask splitting to improve predictions under heavy masking; and (3) Reverse CALM, a cross-tokenizer objective that inverts chunk-level likelihood matching, yielding bounded gradients and dual-end noise filtering. Distilling 8B dense and 16B MoE teachers into a 0.6B student via two heterogeneous pipelines outperforms the baseline by an average of 1.53 points across eight benchmarks, yielding notable gains in code generation, where HumanEval scores reach 48.78 compared to 32.3 for the AR baseline.</p> - https://arxiv.org/abs/2604.26951 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Co-Evolving Policy Distillation - https://arxiv.org/abs/2604.27083 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Naibin Gu, Chenxu Yang, Qingyi Si, Chuanyu Qin, Dingyu Yao, Peng Fu, Zheng Lin, Weiping Wang, Nan Duan, Jiaqi Wang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR suffers from inter-capability divergence cost, while the pipeline of first training experts and then performing OPD, though avoiding divergence, fails to fully absorb teacher capabilities due to large behavioral pattern gaps between teacher and student. We propose Co-Evolving Policy Distillation (CoPD), which encourages parallel training of experts and introduces OPD during each expert's ongoing RLVR training rather than after complete expert training, with experts serving as mutual teachers (making OPD bidirectional) to co-evolve. This enables more consistent behavioral patterns among experts while maintaining sufficient complementary knowledge throughout. Experiments validate that CoPD achieves all-in-one integration of text, image, and video reasoning capabilities, significantly outperforming strong baselines such as mixed RLVR and MOPD, and even surpassing domain-specific experts. The model parallel training pattern offered by CoPD may inspire a novel training scaling paradigm.</p> - https://arxiv.org/abs/2604.27083 - Wed, 29 Apr 2026 00:00:00 +0000 - - - ClawGym: A Scalable Framework for Building Effective Claw Agents - https://arxiv.org/abs/2604.26904 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26904.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fei Bai, Huatong Song, Shuang Sun, Daixuan Cheng, Yike Yang, Chuan Hao, Renyuan Li, Feng Chang, Yuan Wei, Ran Tao, Bryan Dai, Jian Yang, Wayne Xin Zhao</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integrating it with agent training and diagnostic evaluation. To address this challenge, we present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development. Concretely, we construct ClawGym-SynData, a diverse dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations, paired with realistic mock workspaces and hybrid verification mechanisms. We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories, and further explore reinforcement learning via a lightweight pipeline that parallelizes rollouts across per-task sandboxes.To support reliable evaluation, we further construct ClawGym-Bench, a benchmark of 200 instances calibrated through automated filtering and human-LLM review. Relevant resources will be soon released at https://github.com/ClawGym.</p> - https://arxiv.org/abs/2604.26904 - Wed, 29 Apr 2026 00:00:00 +0000 - - - GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents - https://arxiv.org/abs/2604.26752 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.26752.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> V Team, Wenyi Hong, Xiaotao Gu, Ziyang Pan, Zhen Yang, Yuting Wang, Yue Wang, Yuanchang Yue, Yu Wang, Yanling Wang, Yan Wang, Xijun Liu, Wenmeng Yu, Weihan Wang, Wei Li, Shuaiqi Duan, Sheng Yang, Ruiliang Lv, Mingdao Liu, Lihang Pan, Ke Ning, Junhui Ji, Jinjiang Wang, Jing Chen, Jiazheng Xu, Jiale Zhu, Jiale Cheng, Ji Qi, Guobing Gan, Guo Wang, Cong Yao, Zijun Dou, Zihao Zhou, Zihan Wang, Zhiqi Ge, Zhijie Li, Zhenyu Hou, Zhao Xue, Zehui Wang, Zehai He, Yusen Liu, Yukuo Cen, Yuchen Li, Yuan Wang, Yijian Lu, Yanzi Wang, Yadong Xue, Xinyu Zhang, Xinyu Liu, Wenkai Li, Tianyu Tong, Tianshu Zhang, Shengdong Yan, Qinkai Zheng, Mingde Xu, Licheng Bao, Jiaxing Xu, Jiaxin Fan, Jiawen Qian, Jiali Chen, Jiahui Lin, Haozhi Zheng, Haoran Wang, Haochen Li, Fan Yang, Dan Zhang, Chuangxin Zhao, Chengcheng Wu, Boyan Shi, Bowei Jia, Baoxu Wang, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Minlie Huang, Yuxiao Dong, Jie Tang</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.</p> - https://arxiv.org/abs/2604.26752 - Wed, 29 Apr 2026 00:00:00 +0000 - - - Instruction-Guided Poetry Generation in Arabic and Its Dialects - https://arxiv.org/abs/2604.27766 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry, Mohamed Anwar, Abed Alhakim Freihat, Preslav Nakov, Fajri Koto</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic speakers continue to value poetry, existing research on Arabic poetry within Large Language Models (LLMs) has primarily focused on analysis tasks such as interpretation or metadata prediction, e.g., rhyme schemes and titles. In contrast, our work addresses the practical aspect of poetry creation in Arabic by introducing controllable generation capabilities to assist users in writing poetry. Specifically, we present a large-scale, carefully curated instruction-based dataset in Modern Standard Arabic (MSA) and various Arabic dialects. This dataset enables tasks such as writing, revising, and continuing poems based on predefined criteria, including style and rhyme, as well as performing poetry analysis. Our experiments show that fine-tuning LLMs on this dataset yields models that can effectively generate poetry that is aligned with user requirements, based on both automated metrics and human evaluation with native Arabic speakers. The data and the code are available at https://github.com/mbzuai-nlp/instructpoet-ar</p> - https://arxiv.org/abs/2604.27766 + Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark + https://arxiv.org/abs/2604.27582 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> M. Riera-Marín, O. K. Sikha, J. Rodríguez-Comas, M. S. May, T. Kirscher, X. Coubez, P. Meyer, S. Faisan, Z. Pan, X. Zhou, X. Liang, C. Hémon, V. Boussot, J. -L. Dillenseger, J. -C. Nunes, K. -C. Kahl, C. Lüth, J. Traub, P. -H. Conze, M. M. Duh, A. Aubanell, R. de Figueiredo Cardoso, S. Egger-Hackenschmidt, J. García-López, M. A. González-Ballester, A. Galdran</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion (VI), i.e., tumor extension into adjacent critical vessels. Despite its importance for preoperative staging and surgical planning, computational VI assessment remains underexplored. Two major challenges are the lack of public datasets and the diagnostic ambiguity at the tumor-vessel interface, which leads to substantial inter-rater variability even among expert radiologists. To address these limitations, we introduce the CURVAS-PDACVI Dataset and Challenge, an open benchmark for uncertainty-aware AI in PDAC staging based on a densely annotated dataset with five independent expert annotations per scan. We also propose a multi-metric evaluation framework that extends beyond spatial overlap to include probabilistic calibration and VI assessment. Evaluation of six state-of-the-art methods shows that strong global volumetric overlap does not necessarily translate into reliable performance at clinically critical tumor-vessel interfaces. In particular, methods optimized for binary segmentation perform competitively on average overlap metrics, but often degrade in high-complexity cases with low expert consensus, either collapsing in volume or overextending at uncertain boundaries. In contrast, methods that model inter-rater disagreement produce better calibrated probabilistic maps and show greater robustness in these ambiguous cases. The benchmark highlights the limitations of volumetric accuracy as a proxy for localized surgical utility, motivating uncertainty-aware probabilistic models for preoperative decision-making.</p> + https://arxiv.org/abs/2604.27582 Thu, 30 Apr 2026 00:00:00 +0000 - World2Minecraft: Occupancy-Driven Simulated Scenes Construction - https://arxiv.org/abs/2604.27578 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27578.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lechao Zhang, Haoran Xu, Jingyu Gong, Xuhong Wang, Yuan Xie, Xin Tan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose World2Minecraft to convert real-world scenes into structured Minecraft environments based on 3D semantic occupancy prediction. In the reconstructed scenes, we can effortlessly perform downstream tasks such as Vision-Language Navigation(VLN). However, we observe that reconstruction quality heavily depends on accurate occupancy prediction, which remains limited by data scarcity and poor generalization in existing models. We introduce a low-cost, automated, and scalable data acquisition pipeline for creating customized occupancy datasets, and demonstrate its effectiveness through MinecraftOcc, a large-scale dataset featuring 100,165 images from 156 richly detailed indoor scenes. Extensive experiments show that our dataset provides a critical complement to existing datasets and poses a significant challenge to current SOTA methods. These findings contribute to improving occupancy prediction and highlight the value of World2Minecraft in providing a customizable and editable platform for personalized embodied AI research. Project page:https://world2minecraft.github.io/.</p> - https://arxiv.org/abs/2604.27578 + MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks + https://arxiv.org/abs/2604.27818 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27818.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jona te Lintelo, Lichao Wu, Marina Krček, Sengim Karayalçin, Stjepan Picek</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset of experts is engaged for each input, model behavior becomes coupled to routing decisions, yielding a difficult-to-control mechanism that can vary across safety-relevant scenarios. At the same time, adapting model behavior through full fine-tuning or retraining is costly, especially when developers need to rapidly configure the same model for different safety objectives. We present MASCing (MoE Activation Steering Configuration), the first framework that enables flexible reconfiguration of MoE behavior across diverse safety scenarios without retraining. MASCing uses an LSTM-based surrogate model to capture cross-layer routing dependencies and map routing logits to downstream behaviors. It then optimizes a steering matrix to identify behavior-relevant expert circuits and, at inference time, applies steering masks to the routing gates to override expert selection. This enables targeted enhancement or suppression of specific behaviors while preserving general language utility. To demonstrate its reconfigurability, we apply MASCing to two different safety-related objectives and observe consistent gains with negligible overhead across seven open-source MoE models. For multi-turn jailbreak defense, it improves the average defense success rate from 52.5% to 83.9%, with gains of up to 89.2%. For adult-content generation, MASCing enables models to comply with such requests that would otherwise be refused, increasing the average generation success rate from 52.6% to 82.0%, with gains of up to 93.0%. These results establish MASCing as a practical, lightweight, and flexible framework for scenario-specific safety reconfiguration in MoE models.</p> + https://arxiv.org/abs/2604.27818 Thu, 30 Apr 2026 00:00:00 +0000 - MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons - https://arxiv.org/abs/2604.28130 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kehong Gong, Zhengyu Wen, Dao Thien Phong, Mingxi Xu, Weixia He, Qi Wang, Ning Zhang, Zhengyu Li, Guanli Hou, Dongze Lian, Xiaoyu He, Mingyuan Zhang, Hanwang Zhang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized. We observe that the ambiguity in pose-to-rotation mapping arises from missing coordinate system information: the same joint positions can correspond to different rotations under different rest poses and local axis conventions. To resolve this, we introduce a reference pose-rotation pair from the target asset, which, together with the rest pose, not only anchors the mapping but also defines the underlying rotation coordinate system. This formulation turns rotation prediction into a well-constrained conditional problem and enables effective learning. In addition, our model predicts joint positions directly from video without relying on mesh intermediates, improving both robustness and efficiency. Both stages share a skeleton-aware Global-Local Graph-guided Multi-Head Attention (GL-GMHA) module for joint-level local reasoning and global coordination. Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines. Project page: https://animotionlab.github.io/MoCapAnythingV2/</p> - https://arxiv.org/abs/2604.28130 + Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO + https://arxiv.org/abs/2604.27488 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27488.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Tian, Jiawei Chen, Lifan Zheng, Mingxiang Tao, Xinyi Zeng, Zhaoxia Yin, Hang Su, Xian Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-based agents. Addressing the current fragmentation of the skill ecosystem, Skills-Coach explores the boundaries of skill capabilities, thereby facilitating the comprehensive competency coverage essential for intelligent applications. The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating the execution and evaluation of both original and optimized skills; and a Traceable Evaluation Module, which rigorously evaluates performance against specified criteria. Skills-Coach offers flexible execution options through its virtual and real modes. To validate its efficacy, we introduce Skill-X, a comprehensive benchmark dataset consisting of 48 diverse skills. Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents.</p> + https://arxiv.org/abs/2604.27488 Thu, 30 Apr 2026 00:00:00 +0000 - PhyCo: Learning Controllable Physical Priors for Generative Motion - https://arxiv.org/abs/2604.28169 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan, Manmohan Chandraker</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes-without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.</p> - https://arxiv.org/abs/2604.28169 + When Do Diffusion Models learn to Generate Multiple Objects? + https://arxiv.org/abs/2605.00273 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujin Jeong, Arnas Uselis, Iro Laina, Seong Joon Oh, Anna Rohrbach</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different dataset sizes: (1) concept generalization, where each individual concept is observed during training under potentially imbalanced data distributions, and (2) compositional generalization, where specific combinations of concepts are systematically held out. To study these regimes, we introduce mosaic (Multi-Object Spatial relations, AttrIbution, Counting), a controlled framework for dataset generation. By training diffusion models on mosaic, we find that scene complexity plays a dominant role rather than concept imbalance, and that counting is uniquely difficult to learn in low-data regimes. Moreover, compositional generalization collapses as more concept combinations are held out during training. These findings highlight fundamental limitations of diffusion models and motivate stronger inductive biases and data design for robust multi-object compositional generation.</p> + https://arxiv.org/abs/2605.00273 Thu, 30 Apr 2026 00:00:00 +0000 - InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation? - https://arxiv.org/abs/2604.27419 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Wang, Haoran Hu, Longze Chen, Hongbo Wang, Hamid Alinejad-Rokny, Yuan Lin, Min Yang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing benchmarks rely on idealized assumptions, especially for well-structured, information-rich inputs and static execution settings. In contrast, real-world development is constrained by a critical bottleneck: the semantic misalignment between ambiguous, low-quality instructions from non-expert users and model understanding, which results in a failure mode that we term blind execution. To address this gap, we introduce InteractWeb-Bench, the first multimodal interactive benchmark for website generation under non-expert low-code user conditions. InteractWeb-Bench introduces four types of user agents and persona-driven instruction perturbations to systematically simulate diverse user behaviors, including ambiguity, redundancy, and contradiction, grounded in requirement engineering defect taxonomies. We develop an interactive execution environment for agents, featuring a unified action space comprising Clarify, Implement, Verify, and Submit, enabling iterative intent refinement, code synthesis, and visual feedback-based validation. Extensive experiments and analysis reveal that frontier MLLM-based agents remain trapped in blind execution, exposing limitations in intent recognition and adaptive interaction.</p> - https://arxiv.org/abs/2604.27419 + WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments + https://arxiv.org/abs/2604.27776 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27776.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinchao Li, Yunxin Li, Chenrui Zhao, Zhenran Xu, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across geq 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.</p> + https://arxiv.org/abs/2604.27776 Thu, 30 Apr 2026 00:00:00 +0000 - Synthetic Computers at Scale for Long-Horizon Productivity Simulation - https://arxiv.org/abs/2604.28181 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Ge, Baolin Peng, Hao Cheng, Jianfeng Gao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity scenarios, we introduce Synthetic Computers at Scale, a scalable methodology for creating such environments with realistic folder hierarchies and content-rich artifacts (e.g., documents, spreadsheets, and presentations). Conditioned on each synthetic computer, we run long-horizon simulations: one agent creates productivity objectives that are specific to the computer's user and require multiple professional deliverables and about a month of human work; another agent then acts as that user and keeps working across the computer -- for example, navigating the filesystem for grounding, coordinating with simulated collaborators, and producing professional artifacts -- until these objectives are completed. In preliminary experiments, we create 1,000 synthetic computers and run long-horizon simulations on them; each run requires over 8 hours of agent runtime and spans more than 2,000 turns on average. These simulations produce rich experiential learning signals, whose effectiveness is validated by significant improvements in agent performance on both in-domain and out-of-domain productivity evaluations. Given that personas are abundant at billion scale, this methodology can in principle scale to millions or even billions of synthetic user worlds with sufficient compute, enabling broader coverage of diverse professions, roles, contexts, environments, and productivity needs. We argue that scalable synthetic computer creation, together with at-scale simulations, is highly promising as a foundational substrate for agent self-improvement and agentic reinforcement learning in long-horizon productivity scenarios.</p> - https://arxiv.org/abs/2604.28181 + Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling + https://arxiv.org/abs/2604.28075 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ansar Aynetdinov, Patrick Haller, Alan Akbik</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by constructing hierarchical quality filters applied to 500M web documents, comparing multi-epoch training on the filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epochs. Our findings suggest that for non-English LLMs, semantic concentration through quality filtering offers a more viable path to efficient language modeling than simply maximizing unique data volume. We release our German language models (called Boldt), as well as our cleaned evaluation benchmarks to the research community. Our experiments indicate that they achieve state-of-the-art results despite training on 10-360x fewer tokens than comparable models.</p> + https://arxiv.org/abs/2604.28075 Thu, 30 Apr 2026 00:00:00 +0000 - Representation Fréchet Loss for Visual Generation - https://arxiv.org/abs/2604.28190 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Yang, Zhengyang Geng, Xuan Ju, Yonglong Tian, Yue Wang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term this approach FD-loss. Optimizing FD-loss reveals several surprising findings. First, post-training a base generator with FD-loss in different representation spaces consistently improves visual quality. Under the Inception feature space, a one-step generator achieves0.72 FID on ImageNet 256x256. Second, the same FD-loss repurposes multi-step generators into strong one-step generators without teacher distillation, adversarial training or per-sample targets. Third, FID can misrank visual quality: modern representations can yield better samples despite worse Inception FID. This motivates FDr^k, a multi-representation metric. We hope this work will encourage further exploration of distributional distances in diverse representation spaces as both training objectives and evaluation metrics for generative models.</p> - https://arxiv.org/abs/2604.28190 + MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction + https://arxiv.org/abs/2604.27393 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27393.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Cui, Bokai Xu, Chongyi Wang, Tianyu Yu, Weiyue Sun, Yingjing Xu, Tianran Wang, Zhihui He, Wenshuo Ma, Tianchi Cai, Jiancheng Gui, Luoyuan Zhang, Xian Sun, Fuwei Huang, Moye Chen, Zhuo Lin, Hanyu Liu, Qingxin Gui, Qingzhe Han, Yuyang Wen, Huiping Liu, Rongkang Wang, Yaqi Zhang, Hongliang Wei, Chi Chen, You Li, Kechen Fang, Jie Zhou, Yuxuan Li, Guoyang Zeng, Chaojun Xiao, Yankai Lin, Xu Han, Maosong Sun, Zhiyuan Liu, Yuan Yao</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming interaction, yet they still remain far from human-level multimodal interaction. The key bottlenecks are no longer modality coverage or latency alone, but the interaction paradigm itself. First, perception and response are still separated into alternating phases, preventing models from incorporating new inputs for timely adjustment during generation. Second, most current models remain reactive, responding only to explicit user requests instead of acting proactively in the evolving multimodal environment. We present MiniCPM-o 4.5, our latest effort towards human-like multimodal interaction, which mitigates these gaps by real-time full-duplex omni-modal interaction. It can see, listen, and speak simultaneously in real-time, while also exhibiting proactive behaviors such as issuing reminders or comments based on its continuous understanding of the live scene. The key technique behind MiniCPM-o 4.5 is Omni-Flow, a unified streaming framework that aligns omni-modal inputs and outputs along a shared temporal axis. This formulation converts conventional turn-based interaction into a full-duplex, time-aligned process, enabling simultaneous perception and response and allowing proactive behavior to arise within the same framework. With a total of 9B parameters, MiniCPM-o 4.5 approaches Gemini 2.5 Flash in vision-language capabilities, delivering state-of-the-art open-source performance at its scale. It also surpasses Qwen3-Omni-30B-A3B in omni-modal understanding and delivers better speech generation, with significantly higher computation efficiency. Driven by its efficient architecture design and inference optimization, the model can perform real-time full-duplex omni-modal interaction on edge devices with less than 12GB RAM cost.</p> + https://arxiv.org/abs/2604.27393 Thu, 30 Apr 2026 00:00:00 +0000 - Leveraging Verifier-Based Reinforcement Learning in Image Editing - https://arxiv.org/abs/2604.27505 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanzhong Guo, Jie Wu, Jie Liu, Yu Gao, Zilyu Ye, Linxiao Yuan, Xionghui Wang, Yizhou Yu, Weilin Huang</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually give overall scores without detailed checks, ignoring different instruction requirements and causing biased rewards. To address this, we argue that the key is to move from a simple scorer to a reasoning verifier. We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) and then leverages it for downstream image editing. The Edit-RRM breaks instructions into distinct principles, evaluates the edited image against each principle, and aggregates these checks into an interpretable, fine-grained reward. To build such an RRM, we first apply supervised fine-tuning (SFT) as a ``cold-start'' to generate CoT reward trajectories. Then, we introduce Group Contrastive Preference Optimization (GCPO), a reinforcement learning algorithm that leverages human pairwise preference data to reinforce our pointwise RRM. After building the RRM, we use GRPO to train editing models with this non-differentiable yet powerful reward model. Extensive experiments demonstrate that our Edit-RRM surpasses powerful VLMs such as Seed-1.5-VL and Seed-1.6-VL as an editing-specific reward model, and we observe a clear scaling trend, with performance consistently improving from 3B to 7B parameters. Moreover, Edit-R1 delivers gains to editing models like FLUX.1-kontext, highlighting its effectiveness in enhancing image editing.</p> - https://arxiv.org/abs/2604.27505 + HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation + https://arxiv.org/abs/2604.28196 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Zhou, Dingkang Liang, Xiwu Chen, Feiyang Tan, Dingyuan Zhang, Hengshuang Zhao, Xiang Bai</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstrate impressive reasoning capabilities, they lack the capacity to predict future geometric evolution, creating a significant disparity between semantic interpretation and physical simulation. To bridge this gap, we propose HERMES++, a unified driving world model that integrates 3D scene understanding and future geometry prediction within a single framework. Our approach addresses the distinct requirements of these tasks through synergistic designs. First, a BEV representation consolidates multi-view spatial information into a structure compatible with LLMs. Second, we introduce LLM-enhanced world queries to facilitate knowledge transfer from the understanding branch. Third, a Current-to-Future Link is designed to bridge the temporal gap, conditioning geometric evolution on semantic context. Finally, to enforce structural integrity, we employ a Joint Geometric Optimization strategy that integrates explicit geometric constraints with implicit latent regularization to align internal representations with geometry-aware priors. Extensive evaluations on multiple benchmarks validate the effectiveness of our method. HERMES++ achieves strong performance, outperforming specialist approaches in both future point cloud prediction and 3D scene understanding tasks. The model and code will be publicly released at https://github.com/H-EmbodVis/HERMESV2.</p> + https://arxiv.org/abs/2604.28196 Thu, 30 Apr 2026 00:00:00 +0000 - Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows - https://arxiv.org/abs/2604.28139 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenxin Li, Zhengyang Tang, Huangxin Lin, Yunlong Lin, Shijue Huang, Shengyuan Liu, Bowen Ye, Rang Li, Lei Li, Benyou Wang, Yixuan Yuan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it difficult to evaluate agents against evolving workflow demand or verify whether a task was executed. We introduce Claw-Eval-Live, a live benchmark for workflow agents that separates a refreshable signal layer, updated across releases from public workflow-demand signals, from a reproducible, time-stamped release snapshot. Each release is constructed from public workflow-demand signals, with ClawHub Top-500 skills used in the current release, and materialized as controlled tasks with fixed fixtures, services, workspaces, and graders. For grading, Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts, using deterministic checks when evidence is sufficient and structured LLM judging only for semantic dimensions. The release contains 105 tasks spanning controlled business services and local workspace repair, and evaluates 13 frontier models under a shared public pass rule. Experiments reveal that reliable workflow automation remains far from solved: the leading model passes only 66.7% of tasks and no model reaches 70%. Failures are structured by task family and execution surface, with HR, management, and multi-system business workflows as persistent bottlenecks and local workspace repair comparatively easier but unsaturated. Leaderboard rank alone is insufficient because models with similar pass rates can diverge in overall completion, and task-level discrimination concentrates in a middle band of tasks. Claw-Eval-Live suggests that workflow-agent evaluation should be grounded twice, in fresh external demand and in verifiable agent action.</p> - https://arxiv.org/abs/2604.28139 - Thu, 30 Apr 2026 00:00:00 +0000 + Healthcare AI GYM for Medical Agents + https://arxiv.org/abs/2605.02943 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbyul Jeong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisions -- yet a unified training environment provides the breadth of clinical domains and specialized tools to train generalizable medical AI agents through reinforcement learning remains elusive. We present a comprehensive empirical study of multi-turn agentic RL for medical AI, built on , a gymnasium-compatible environment spanning 10 clinical domains with 3.6K+ tasks, 135 domain-specific tools, and a knowledge base of 828K medical passages. Our analysis reveals that agentic multi-turn structure degrades into verbose single-turn monologues, characterized by monotonic length explosion and a simultaneous erosion of tool-use frequency. We characterize how this collapse, alongside distillation instability, stems from the misalignment of sparse terminal rewards with sequential clinical trajectories. We find that vanilla GRPO achieves strong final accuracy on some benchmarks but suffers from training instability, evidenced by significant oscillations in response length and prolonged convergence periods. To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation (TT-OPD), a self-distillation framework where a gradient-free EMA teacher leverages outcome-privileged information to provide dense, outcome-aware KL regularization at every conversation turn. TT-OPD achieves the best performance on 10 of 18 benchmarks with an average +3.9~pp improvement over the non-RL baseline with faster early convergence, controlled response length, and sustained multi-turn tool use.</p> + https://arxiv.org/abs/2605.02943 + Fri, 01 May 2026 00:00:00 +0000 - ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control - https://arxiv.org/abs/2604.27711 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanghao Zhou, Jingyu Ma, Yibo Peng, Zhenguo Sun, Yu Bai, Börje F. Karlsson</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Humanoid control systems have made significant progress in recent years, yet modeling fluent interaction-rich behavior between a robot, its surrounding environment, and task-relevant objects remains a fundamental challenge. This difficulty arises from the need to jointly capture spatial context, temporal dynamics, robot actions, and task intent at scale, which is a poor match to conventional supervision. We propose ExoActor, a novel framework that leverages the generalization capabilities of large-scale video generation models to address this problem. The key insight in ExoActor is to use third-person video generation as a unified interface for modeling interaction dynamics. Given a task instruction and scene context, ExoActor synthesizes plausible execution processes that implicitly encode coordinated interactions between robot, environment, and objects. Such video output is then transformed into executable humanoid behaviors through a pipeline that estimates human motion and executes it via a general motion controller, yielding a task-conditioned behavior sequence. To validate the proposed framework, we implement it as an end-to-end system and demonstrate its generalization to new scenarios without additional real-world data collection. Furthermore, we conclude by discussing limitations of the current implementation and outlining promising directions for future research, illustrating how ExoActor provides a scalable approach to modeling interaction-rich humanoid behaviors, potentially opening a new avenue for generative models to advance general-purpose humanoid intelligence.</p> - https://arxiv.org/abs/2604.27711 - Thu, 30 Apr 2026 00:00:00 +0000 + Recovering Hidden Reward in Diffusion-Based Policies + https://arxiv.org/abs/2605.00623 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00623.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanbiao Ji, Qiuchang Li, Yuting Hu, Shaokai Wu, Wenyuan Xie, Guodong Zhang, Qicheng He, Deyi Ji, Yue Ding, Hongtao Lu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under maximum-entropy optimality, the score function learned via denoising score matching recovers the gradient of the expert's soft Q-function, enabling reward extraction without adversarial training. Formally, we prove that constraining the learned field to be conservative reduces hypothesis complexity and tightens out-of-distribution generalization bounds. We further characterize the identifiability of recovered rewards and bound how score estimation errors propagate to action preferences. Empirically, EnergyFlow achieves state-of-the-art imitation performance on various manipulation tasks while providing an effective reward signal for downstream reinforcement learning that outperforms both adversarial IRL methods and likelihood-based alternatives. These results show that the structural constraints required for valid reward extraction simultaneously serve as beneficial inductive biases for policy generalization. The code is available at https://github.com/sotaagi/EnergyFlow.</p> + https://arxiv.org/abs/2605.00623 + Fri, 01 May 2026 00:00:00 +0000 - Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists - https://arxiv.org/abs/2604.28158 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujun Wu, Dongxu Zhang, Xinchen Li, Jinhang Xu, Yiling Duan, Yumou Liu, Jiabao Pan, Xuanhe Zhou, Jingxuan Wei, Siyuan Li, Jintao Chen, Conghui He, Cheng Tan</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge, adapt, and build upon one another. With the rise of AI-driven research agents as a new class of consumers of scientific knowledge, this limitation becomes increasingly consequential, as such agents cannot reliably reconstruct method evolution topologies from unstructured text. We introduce Intern-Atlas, a methodological evolution graph that automatically identifies method-level entities, infers lineage relationships among methodologies, and captures the bottlenecks that drive transitions between successive innovations. Built from 1,030,314 papers spanning AI conferences, journals, and arXiv preprints, the resulting graph comprises 9,410,201 semantically typed edges, each grounded in verbatim source evidence, forming a queryable causal network of methodological development. To operationalize this structure, we further propose a self-guided temporal tree search algorithm for constructing evolution chains that trace the progression of methods over time. We evaluate the quality of the resulting graph against expert-curated ground-truth evolution chains and observe strong alignment. In addition, we demonstrate that Intern-Atlas enables downstream applications in idea evaluation and automated idea generation. We position methodological evolution graphs as a foundational data layer for the emerging automated scientific discovery.</p> - https://arxiv.org/abs/2604.28158 - Thu, 30 Apr 2026 00:00:00 +0000 + Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation + https://arxiv.org/abs/2605.00529 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziwen Zhao, Menglin Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where k-means clustering introduces noise due to rigid distribution assumptions; (2) structural isolation, as tree indexes lack explicit cross-document connections; and (3) coarse abstraction, which obscures fine-grained details. To address these limitations, we propose Ψ-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts to data distributions without a priori assumption. Second, a multi-granular retrieval agent that intelligently interacts with the knowledge base with reorganized queries and an agent-powered hybrid retriever. Ψ-RAG supports diverse tasks from token-level question answering to document-level summarization. On cross-document multi-hop QA benchmarks, it outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score. Code is available at https://github.com/Newiz430/Psi-RAG.</p> + https://arxiv.org/abs/2605.00529 + Fri, 01 May 2026 00:00:00 +0000 - Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling - https://arxiv.org/abs/2604.28185 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keming Wu, Zuhao Yang, Kaichen Zhang, Shizun Wang, Haowei Zhu, Sicong Leng, Zhongyu Yang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Wang, Hui Zhang, Haonan Wang, Hang Zhou, Yifan Pu, Xingxuan Li, Fangneng Zhan, Bo Li, Lidong Bing, Yuxin Song, Ziwei Liu, Wenhu Chen, Jingdong Wang, Xinchao Wang, Xiaojuan Qi, Shijian Lu, Bin Wang</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.</p> - https://arxiv.org/abs/2604.28185 - Thu, 30 Apr 2026 00:00:00 +0000 + ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning + https://arxiv.org/abs/2605.00380 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00380.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Li Wang, Xiaodong Lu, Wei Lin, Ran He, Guojun Yin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability without losing diversity, this paper proposes negative sample projection Residual Reinforcement Learning (ResRL) that decouples similar semantic distributions among positive and negative responses. We theoretically link Lazy Likelihood Displacement (LLD) to negative-positive head-gradient interference and derive a single-forward proxy that upper-bounds representation alignment to guide conservative advantage reweighting. ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong baselines on average across twelve benchmarks spanning Mathematics, Code, Agent Tasks, and Function Calling. Notably, ResRL surpasses NSR on mathematical reasoning by 9.4\% in Avg@16 and 7.0\% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git.</p> + https://arxiv.org/abs/2605.00380 + Fri, 01 May 2026 00:00:00 +0000 - Heterogeneous Scientific Foundation Model Collaboration - https://arxiv.org/abs/2604.27351 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27351.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Li, Jiaru Zou, Feihao Fang, Xuying Ning, Mengting Ai, Tianxin Wei, Sirui Chen, Xiyuan Yang, Jingrui He</p><p><b>Upvotes:</b> 193</p><p><b>Summary:</b> Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific domains where domain-specific foundation models have been developed to address specialized tasks beyond natural language. In this work, we introduce Eywa, a heterogeneous agentic framework designed to extend language-centric systems to a broader class of scientific foundation models. The key idea of Eywa is to augment domain-specific foundation models with a language-model-based reasoning interface, enabling language models to guide inference over non-linguistic data modalities. This design allows predictive foundation models, which are typically optimized for specialized data and tasks, to participate in higher-level reasoning and decision-making processes within agentic systems. Eywa can serve as a drop-in replacement for a single-agent pipeline (EywaAgent) or be integrated into existing multi-agent systems by replacing traditional agents with specialized agents (EywaMAS). We further investigate a planning-based orchestration framework in which a planner dynamically coordinates traditional agents and Eywa agents to solve complex tasks across heterogeneous data modalities (EywaOrchestra). We evaluate Eywa across a diverse set of scientific domains spanning physical, life, and social sciences. Experimental results demonstrate that Eywa improves performance on tasks involving structured and domain-specific data, while reducing reliance on language-based reasoning through effective collaboration with specialized foundation models.</p> - https://arxiv.org/abs/2604.27351 - Thu, 30 Apr 2026 00:00:00 +0000 + Trees to Flows and Back: Unifying Decision Trees and Diffusion Models + https://arxiv.org/abs/2605.00414 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sai Niranjan Ramachandran, Suvrit Sra</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: Global Trajectory Score Matching (GTSM), for which gradient boosting (in an idealized version) is asymptotically optimal. We underscore the conceptual value of our work through two key practical instantiations: \treeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2\times computational speedup, and \dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2\% on many benchmarks.</p> + https://arxiv.org/abs/2605.00414 + Fri, 01 May 2026 00:00:00 +0000 + + + End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer + https://arxiv.org/abs/2605.00503 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00503.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenda Chu, Bingliang Zhang, Jiaqi Han, Yizhuo Li, Linjie Yang, Yisong Yue, Qiushan Guo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision from generation results to the tokenizer. This contrasts with prior two-stage approaches that train tokenizers and generative models separately. We further investigate leveraging vision foundation models to improve 1D tokenizers for autoregressive modeling. Our autoregressive generative model achieves strong empirical results, including a state-of-the-art FID score of 1.48 without guidance on ImageNet 256x256 generation.</p> + https://arxiv.org/abs/2605.00503 + Fri, 01 May 2026 00:00:00 +0000 + + + Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies + https://arxiv.org/abs/2605.00416 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00416.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Wang, Xinchen Li, Pengwei Xie, Pu Yang, Buqing Nie, Yunuo Cai, Qinglin Zhang, Chendi Qu, Jeffrey Wu, Jianheng Song, Xinlin Ren, Jingshun Huang, Mingjie Pan, Siyuan Feng, Zhi Chen, Jianlan Luo</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter distribution shifts, long-tail failures, task variations, and human correction opportunities that fixed demonstration datasets cannot fully capture. We present Learning While Deploying (LWD), a fleet-scale offline-to-online reinforcement learning framework for continual post-training of generalist Vision-Language-Action (VLA) policies. Starting from a pretrained VLA policy, LWD closes the loop between deployment, shared physical experience, policy improvement, and redeployment by using autonomous rollouts and human interventions collected across a robot fleet. To stabilize learning from heterogeneous, sparse-reward fleet data, LWD combines Distributional Implicit Value Learning (DIVL) for robust value estimation with Q-learning via Adjoint Matching (QAM) for policy extraction in flow-based VLA action generators. We validate LWD on a fleet of 16 dual-arm robots across eight real-world manipulation tasks, including semantic grocery restocking and 3--5 minute long-horizon tasks. A single generalist policy improves as fleet experience accumulates, reaching an average success rate of 95%, with the largest gains on long-horizon tasks.</p> + https://arxiv.org/abs/2605.00416 + Fri, 01 May 2026 00:00:00 +0000 + + + Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning + https://arxiv.org/abs/2605.00347 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengshuai Shi, Wenzhe Li, Xinran Liang, Yizhou Lu, Wenjia Yang, Ruirong Feng, Seth Karten, Ziran Yang, Zihan Ding, Gabriel Sarch, Danqi Chen, Karthik Narasimhan, Chi Jin</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier. However, existing approaches either rely on large-scale supervised fine-tuning (SFT) on human trajectories or apply reinforcement learning (RL) only in relatively short-horizon settings (typically around 20--30 turns). In this work, we study RL-based training of VLMs for long-horizon decision-making in Super Mario Land, a visually grounded environment requiring 100+ turns of interaction with coordinated perception, reasoning, and action. We begin with a systematic investigation of key algorithmic components and propose an adapted variant of PPO with a lightweight turn-level critic, which substantially improves training stability and sample efficiency over critic-free methods such as GRPO and Reinforce++. We further show that pretrained VLMs provide strong action priors, significantly improving sample efficiency during RL training and reducing the need for manual design choices such as action engineering, compared to classical deep RL trained from scratch. Building on these insights, we introduce Odysseus, an open training framework for VLM agents, achieving substantial gains across multiple levels of the game and at least 3 times average game progresses than frontier models. Moreover, the trained models exhibit consistent improvements under both in-game and cross-game generalization settings, while maintaining general-domain capabilities. Overall, our results identify key ingredients for making RL stable and effective in long-horizon, multi-modal settings, and provide practical guidance for developing VLMs as embodied agents.</p> + https://arxiv.org/abs/2605.00347 + Fri, 01 May 2026 00:00:00 +0000 + + + Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance + https://arxiv.org/abs/2605.00553 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minchan Kwon, Sunghyun Baek, Minseo Kim, Jaemyung Yu, Dongyoon Han, Junmo Kim</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in red-teaming is important, but achieving both is challenging. Generative Flow Networks (GFNs) that perform distribution matching are a promising methods, but they are notorious for training instability and mode collapse. In particular, unstable rewards in red-teaming accelerate mode collapse. We propose Stable-GFN (S-GFN), which eliminates partition function Z estimation in GFN and reduces training instability. S-GFN avoids Z-estimation through pairwise comparisons and employs a robust masking methodology against noisy rewards. Additionally, we propose a fluency stabilizer to prevent the model from getting stuck in local optima that produce gibberish. S-GFN provides more stable training while maintaining the optimal policy of GFN. We demonstrate the overwhelming attack performance and diversity of S-GFN across various settings.</p> + https://arxiv.org/abs/2605.00553 + Fri, 01 May 2026 00:00:00 +0000 + + + Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs + https://arxiv.org/abs/2605.00814 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00814.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Zefeng He, Muxin Fu, Daizong Liu, Wei-Long Zheng, Yu Cheng</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition function, causing visual attention to decay inversely with generated sequence length. To counteract this, we propose Persistent Visual Memory (PVM), a lightweight learnable module designed to ensure sustained, on-demand visual perception. Integrated as a parallel branch alongside the Feed-Forward Network (FFN) in LVLMs, PVM establishes a distance-agnostic retrieval pathway that directly provides visual embeddings for precise visual perception, thereby structurally mitigating the signal suppression inherent to deep generation. Extensive experiments on Qwen3-VL models demonstrate that PVM brings notable improvements with negligible parameter overhead, delivering consistent average accuracy gains across both 4B and 8B scales, particularly in complex reasoning tasks that demand persistent visual perception. Furthermore, in-depth analysis reveals that PVM can resist length-induced signal decay and accelerate internal prediction convergence.</p> + https://arxiv.org/abs/2605.00814 + Fri, 01 May 2026 00:00:00 +0000 + + + Map2World: Segment Map Conditioned Text to 3D World Generation + https://arxiv.org/abs/2605.00781 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00781.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang, Jiaolong Yang, Kyoung Mu Lee</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> 3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid layouts and suffer from inconsistencies in object scale throughout the entire world. In this work, we introduce a novel framework, Map2World, that first enables 3D world generation conditioned on user-defined segment maps of arbitrary shapes and scales, ensuring global-scale consistency and flexibility across expansive environments. To further enhance the quality, we propose a detail enhancer network that generates fine details of the world. The detail enhancer enables the addition of fine-grained details without compromising overall scene coherence by incorporating global structure information. We design the entire pipeline to leverage strong priors from asset generators, achieving robust generalization across diverse domains, even under limited training data for scene generation. Extensive experiments demonstrate that our method significantly outperforms existing approaches in user-controllability, scale consistency, and content coherence, enabling users to generate 3D worlds under more complex conditions.</p> + https://arxiv.org/abs/2605.00781 + Fri, 01 May 2026 00:00:00 +0000 + + + Let ViT Speak: Generative Language-Image Pre-training + https://arxiv.org/abs/2605.00809 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00809.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Fang, Mengcheng Lan, Zilong Huang, Weixian Lei, Yunqing Zhao, Yujie Zhong, Yingchen Yu, Qi She, Yao Zhao, Yunchao Wei</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> In this paper, we present Generative Language-Image Pre-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) Simplicity: a single transformer jointly models visual and textual tokens; (2) Scalability: it scales effectively with both data and model size; and (3) Performance: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.</p> + https://arxiv.org/abs/2605.00809 + Fri, 01 May 2026 00:00:00 +0000 + + + Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL + https://arxiv.org/abs/2604.28123 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.28123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model's original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, where perception errors and reasoning failures follow distinct drift patterns that compound during subsequent RL. We introduce PRISM, a three-stage pipeline that mitigates this drift by inserting an explicit distribution-alignment stage between SFT and RLVR. Building on the principle of on-policy distillation (OPD), PRISM casts alignment as a black-box, response-level adversarial game between the policy and a Mixture-of-Experts (MoE) discriminator with dedicated perception and reasoning experts, providing disentangled corrective signals that steer the policy toward the supervision distribution without requiring access to teacher logits. While 1.26M public demonstrations suffice for broad SFT initialization, distribution alignment demands higher-fidelity supervision; we therefore curate 113K additional demonstrations from Gemini 3 Flash, featuring dense visual grounding and step-by-step reasoning on the hardest unsolved problems. Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the SFT-to-RLVR baseline on 4B and 8B, respectively. Our code, data, and model checkpoints are publicly available at https://github.com/XIAO4579/PRISM.</p> + https://arxiv.org/abs/2604.28123 + Fri, 01 May 2026 00:00:00 +0000 + + + UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors + https://arxiv.org/abs/2605.00658 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Houyuan Chen, Hong Li, Xianghao Kong, Tianrui Zhu, Shaocong Xu, Weiqing Xiao, Yuwei Guo, Chongjie Ye, Lvmin Zhang, Hao Zhao, Anyi Rao</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs that are activated when a modality serves as the generation target, preserving the strong priors of the VDM. Cross-Modal Self-Attention (CMSA) shares keys and values across modalities while keeping modality-specific queries, facilitating information exchange and inter-modal alignment. We instantiate UniVidX in two domains: UniVid-Intrinsic, for RGB videos and intrinsic maps including albedo, irradiance, and normal; and UniVid-Alpha, for blended RGB videos and their constituent RGBA layers. Experiments show that both models achieve performance competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github.io/UniVidX.github.io/</p> + https://arxiv.org/abs/2605.00658 + Fri, 01 May 2026 00:00:00 +0000 + + + Agentic AI Systems Should Be Designed as Marginal Token Allocators + https://arxiv.org/abs/2605.01214 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01214.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqi Zhu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> This position paper argues that agentic AI systems should be designed and evaluated as marginal token allocation economies rather than as text generators priced by the unit. We follow a single request -- a developer asking a coding agent to fix a failing test -- through four economic layers that today are designed in isolation: a router that decides which model answers, an agent that decides whether to plan, act, verify, or defer, a serving stack that decides how to produce each token, and a training pipeline that decides whether the trace is worth learning from. We show that all four layers are solving the same first-order condition -- marginal benefit equals marginal cost plus latency cost plus risk cost -- with different index sets and different prices. The framing is deliberately minimal: we do not propose a complete theory of AI economics. But adopting marginal token allocation as the shared accounting object explains why systems that locally minimize tokens globally misallocate them, predicts a small set of recurring failure modes (over-routing, over-delegation, under-verification, serving congestion, stale rollouts, cache misuse), and points to a concrete research agenda in token-aware evaluation, autonomy pricing, congestion-priced serving, and risk-adjusted RL budgeting.</p> + https://arxiv.org/abs/2605.01214 + Sat, 02 May 2026 00:00:00 +0000 + + + Prescriptive Scaling Laws for Data Constrained Training + https://arxiv.org/abs/2605.01640 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01640.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Justin Lovelace, Christian Belardi, Srivatsa Kundurthy, Shriya Sudhakar, Kilian Q. Weinberger</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law assumes every training token is unique. This limits its ability to guide pretraining decisions in data-constrained regimes. We model the excess loss under repetition with a simple additive overfitting penalty and find that it accurately describes model behavior. Our scaling law yields qualitatively new compute-optimal allocation advice. Beyond a point, further repetition is counterproductive and compute is better spent on model capacity. We show that following our law's recommended configuration improves performance in data-constrained regimes. Finally, because our one-parameter form isolates overfitting in a single coefficient, it enables direct comparison across training configurations. As a case study, we show that strong weight decay (λ=1.0) reduces this coefficient by approximately 70%, providing a scaling-law explanation for recent findings that optimal weight decay in data-constrained regimes is an order of magnitude larger than standard practice.</p> + https://arxiv.org/abs/2605.01640 + Sat, 02 May 2026 00:00:00 +0000 + + + SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion + https://arxiv.org/abs/2605.01466 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01466.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaoyang Li, Zhichao You, Tianrui Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.</p> + https://arxiv.org/abs/2605.01466 + Sat, 02 May 2026 00:00:00 +0000 + + + ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue + https://arxiv.org/abs/2605.01371 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01371.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daoxuan Zhang, Ping Chen, Jianyi Zhou, Shuo Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making, making them inherently suited for UAV Search and Rescue (SAR). However, existing UAV SAR research is dominated by traditional vision and path-planning methods and lacks a comprehensive and unified benchmark for embodied agents. To bridge this gap, we first propose the novel task of Embodied Search and Rescue (ESAR), which requires aerial agents to autonomously explore complex environments, identify rescue clues, and reason about victim locations to execute informed decision-making. Additionally, we present ESARBench, the first comprehensive benchmark designed to evaluate MLLM-driven UAV agents in highly realistic SAR scenarios. Leveraging Unreal Engine 5 and AirSim, we construct four high-fidelity, large-scale open environments mapped directly from real-world Geographic Information System (GIS) data to ensure photorealistic landscapes. To rigorously simulate actual rescue operations, our benchmark incorporates dynamic variables including weather conditions, time of day, and stochastic clue placement. Furthermore, we create a dataset of 600 tasks modeled after real-world rescue cases and propose a robust set of evaluation metrics. We evaluate diverse baselines, ranging from traditional heuristics to advanced ground and aerial MLLM-based ObjectNav agents. Experimental results highlight the challenges in ESAR, revealing critical bottlenecks in spatial memory, aerial adaptation, and the trade-off between search efficiency and flight safety. We hope ESARBench serves as a valuable resource to advance research on Embodied Search and Rescue domain. Source code and project page: https://4amgodvzx.github.io/ESAR.github.io.</p> + https://arxiv.org/abs/2605.01371 + Sat, 02 May 2026 00:00:00 +0000 + + + Hallucinations Undermine Trust; Metacognition is a Way Forward + https://arxiv.org/abs/2605.01428 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gal Yona, Mor Geva, Yossi Matias</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLMs are increasingly expected to be helpful in more complex or nuanced setups. Yet even in the simplest setting -- factoid question-answering with clear ground truth-frontier models without external tools continue to hallucinate. We argue that most factuality gains in this domain have come from expanding the model's knowledge boundary (encoding more facts) rather than improving awareness of that boundary (distinguishing known from unknown). We conjecture that the latter is inherently difficult: models may lack the discriminative power to perfectly separate truths from errors, creating an unavoidable tradeoff between eliminating hallucinations and preserving utility. This tradeoff dissolves under a different framing. If we understand hallucinations as confident errors -- incorrect information delivered without appropriate qualification -- a third path emerges beyond the answer-or-abstain dichotomy: expressing uncertainty. We propose faithful uncertainty: aligning linguistic uncertainty with intrinsic uncertainty. This is one facet of metacognition -- the ability to be aware of one's own uncertainty and to act on it. For direct interaction, acting on uncertainty means communicating it honestly; for agentic systems, it becomes the control layer governing when to search and what to trust. Metacognition is thus essential for LLMs to be both trustworthy and capable; we conclude by highlighting open problems for progress towards this objective.</p> + https://arxiv.org/abs/2605.01428 + Sat, 02 May 2026 00:00:00 +0000 + + + Linear-Time Global Visual Modeling without Explicit Attention + https://arxiv.org/abs/2605.01711 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01711.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruize He, Dongchen Han, Gao Huang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we demonstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters. Through this lens, we explain attention's global modeling power not as explicit token-wise aggregation, but as an implicit process where dynamically generated parameters act as a compressed representation of the global context. Inspired by this insight, we investigate a fundamental question: can we achieve Transformer-level sequence global modeling entirely through dynamic parameterization while maintaining linear complexity, effectively replacing explicit attention? To explore this, we design various dynamic parameter prediction strategies and integrate them into standard network layers. Extensive empirical studies on vision models demonstrate that dynamic parameterization can indeed serve as a highly effective, linear-complexity alternative to explicit attention, opening new pathways for efficient sequence modeling. Code is available at https://github.com/LeapLabTHU/WeightFormer.</p> + https://arxiv.org/abs/2605.01711 + Sun, 03 May 2026 00:00:00 +0000 + + + TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis + https://arxiv.org/abs/2605.01717 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01717.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinran Li, Xinze Che, Yifan Lyu, Zhiqi Huang, Xiujuan Xu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce structural noise and fail to consider the temporal sequence of the dialogues, or use standard RoPE, which implicitly captures relative distances in a flat sequence but cannot clearly separate the token-level syntactic order from the utterance-level progression, and may suffer from the Distance Dilution problem. To address these issues, we propose a new framework that combines Thread-Constrained Directed Acyclic Graph (TC-DAG) and Discourse-Aware Rotary Position Embedding (D-RoPE). Specifically, TC-DAG filters out cross-thread noise based on thread constraints, maintains global connectivity through root anchoring, and incorporates the temporal sequence of the dialogues. D-RoPE aligns multi-layer semantics using dual-stream projection and multi-scale frequency signals, captures thread dependencies using tree-like distances, and alleviates the token-level Distance Dilution problem by incorporating utterance-level progressions. Experimental results on two benchmark datasets demonstrate that our framework achieves state-of-the-art performance.</p> + https://arxiv.org/abs/2605.01717 + Sun, 03 May 2026 00:00:00 +0000 + + + Motion-Aware Caching for Efficient Autoregressive Video Generation + https://arxiv.org/abs/2605.01725 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01725.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Xu, Yuexiao Ma, Songwei Liu, Xuzhe Zheng, Shiwei Liu, Chenqian Yan, Xiawu Zheng, Rongrong Ji, Fei Chao, Xing Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of 6.28times and 1.64times respectively, while effectively preserving generation quality (VBench: 1%downarrow and 0.01%downarrow respectively). The code is available at https://github.com/ywlq/MotionCache.</p> + https://arxiv.org/abs/2605.01725 + Sun, 03 May 2026 00:00:00 +0000 + + + Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction + https://arxiv.org/abs/2605.05242 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuofeng Li, Haoxiang Zhang, Cong Wei, Pan Lu, Ping Nie, Yi Lu, Yuyang Bai, Shangbin Feng, Hangxiao Zhu, Ming Zhong, Yuyu Zhang, Jianwen Xie, Yejin Choi, James Zou, Jiawei Han, Wenhu Chen, Jimmy Lin, Dongfu Jiang, Yu Zhang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning. Agentic tasks further exacerbate this limitation because they require agents to orchestrate multiple steps, including discovering intermediate entities, combining weak clues, and revising the plan after observing partial evidence. To tackle the limitation, we study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools (e.g., grep, file reads, shell commands, lightweight scripts), without any embedding model, vector index, or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines on several BRIGHT and BEIR datasets, and attains strong accuracy on BrowseComp-Plus and multi-hop QA without relying on any conventional semantic retriever. Our results indicate that as language agents become stronger, retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus, with which DCI opens a broader interface-design space for agentic search.</p> + https://arxiv.org/abs/2605.05242 + Sun, 03 May 2026 00:00:00 +0000 + + + From Context to Skills: Can Language Models Learn from Context Skillfully? + https://arxiv.org/abs/2604.27660 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.27660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuzheng Si, Haozhe Zhao, Yu Lei, Qingyi Wang, Dingwei Chen, Zhitong Wang, Zhenhailong Wang, Kangyang Luo, Zheng Wang, Gang Chen, Fanchao Qi, Minjia Zhang, Maosong Sun</p><p><b>Upvotes:</b> 148</p><p><b>Summary:</b> Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, constructing such skills for context learning scenarios faces two challenges: the prohibitive cost of manual skill annotation for long, technically dense contexts, and the lack of external feedback for automated skill construction. In this paper, we propose Ctx2Skill, a self-evolving framework that autonomously discovers, refines, and selects context-specific skills without human supervision or external feedback. At its core, a multi-agent self-play loop has a Challenger that generates probing tasks and rubrics, a Reasoner that attempts to solve them guided by an evolving skill set, and a neutral Judge that provides binary feedback. Crucially, both the Challenger and the Reasoner evolve through accumulated skills: dedicated Proposer and Generator agents analyze failure cases and synthesize them into targeted skill updates for both sides, enabling automated skill discovery and refinement. To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance across representative cases for the Reasoner side, ensuring robust and generalizable skill evolution. The resulting skills can be plugged into any language model to obtain better context learning capability. Evaluated on four context learning tasks from CL-bench, Ctx2Skill consistently improves solving rates across backbone models.</p> + https://arxiv.org/abs/2604.27660 + Sun, 03 May 2026 00:00:00 +0000 + + + Perceptual Flow Network for Visually Grounded Reasoning + https://arxiv.org/abs/2605.02730 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yangfu Li, Yuning Gong, Hongjian Zhan, Teng Li, Yuanhuiyi Lyu, Tianyi Chen, Qi Liu, Ziyuan Huang, Zhihang Zhong, Dandan Zheng, Yue Lu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce geometric priors from visual experts as additional supervision. However, we observe that such supervision is typically suboptimal: it is biased toward geometric precision and offers limited reasoning utility. To bridge this gap, we propose Perceptual Flow Network (PFlowNet), which eschews rigid alignment with the expert priors and achieves interpretable yet more effective visual reasoning. Specifically, PFlowNet decouples perception from reasoning to establish a self-conditioned generation process. Based on this, it integrates multi-dimensional rewards with vicinal geometric shaping via variational reinforcement learning, thereby facilitating reasoning-oriented perceptual behaviors while preserving visual reliability. PFlowNet delivers a provable performance guarantee and competitive empirical results, particularly setting new SOTA records on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).</p> + https://arxiv.org/abs/2605.02730 + Mon, 04 May 2026 00:00:00 +0000 + + + Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces + https://arxiv.org/abs/2605.02801 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02801.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenchen Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.</p> + https://arxiv.org/abs/2605.02801 + Mon, 04 May 2026 00:00:00 +0000 + + + PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments + https://arxiv.org/abs/2605.02240 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoqi Liu, Imran Q. Mohiuddin, Austin J. Schoeffler, Kavita Renduchintala, Ashwin Nayak, Prasantha L. Vemu, Shivam C. Vedak, Kameron C. Black, John L. Havlik, Isaac Ogunmola, Stephen P. Ma, Roopa Dhatt, Jonathan H. Chen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record (EHR) environments. Existing medical agent benchmarks primarily focus on static knowledge recall, single-step atomic actions, or action intent without verifiable execution against the environment. As a result, they fail to capture the long-horizon, composite workflows that characterize real clinical systems. PhysicianBench comprises 100 long-horizon tasks adapted from real consultation cases between primary care and subspecialty physicians, with each task independently reviewed by a separate panel of physicians. Tasks are instantiated in an EHR environment with real patient records and accessed through the same standard APIs used by commercial EHR vendors. Tasks span 21 specialties (e.g., cardiology, endocrinology, oncology, psychiatry) and diverse workflow types (e.g., diagnosis interpretation, medication prescribing, treatment planning), requiring an average of 27 tool calls per task. Solving each task requires retrieving data across encounters, reasoning over heterogeneous clinical information, executing consequential clinical actions, and producing clinical documentation. Each task is decomposed into structured checkpoints (670 in total across the benchmark) capturing distinct stages of completion graded by task-specific scripts with execution-grounded verification. Across 13 proprietary and open-source LLM agents, the best-performing model achieves only 46% success rate (pass@1), while open-source models reach at most 19%, revealing a substantial gap between current agent capabilities and the demands of real-world clinical workflows. PhysicianBench provides a realistic and execution-grounded benchmark for measuring progress toward autonomous clinical agents.</p> + https://arxiv.org/abs/2605.02240 + Mon, 04 May 2026 00:00:00 +0000 + + + T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning + https://arxiv.org/abs/2605.02178 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haixin Wang, Hejie Cui, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T^2PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T^2PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T^2PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T^2PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at: https://github.com/WillDreamer/T2PO.</p> + https://arxiv.org/abs/2605.02178 + Mon, 04 May 2026 00:00:00 +0000 + + + Generative Modeling with Orbit-Space Particle Flow Matching + https://arxiv.org/abs/2605.02222 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk, Bo Zhu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to permutation symmetries, so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; and (ii) particles live in physical space, so the flow terminal velocity has physical meaning and can encode geometric attributes, e.g., surface normals. OGPP instantiates three key components: (1) orbit-space canonicalization of the probability-path terminal endpoint, (2) particle index embeddings for role specialization, and (3) geometric probability paths with arc-length-aware terminal velocities that generate normals as a byproduct of the flow. We evaluate OGPP on minimal-surface benchmarks, where it reduces metric error by up to two orders of magnitude in a single inference step; on ShapeNet, where it matches the state of the art with 5x fewer steps and reaches airplane EMD comparable to DiT-3D with 26x fewer parameters and 5x fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D.</p> + https://arxiv.org/abs/2605.02222 + Mon, 04 May 2026 00:00:00 +0000 + + + SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors + https://arxiv.org/abs/2411.18966 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2411.18966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Cheng Lin, Shiqing Xin, Xin Li, Wenping Wang, Taku Komura</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Gaussian Splatting demonstrates impressive results in multi-view reconstruction based on Gaussian explicit representations. However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation. In this paper, we introduce a new method called SVGS (Spatially Varying Gaussian Splatting) that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear interpolation, movable kernels, and tiny neural networks as spatially varying functions. SVGS employs 2D Gaussian surfels as primitives, which significantly enhances novel-view synthesis while maintaining high-quality geometric reconstruction. This approach is particularly effective in practical applications, as scenes combining complex textures with relatively simple geometry occur frequently in real-world environments. Quantitative and qualitative experimental results demonstrate that all three functions outperform the baseline, with the best movable kernels achieving superior novel view synthesis performance on multiple datasets, highlighting the strong potential of spatially varying functions. Project page: https://ruixu.me/html/SuperGaussians/index.html</p> + https://arxiv.org/abs/2411.18966 + Mon, 04 May 2026 00:00:00 +0000 + + + AcademiClaw: When Students Set Challenges for AI Agents + https://arxiv.org/abs/2605.02661 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu, Jiabao Wu, Kaiwen Tao, Kun Wang, Lingyu Yang, Qiran Zhang, Xiuting Guo, Xuanyu Wang, Yang Wang, Yanjie Wang, Yi Yang, Zijian Hu, Ziyi Yang, Zonghan Zhou, Binghao Qiang, Borui Zhang, Chenning Li, Enchang Zhang, Feifan Chen, Feng Jian, Fengyin Sun, Hao Qiu, Hao Zheng, Haoran Zhu, Hongyu Liu, Jianbin Deng, Jiaxin Song, Jiaying Chi, Jiayou Shi, Jie Fang, Jinghui Zhong, Jingyu Zhou, Jinze Li, Junfeng Yi, Junyan Yu, Junzhi Xue, Ni Song, Pengyi Chen, Qi Chen, Quansheng Li, Rui Tao, Shenghai Gong, Shenhang Lu, Tianqi Shen, Tianxiang Zhu, Tiehan Kang, Tingyu Li, Wendi Wu, Xiao Shen, Xiao Zhou, Xiaotao Zhang, Xinrong Li, Xuankun Yang, Xun Zhang, Yan Li, Ye Lu, Yi Wang, Yibo Zhou, Yichi Zhang, Yihao Sun, Yijun Huang, Yixin Zhu, Yixuan Wu, Yuchen Sun, Yue Wu, Yuheng Sun, Yukun Li, Yutian Tu, Yuxuan Qin, Yuzhuo Wu, Zeyu Li, Zhengyu Lou, Zhenning Ran, Zizhu He, Pengfei Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We introduce AcademiClaw, a bilingual benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic workflows -- homework, research projects, competitions, and personal projects -- that they found current AI agents unable to solve effectively. Curated from 230 student-submitted candidates through rigorous expert review, the final task set spans 25+ professional domains, ranging from olympiad-level mathematics and linguistics problems to GPU-intensive reinforcement learning and full-stack system debugging, with 16 tasks requiring CUDA GPU execution. Each task executes in an isolated Docker sandbox and is scored on task completion by multi-dimensional rubrics combining six complementary techniques, with an independent five-category safety audit providing additional behavioral analysis. Experiments on six frontier models show that even the best achieves only a 55\% pass rate. Further analysis uncovers sharp capability boundaries across task domains, divergent behavioral strategies among models, and a disconnect between token consumption and output quality, providing fine-grained diagnostic signals beyond what aggregate metrics reveal. We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across the full breadth of real-world academic demands. All data and code are available at https://github.com/GAIR-NLP/AcademiClaw.</p> + https://arxiv.org/abs/2605.02661 + Mon, 04 May 2026 00:00:00 +0000 + + + Video Generation with Predictive Latents + https://arxiv.org/abs/2605.02134 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02134.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yian Zhao, Feng Wang, Qiushan Guo, Chang Liu, Xiangyang Ji, Jian Zhang, Jie Chen</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable reconstruction quality, continued optimization of reconstruction does not necessarily translate into improved generative performance. How to enhance the diffusability of video latents remains a critical and unresolved challenge. In this work, inspired by principles of predictive world modeling, we investigate the potential of predictive learning to improve the video generative modeling. To this end, we introduce a simple and effective predictive reconstruction objective that unifies predictive learning with video reconstruction. Specifically, we randomly discard future frames and encode only partial past observations, while training the decoder to reconstruct the observed frames and predict future ones simultaneously. This design encourages the latent space to encode temporally predictive structures and build a more coherent understanding of video dynamics, thereby improving generation quality. Our model, termed Predictive Video VAE (PV-VAE), achieves superior performance on video generation, with 52% faster convergence and a 34.42 FVD improvement over the Wan2.2 VAE on UCF101. Furthermore, comprehensive analyses demonstrate that PV-VAE not only exhibits favorable scalability, with generative performance improving alongside VAE training, but also yields consistent gains in downstream video understanding, underscoring a latent space that effectively captures temporal coherence and motion priors.</p> + https://arxiv.org/abs/2605.02134 + Mon, 04 May 2026 00:00:00 +0000 + + + HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness + https://arxiv.org/abs/2605.02396 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianing Wang, Linsen Guo, Zhengyu Chen, Qi Guo, Hongyu Zang, Wenjie Shi, Haoxiang Ma, Xiangyu Xi, Xiaoyu Li, Wei Wang, Xunliang Cai</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.</p> + https://arxiv.org/abs/2605.02396 + Mon, 04 May 2026 00:00:00 +0000 + + + ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration + https://arxiv.org/abs/2605.03042 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruofeng Yang, Yongcan Li, Shuai Li</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For long-horizon research workflows, the central failure mode is not a visible breakdown but a plausible unsupported success: a long-running agent can produce claims whose evidential support is incomplete, misreported, or silently inherited from the executor's framing. Therefore, we present ARIS as a research harness that coordinates machine-learning research workflows through cross-model adversarial collaboration as a default configuration: an executor model drives forward progress while a reviewer from a different model family is recommended to critique intermediate artifacts and request revisions. ARIS has three architectural layers. The execution layer provides more than 65 reusable Markdown-defined skills, model integrations via MCP, a persistent research wiki for iterative reuse of prior findings, and deterministic figure generation. The orchestration layer coordinates five end-to-end workflows with adjustable effort settings and configurable routing to reviewer models. The assurance layer includes a three-stage process for checking whether experimental claims are supported by evidence: integrity verification, result-to-claim mapping, and claim auditing that cross-checks manuscript statements against the claim ledger and raw evidence, as well as a five-pass scientific-editing pipeline, mathematical-proof checks, and visual inspection of the rendered PDF. A prototype self-improvement loop records research traces and proposes harness improvements that are adopted only after reviewer approval.</p> + https://arxiv.org/abs/2605.03042 + Mon, 04 May 2026 00:00:00 +0000 + + + MolmoAct2: Action Reasoning Models for Real-world Deployment + https://arxiv.org/abs/2605.02881 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoquan Fang, Jiafei Duan, Donovan Clay, Sam Wang, Shuo Liu, Weikai Huang, Xiang Fan, Wei-Chuan Tsai, Shirui Chen, Yi Ru Wang, Shanli Xing, Jaemin Cho, Jae Sung Park, Ainaz Eftekhar, Peter Sushko, Karen Farley, Angad Wadhwa, Cole Harrison, Winson Han, Ying-Chun Lee, Eli VanderBilt, Rose Hendrix, Suveen Ellawela, Lucas Ngoo, Joyce Chai, Zhongzheng Ren, Ali Farhadi, Dieter Fox, Ranjay Krishna</p><p><b>Upvotes:</b> 268</p><p><b>Summary:</b> Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor along five axes. We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. We release three new datasets spanning low-to-medium cost platforms, including MolmoAct2-BimanualYAM, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date, together with quality-filtered Franka (DROID) and SO100/101 subsets. We provide OpenFAST, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. We redesign the architecture to graft a flow-matching continuous-action expert onto a discrete-token VLM via per-layer KV-cache conditioning. Finally, we propose MolmoThink, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including Pi-05, while MolmoER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Project page: https://allenai.org/blog/molmoact2</p> + https://arxiv.org/abs/2605.02881 + Mon, 04 May 2026 00:00:00 +0000 + + + The Scaling Properties of Implicit Deductive Reasoning in Transformers + https://arxiv.org/abs/2605.04330 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enrico Vompa, Tanel Tammet</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelating provability from spurious features and enforcing algorithmic alignment, we find that in sufficiently deep models with a bidirectional prefix mask, implicit reasoning approaches explicit CoT performance across graph topologies and problem widths, though CoT remains necessary for depth extrapolation.</p> + https://arxiv.org/abs/2605.04330 + Tue, 05 May 2026 00:00:00 +0000 + + + A Benchmark for Interactive World Models with a Unified Action Generation Framework + https://arxiv.org/abs/2605.03941 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianjie Fang, Yingshan Lei, Qin Wan, Ziyou Wang, Yuchao Huang, Yongyan Xu, Baining Zhao, Weichen Zhang, Chen Gao, Xinlei Chen, Yong Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.</p> + https://arxiv.org/abs/2605.03941 + Tue, 05 May 2026 00:00:00 +0000 + + + APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music + https://arxiv.org/abs/2605.03395 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaavid Aktar Husain, Dorien Herremans</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems. However, the explosive rise of AI-generated music platforms has created an entirely new and largely unexplored landscape, where a surge of songs is produced and consumed daily without the traditional markers of artist reputation or label backing. Key, yet unexplored in this pursuit is aesthetic quality. We propose APEX, the first large-scale multi-task learning framework for AI-generated music, trained on over 211k songs (10k hours of audio) from Suno and Udio, that jointly predicts engagement-based popularity signals - streams and likes scores - alongside five perceptual aesthetic quality dimensions from frozen audio embeddings extracted from MERT, a self-supervised music understanding model. Aesthetic quality and popularity capture complementary aspects of music that together prove valuable: in an out-of-distribution evaluation on the Music Arena dataset, comprising pairwise human preference battles across eleven generative music systems unseen during training, including aesthetic features consistently improves preference prediction, demonstrating strong generalisation of the learned representations across generative architectures.</p> + https://arxiv.org/abs/2605.03395 + Tue, 05 May 2026 00:00:00 +0000 + + + Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback + https://arxiv.org/abs/2605.03848 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Edoardo Bianchi, Antonio Liotta</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identification. This task is challenging because proficiency is encoded in subtle differences in timing, balance, body mechanics, and execution, often distributed across multiple views and short temporal events. We discuss three recent contributions to multi-view proficiency estimation on Ego-Exo4D. SkillFormer introduces a parameter-efficient discriminative architecture for selective multi-view fusion; PATS improves temporal sampling by preserving locally dense excerpts of fundamental movements; and ProfVLM reformulates proficiency estimation as conditional language generation, producing both a proficiency label and expert-style feedback through a gated cross-view projector and a compact language backbone. Together, these methods achieve state-of-the-art accuracy on Ego-Exo4D with up to 20x fewer trainable parameters and up to 3x fewer training epochs than video-transformer baselines, while moving from closed-set classification toward interpretable feedback generation. These results highlight a shift toward efficient, multi-view systems that combine selective fusion, proficiency-aware sampling, and actionable generative feedback.</p> + https://arxiv.org/abs/2605.03848 + Tue, 05 May 2026 00:00:00 +0000 + + + Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies + https://arxiv.org/abs/2605.03596 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirui Tang, Xuanhe Zhou, Yumou Liu, Linchun Li, Weizheng Wang, Hongzhang Huang, Jun Zhou, Jiachen Song, Shaoli Yu, Jinqi Wang, Zihang Zhou, Hongyi Zhou, Yuting Lv, Jinyang Li, Jiashuo Liu, Ruoyu Chen, Chunwei Liu, GuoLiang Li, Jihua Kang, Fan Wu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning invOlving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches only 68.7%, substantially below the human result of 80.7%, and the average performance across agents is only 47.4%.</p> + https://arxiv.org/abs/2605.03596 + Tue, 05 May 2026 00:00:00 +0000 + + + PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination + https://arxiv.org/abs/2605.03571 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Wang, Xinyi Chen, Longze Chen, Hongbo Wang, Hamid Alinejad-Rokny, Yuan Lin, Min Yang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks predominantly view patent examination as discriminative classification or static extraction, failing to capture its inherently interactive and iterative nature, similar to the peer review and rebuttal process in academic publishing. In this paper, we introduce PatRe, the first benchmark that models the full patent examination lifecycle, including Office Action generation and applicant rebuttal. PatRe comprises 480 real-world cases and supports both oracle and retrieval-simulated evaluation settings. Our benchmark reframes patent examination as a dynamic, multi-turn process of justification and response. Extensive experiments across various LLMs reveal critical insights into model performance, including differences between proprietary and open-source models, as well as task asymmetries between examiner analysis and applicant-side rebuttal. These findings highlight both the potential and current limitations of LLMs in modeling complex, real-world legal reasoning and technical novelty judgment in patent examination. We release our code and dataset to facilitate future research on patent examination modeling.</p> + https://arxiv.org/abs/2605.03571 + Tue, 05 May 2026 00:00:00 +0000 + + + SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment + https://arxiv.org/abs/2605.04012 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joseph Breda, Fadi Yousif, Beszel Hawkins, Marinela Cotoi, Miao Liu, Ray Luo, Po-Hsuan Cameron Chen, Mike Schaekermann, Samuel Schmidgall, Xin Liu, Girish Narayanswamy, Samuel Solomon, Maxwell A. Xu, Xiaoran Fan, Longfei Shangguan, Anran Wang, Bhavna Daryani, Buddy Herkenham, Cara Tan, Mark Malhotra, Shwetak Patel, John B. Hernandez, Quang Duong, Yun Liu, Zach Wasson, Dimitrios Antos, Bob Lou, Matthew Thompson, Jonathan Richina, Anupam Pathak, Nichole Young-Lin, Jake Sunshine, Daniel McDuff</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Language models excel at diagnostic assessments on currated medical case-studies and vignettes, performing on par with, or better than, clinical professionals. However, existing studies focus on complex scenarios with rich context making it difficult to draw conclusions about how these systems perform for patients reporting symptoms in everyday life. We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and differential diagnosis (DDx), via the Fitbit app in a study that randomized participants (N=13,917) to interact with five AI agents. This corpus captures diverse communication and a realistic distribution of illnesses from a real world population. A subset of 1,228 participants reported a clinician-provided diagnosis, and 517 of these were further evaluated by a panel of clinicians during over 250 hours of annotation. SymptomAI DDx were significantly more accurate (OR = 2.47, p < 0.001) than those from independent clinicians given the same dialogue in a blinded randomized comparison. Moreover, agentic strategies which conduct a dedicated symptom interview that elicit additional symptom information before providing a diagnosis, perform substantially better than baseline, user-guided conversations (p < 0.001). An auxiliary analysis on 1,509 conversations from a general US population panel validated that these results generalize beyond wearable device users. We used SymptomAI diagnoses as labels for all 13,917 participants to analyze over 500,000 days of wearable metrics across nearly 400 unique conditions. We identified strong associations between acute infections and physiological shifts (e.g., OR > 7 for influenza). While limited by self-reported ground truth, these results demonstrate the benefits of a dedicated and complete symptom interview compared to a user-guided symptom discussion, which is the default of most consumer LLMs.</p> + https://arxiv.org/abs/2605.04012 + Tue, 05 May 2026 00:00:00 +0000 + + + Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation + https://arxiv.org/abs/2605.04128 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Song, Wenbo Li, Guoqing Ma, Wei Tang, Bo Wang, Yuan Zhang, Yijun Yang, Yicheng Xiao, Jianhui Liu, Yanbing Zhang, Guohui Zhang, Wenhu Zhang, Hang Xu, Nan Jiang, Xin Han, Haoze Sun, Maoquan Zhang, Haoyang Huang, Nan Duan</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.</p> + https://arxiv.org/abs/2605.04128 + Tue, 05 May 2026 00:00:00 +0000 + + + Audio-Visual Intelligence in Large Foundation Models + https://arxiv.org/abs/2605.04045 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> You Qin, Kai Liu, Shengqiong Wu, Kai Wang, Shijian Deng, Yapeng Tian, Junbin Xiao, Yazhou Xing, Yinghao Ma, Bobo Li, Roger Zimmermann, Lei Cui, Furu Wei, Jiebo Luo, Hao Fei</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the multimodal real world. In the era of large foundation models, joint modeling of audio and vision has become increasingly crucial, i.e., not only for understanding but also for controllable generation and reasoning across dynamic, temporally grounded signals. Recent advances, such as Meta MovieGen and Google Veo-3, highlight the growing industrial and academic focus on unified audio-vision architectures that learn from massive multimodal data. However, despite rapid progress, the literature remains fragmented, spanning diverse tasks, inconsistent taxonomies, and heterogeneous evaluation practices that impede systematic comparison and knowledge integration. This survey provides the first comprehensive review of AVI through the lens of large foundation models. We establish a unified taxonomy covering the broad landscape of AVI tasks, ranging from understanding (e.g., speech recognition, sound localization) to generation (e.g., audio-driven video synthesis, video-to-audio) and interaction (e.g., dialogue, embodied, or agentic interfaces). We synthesize methodological foundations, including modality tokenization, cross-modal fusion, autoregressive and diffusion-based generation, large-scale pretraining, instruction alignment, and preference optimization. Furthermore, we curate representative datasets, benchmarks, and evaluation metrics, offering a structured comparison across task families and identifying open challenges in synchronization, spatial reasoning, controllability, and safety. By consolidating this rapidly expanding field into a coherent framework, this survey aims to serve as a foundational reference for future research on large-scale AVI.</p> + https://arxiv.org/abs/2605.04045 + Tue, 05 May 2026 00:00:00 +0000 + + + Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems + https://arxiv.org/abs/2605.04018 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04018.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yilun Zhao, Jinbiao Wei, Tingyu Song, Siyue Zhang, Chen Zhao, Arman Cohan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide complementary evidence across iterative search and synthesis. However, existing work remains limited on both evaluation and training: benchmarks such as BRIGHT provide narrow gold sets and evaluate retrievers in isolation, while synthetic training corpora often optimize single-passage relevance rather than evidence portfolio construction. We introduce BRIGHT-Pro, an expert-annotated benchmark that expands each query with multi-aspect gold evidence and evaluates retrievers under both static and agentic search protocols. We further construct RTriever-Synth, an aspect-decomposed synthetic corpus that generates complementary positives and positive-conditioned hard negatives, and use it to LoRA fine-tune RTriever-4B from Qwen3-Embedding-4B. Experiments across lexical, general-purpose, and reasoning-intensive retrievers show that aspect-aware and agentic evaluation expose behaviors hidden by standard metrics, while RTriever-4B substantially improves over its base model.</p> + https://arxiv.org/abs/2605.04018 + Tue, 05 May 2026 00:00:00 +0000 + + + OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories + https://arxiv.org/abs/2605.04036 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04036.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuwen Du, Rui Ye, Shuo Tang, Keduan Huang, Xinyu Zhu, Yuzhu Cai, Siheng Chen</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continual pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). In this report, we show that when fueled with informative and high-difficulty trajectories, a simple SFT approach could be surprisingly powerful for training frontier search agents. By introducing three simple data synthesis modifications: scaling knowledge graph size for richer exploration, expanding the tool set size for broader functionality, and strict low-step filtering, we establish a stronger baseline. Trained on merely 10.6k data points, our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench, surpassing even Tongyi DeepResearch trained with heavy CPT+SFT+RL pipeline, which achieves 43.4%, 46.7%, 32.9%, and 75.0%, respectively. Notably, OpenSeeker-v2 represents the first state-of-the-art search agent within its model scale and paradigm to be developed by a purely academic team using only SFT. We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community.</p> + https://arxiv.org/abs/2605.04036 + Tue, 05 May 2026 00:00:00 +0000 + + + RLDX-1 Technical Report + https://arxiv.org/abs/2605.03269 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Huiwon Jang, Myungkyu Koo, Suhyeok Jang, Taeyoung Kim, Beomjun Kim, Byungjun Yoon, Changsung Jang, Daewon Choi, Dongsu Han, Donguk Lee, Heeseung Kwon, Hojin Jeon, Jaehyun Kang, Jaekyoung Bae, Jihyuk Lee, Jimin Lee, John Won, Joonwoo Ahn, Junhyeong Park, Junyoung Sung, Kyungmin Lee, Minseong Han, Minsung Yoon, Sejune Joo, Seonil Son, Seungcheol Park, Seunggeun Cho, Seungjun Moon, Seungku Kim, Yonghoon Dong, Yongjin Cho, Youngchan Kim, Chang Hwan Kim, Dohyeon Kim, Hazel Lee, Heecheol Kim, Hensen Ahn, Hyungkyu Ryu, Hyunsoo Choi, Hyunsoo Shin, Jaeheon Jung, Jaewoo Kim, Jinwook Kim, Joochul Chang, Joonsoo Kim, Junghun Park, Jungwoo Park, Junho Cho, Junhyeok Park, Junwon Lee, Kangwook Lee, Kwanghoon Kim, Kyoungwhan Choe, Manoj Bhadu, Nayoung Oh, Sangjun Kim, Sangwoo Kim, Seunghoon Shim, Seunghyun Kim, Seungjun Lee, Seungyup Ka, Sungryol Yang, Wook Jung, Yashu Shukla, Yeonjae Lee, Yeonwoo Bae, Jinwoo Shin</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene understanding and language-conditioned generalization) inherited from pre-trained Vision-Language Models, they still struggle with complex real-world tasks requiring broader functional capabilities (e.g. motion awareness, memory-aware decision making, and physical sensing). To address this, we introduce RLDX-1, a general-purpose robotic policy for dexterous manipulation built on the Multi-Stream Action Transformer (MSAT), an architecture that unifies these capabilities by integrating heterogeneous modalities through modality-specific streams with cross-modal joint self-attention. RLDX-1 further combines this architecture with system-level design choices, including synthesizing training data for rare manipulation scenarios, learning procedures specialized for human-like manipulation, and inference optimizations for real-time deployment. Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier VLAs (e.g. π_{0.5} and GR00T N1.6) across both simulation benchmarks and real-world tasks that require broad functional capabilities beyond general versatility. In particular, RLDX-1 shows superiority in ALLEX humanoid tasks by achieving success rates of 86.8% while π_{0.5} and GR00T N1.6 achieve around 40%, highlighting the ability of RLDX-1 to control a high-DoF humanoid robot under diverse functional demands. Together, these results position RLDX-1 as a promising step toward reliable VLAs for complex, contact-rich, and dynamic real-world dexterous manipulation.</p> + https://arxiv.org/abs/2605.03269 + Tue, 05 May 2026 00:00:00 +0000 + + + Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation + https://arxiv.org/abs/2605.03849 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.03849.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Wu, Mengqi Huang, Shaojin Wu, Weinan Jia, Yuxin Wang, Zhendong Mao, Yongdong Zhang</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student to match the teacher's output indiscriminately, treating every rollout, frame, and pixel as equally reliable supervision. We argue that this caps distilled quality, since it overlooks two complementary axes of variance in DMD supervision: Inter-Reliability across student rollouts whose supervision varies in reliability, and Intra-Perplexity across spatial regions and temporal frames that contribute unequally to where quality can still be improved. The objective thus conflates two questions under a uniform weight: whether to learn from each rollout, and where to concentrate optimization within it. To address this, we propose Stream-R1, a Reliability-Perplexity Aware Reward Distillation framework that adaptively reweights the distillation objective at both rollout and spatiotemporal-element levels through a single shared reward-guided mechanism. At the Inter-Reliability level, Stream-R1 rescales each rollout's loss by an exponential of a pretrained video reward score, so that rollouts with reliable supervision dominate optimization. At the Intra-Perplexity level, it back-propagates the same reward model to extract per-pixel gradient saliency, which is factored into spatial and temporal weights that concentrate optimization pressure on regions and frames where refinement yields the largest expected gain. An adaptive balancing mechanism prevents any single quality axis from dominating across visual quality, motion quality, and text alignment. Stream-R1 attains consistent improvements on all three dimensions over distillation baselines on standard streaming video generation benchmarks, without architectural modification or additional inference cost.</p> + https://arxiv.org/abs/2605.03849 + Tue, 05 May 2026 00:00:00 +0000 + + + A Foundation Model for Zero-Shot Logical Rule Induction + https://arxiv.org/abs/2605.04916 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04916.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yin Jun Phua</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer.</p> + https://arxiv.org/abs/2605.04916 + Wed, 06 May 2026 00:00:00 +0000 + + + KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels + https://arxiv.org/abs/2605.04956 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04956.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Wang, Jintao Zhang, Kai Jiang, Haoxu Wang, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBench-X, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from 1.58times to 1.44times; newly rescued kernels consistently underperform persistently correct ones (1.16times vs 1.58times speedup in round~0to1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches 21.4times. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX</p> + https://arxiv.org/abs/2605.04956 + Wed, 06 May 2026 00:00:00 +0000 + + + RemoteZero: Geospatial Reasoning with Zero Human Annotations + https://arxiv.org/abs/2605.04451 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04451.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Yao, Fan Liu, Shengxiang Xu, Chuanyi Zhang, Rui Min, Shimin Di, Yuhui Zheng</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Geospatial reasoning requires models to resolve complex spatial semantics and user intent into precise target locations for Earth observation. Recent progress has liberated the reasoning path from manual curation, allowing models to generate their own inference chains. Yet a final dependency remains: they are still supervised by human-annotated ground-truth coordinates. This leaves the reasoning process autonomous, but not its spatial endpoint, and prevents true self-evolution on abundant unlabeled remote sensing data. To break this bottleneck, we introduce RemoteZero, a box-supervision-free framework for geospatial reasoning. RemoteZero is motivated by a simple asymmetry: an MLLM is typically better at verifying whether a region satisfies a query than at directly generating precise coordinates. Leveraging this stronger discriminative ability, RemoteZero replaces geometric supervision with intrinsic semantic verification and enables GRPO training without box annotations. The resulting framework further supports iterative self-evolution, allowing the model to improve from unlabeled remote sensing imagery through its own verification signal. Experiments show that RemoteZero achieves competitive performance against strong supervised methods, demonstrating the potential of self-verifying training for geospatial reasoning localization.</p> + https://arxiv.org/abs/2605.04451 + Wed, 06 May 2026 00:00:00 +0000 + + + TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding + https://arxiv.org/abs/2605.04962 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minjie Qiang, Mingming Zhang, Xiaoyi Bao, Xing Fu, Yu Cheng, Weiqiang Wang, Zhongqing Wang, Ningtao Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack retrieval-compatible vector outputs, whereas text embedding models often fail to capture tabular structure and numerical semantics. To bridge this gap, we first introduce the Tabular Embedding Benchmark (TabBench), a comprehensive suite designed to evaluate the tabular understanding capability of embedding models. We then propose TabEmbed, the first generalist embedding model that unifies tabular classification and retrieval within a shared embedding space. By reformulating diverse tabular tasks as semantic matching problems, TabEmbed leverages large-scale contrastive learning with positive-aware hard negative mining to discern fine-grained structural and numerical nuances. Experimental results on TabBench demonstrate that TabEmbed significantly outperforms state-of-the-art text embedding models, establishing a new baseline for universal tabular representation learning. Code and datasets are publicly available at https://github.com/qiangminjie27/TabEmbed and https://huggingface.co/datasets/qiangminjie27/TabBench.</p> + https://arxiv.org/abs/2605.04962 + Wed, 06 May 2026 00:00:00 +0000 + + + ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving + https://arxiv.org/abs/2605.04647 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huimin Wang, Yue Wang, Bihao Cui, Pengxiang Li, Ben Lu, Mingqian Wang, Tong Wang, Chuan Tang, Teng Zhang, Kun Zhan</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete trajectory tokens and generates them through parallel masked decoding. This discrete token space enables in-place trajectory revision: AutoEdit rewrites selected tokens using the same model, without requiring an auxiliary refinement network. To train this capability, we use a two-stage procedure. First, we construct structure-aware perturbations of expert trajectories along longitudinal progress and lateral heading directions and supervise the model to recover the original expert trajectory. We then fine-tune the full decision--draft--reflect rollout with reinforcement learning (RL), assigning terminal driving reward to the final post-edit trajectory and propagating policy-gradient credit through full-rollout transitions. Full-rollout RL proves crucial for coupling drafting and editing: under supervised training alone, inference-time AutoEdit improves PDMS by at most 0.3, whereas RL increases its gain to 1.9. We also co-design an efficient reflective decoding stack for the decision--draft--reflect pipeline, combining shared-prefix KV reuse, Alternating Step Decode, and fused on-device unmasking. On NAVSIM, ReflectDrive-2 achieves 91.0 PDMS with camera-only input and 94.8 PDMS in a best-of-6 oracle setting, while running at 31.8 ms average latency on NVIDIA Thor.</p> + https://arxiv.org/abs/2605.04647 + Wed, 06 May 2026 00:00:00 +0000 + + + StableI2I: Spotting Unintended Changes in Image-to-Image Transition + https://arxiv.org/abs/2605.04453 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayang Li, Shuo Cao, Xiaohui Li, Zhizhen Zhang, Kaiwen Zhu, Yule Duan, Yu Qiao, Jian Zhang, Yihao Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems.</p> + https://arxiv.org/abs/2605.04453 + Wed, 06 May 2026 00:00:00 +0000 + + + Lightning Unified Video Editing via In-Context Sparse Attention + https://arxiv.org/abs/2605.04569 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shitong Shao, Zikai Zhou, Haopeng Li, Yingwei Song, Wenliang Zhong, Lichen Bai, Zeke Xie</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \texttt{LIVEditor} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor achieves a sim60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.</p> + https://arxiv.org/abs/2605.04569 + Wed, 06 May 2026 00:00:00 +0000 + + + CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing + https://arxiv.org/abs/2605.02910 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Qian, Hyeonjeong Ha, Jiayu Liu, Jeonghwan Kim, Jiateng Liu, Bingxuan Li, Aditi Tiwari, Dwip Dalal, Zhenhailong Wang, Xiusi Chen, Mahdi Namazifar, Yunzhu Li, Heng Ji</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of creative tool use, where a model repurposes available objects by reasoning about their affordances and attributes rather than relying on canonical usage. As a first step, we introduce CreativityBench, a benchmark for evaluating affordance-based creativity in LLMs. To this end, we build a large-scale affordance knowledge base (KB) with 4K entities and 150K+ affordance annotations, explicitly linking objects, parts, attributes, and actionable uses. Building on this KB, we generate 14K grounded tasks that require identifying non-obvious yet physically plausible solutions under constraints. Evaluations across 10 state-of-the-art LLMs, including closed and open-source models, show that models can often select a plausible object, but fail to identify the correct parts, their affordances, and the underlying physical mechanism needed to solve the task, leading to a significant drop in performance. Furthermore, improvements from model scaling quickly saturate, strong general reasoning does not reliably translate to creative affordance discovery, and common inference-time strategies such as Chain-of-Thought yield limited gains. These results suggest that creative tool use remains a major challenge for current models, and that CreativityBench provides a useful testbed for studying this missing dimension of intelligence, with potential implications for planning and reasoning modules in future agents.</p> + https://arxiv.org/abs/2605.02910 + Wed, 06 May 2026 00:00:00 +0000 + + + D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models + https://arxiv.org/abs/2605.05204 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dengyang Jiang, Xin Jin, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Ruoyi Du, Xiangpeng Yang, Qilong Wu, Zhen Li, Peng Gao, Harry Yang, Steven Hoi</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for directly continuous supervised fine-tuning. For example, applying the commonly used fine-tuning technique would compromises their inherent few-step inference capability. To address this, we propose D-OPSD, a novel training paradigm for step-distilled diffusion models that enables on-policy learning during supervised fine-tuning. We first find that the modern diffusion model where the LLM/VLM serves as the encoder can inherit its encoder's in-context capabilities. This enables us to make the training as an on-policy self-distillation process. Specifically, during training, we make the model acts as both the teacher and the student with different contexts, where the student is conditioned only on the text feature, while the teacher is conditioned on the multimodal feature of both the text prompt and the target image. Training minimizes the two predicted distributions over the student's own roll-outs. By optimized on the model's own trajectory and under it's own supervision, D-OPSD enables the model to learn new concept, style, etc. without sacrificing the original few-step capacity.</p> + https://arxiv.org/abs/2605.05204 + Wed, 06 May 2026 00:00:00 +0000 + + + PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World + https://arxiv.org/abs/2605.05163 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhan Yang, Chunshi Wang, Junliang Ye, Yang Li, Zanxin Chen, Zehuan Huang, Yao Mu, Zhuo Chen, Chunchao Guo, Xihui Liu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a "physical architect" to plan a "Hierarchical Physical Blueprint" defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.</p> + https://arxiv.org/abs/2605.05163 + Wed, 06 May 2026 00:00:00 +0000 + + + RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation + https://arxiv.org/abs/2605.04523 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ivan Bondarenko, Roman Derunets, Oleg Sedukhin, Mikhail Komarov, Ivan Chernov, Mikhail Kulakov</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval</p> + https://arxiv.org/abs/2605.04523 + Wed, 06 May 2026 00:00:00 +0000 + + + OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents + https://arxiv.org/abs/2605.05185 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang, Dasen Dai, Quanxin Shou, Yunlong Lin, Xiangyu Yue, Shenghua Gao, Tianyu Pang</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and SearchVL-RL-8k for RL. Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction, enabling agents to combine active perception with external knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles cascading tool failures by masking post-failure tokens while preserving useful pre-failure reasoning through one-sided advantage clamping. Built on this recipe, OpenSearch-VL delivers substantial performance gains, with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research on multimodal deep search agents.</p> + https://arxiv.org/abs/2605.05185 + Wed, 06 May 2026 00:00:00 +0000 + + + Stream-T1: Test-Time Scaling for Streaming Video Generation + https://arxiv.org/abs/2605.04461 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.04461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijing Tu, Shaojin Wu, Mengqi Huang, Wenchuan Wang, Yuxin Wang, Chunxiao Liu, Zhendong Mao</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration costs and lack temporal guidance. To address these structural bottlenecks, we propose shifting the focus to streaming video generation. We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced Stream-T1, a pioneering comprehensive TTS framework exclusively tailored for streaming video generation. Specifically, Stream-T1 is composed of three units: (1) Stream -Scaled Noise Propagation, which actively refines the initial latent noise of the generating chunk using historically proven, high-quality previous chunk noise, effectively establishes temporal dependency and utilizing the historical Gaussian prior to guide the current generation; (2) Stream -Scaled Reward Pruning, which comprehensively evaluates generated candidates to strike an optimal balance between local spatial aesthetics and global temporal coherence by integrating immediate short-term assessments with sliding-window-based long-term evaluations; (3) Stream-Scaled Memory Sinking, which dynamically routes the context evicted from KV-cache into distinct updating pathways guided by the reward feedback, ensuring that previously generated visual information effectively anchors and guides the subsequent video stream. Evaluated on both 5s and 30s comprehensive video benchmarks, Stream-T1 demonstrates profound superiority, significantly improving temporal consistency, motion smoothness, and frame-level visual quality.</p> + https://arxiv.org/abs/2605.04461 + Wed, 06 May 2026 00:00:00 +0000 + + + PianoCoRe: Combined and Refined Piano MIDI Dataset + https://arxiv.org/abs/2605.06627 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ilya Borovik</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Symbolic music datasets with matched scores and performances are essential for many music information retrieval (MIR) tasks. Yet, existing resources often cover a narrow range of composers, lack performance variety, omit note-level alignments, or use inconsistent naming formats. This work presents PianoCoRe, a large-scale piano MIDI dataset that unifies and refines major open-source piano corpora. The dataset contains 250,046 performances of 5,625 pieces written by 483 composers, totaling 21,763 h of performed music. PianoCoRe is released in tiered subsets to support different applications: from large-scale analysis and pre-training (PianoCoRe-C and deduplicated PianoCoRe-B) to expressive performance modeling with note-level score alignment (PianoCoRe-A/A*). The note-aligned subset, PianoCoRe-A, provides the largest open-source collection of 157,207 performances aligned to 1,591 scores to date. In addition to the dataset, the contributions are: (1) a MIDI quality classifier for detecting corrupted and score-like transcriptions and (2) RAScoP, an alignment refinement pipeline that cleans temporal alignment errors and interpolates missing notes. The analysis shows that the refinement reduces temporal noise and eliminates tempo outliers. Moreover, an expressive performance rendering model trained on PianoCoRe demonstrates improved robustness to unseen pieces compared to models trained on raw or smaller datasets. PianoCoRe provides a ready-to-use foundation for the next generation of expressive piano performance research.</p> + https://arxiv.org/abs/2605.06627 + Thu, 07 May 2026 00:00:00 +0000 + + + XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity + https://arxiv.org/abs/2605.05662 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dasol Choi, Eugenia Kim, Jaewon Noh, Sang Seo, Eunmi Kim, Myunggyo Oh, Yunjin Park, Brigitta Jesica Kartono, Josef Pichlmeier, Helena Berndt, Sai Krishna Mendu, Glenn Johannes Tungka, Özlem Gökçe, Suresh Gehlot, Katherine Pratt, Amanda Minnich, Haon Park</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench. a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. To distinguish principled refusal from comprehension failure, we evaluate Attack Success Rate (ASR) alongside two complementary metrics we introduce: Neutral-Safe Rate (NSR) and Cultural Sensitivity Rate (CSR). Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, jailbreak robustness and cultural awareness do not show a coupled relationship among frontier models, so a composite safety score obscures per-axis variation. Second, local models exhibit a near-linear ASR-NSR trade-off (r = -0.81), indicating that their apparent safety reflects generation failure rather than genuine alignment. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.</p> + https://arxiv.org/abs/2605.05662 + Thu, 07 May 2026 00:00:00 +0000 + + + The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models + https://arxiv.org/abs/2605.06196 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chonghan Qin, Xiachong Feng, Ziyun Song, Xiaocheng Feng, Jing Xiong, Lingpeng Kong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large language models (LLMs) are routinely prompted to take on social roles ranging from individuals to institutions, yet it remains unclear whether their internal representations encode the granularity of such roles, from micro-level individual experience to macro-level organizational, institutional, or national reasoning. We show that they do. We define a contrast-based Granularity Axis as the difference between mean macro- and micro-role hidden states. In Qwen3-8B, this axis aligns with the principal axis (PC1) of the role representation space at cosine 0.972 and accounts for 52.6% of its variance, indicating that granularity is the dominant geometric axis organizing prompted social roles. We construct 75 social roles across five granularity levels and collect 91,200 role-conditioned responses over shared questions and prompt variants, then extract role-level hidden states and project them onto the axis. Role projections increase monotonically across all five levels, remain stable across layers, prompt variants, endpoint definitions, held-out splits, and score-filtered subsets, and transfer to Llama-3.1-8B-Instruct. The axis is also causally relevant: activation steering along it shifts response granularity in the predicted direction, with Llama moving from 2.00 to 3.17 on a five-point macro scale under positive steering on prompts that admit local responses. The two models differ in controllability, suggesting that steering depends on each model's default operating regime. Overall, our findings suggest that social role granularity is not merely a stylistic surface feature, but a structured, ordered, and causally manipulable latent direction in role-conditioned language model behavior.</p> + https://arxiv.org/abs/2605.06196 + Thu, 07 May 2026 00:00:00 +0000 + + + SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation + https://arxiv.org/abs/2605.06356 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> YaoYang Liu, Yuechen Zhang, Wenbo Li, Yufei Zhao, Rui Liu, Long Chen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions suffer from various weaknesses: 1) end-to-end models are often prohibitively expensive in memory and latency; 2) cascading low-resolution generation with a generic video super-resolution tends to hallucinate details and drift from input-specific local structures, since the super-resolution stage is not explicitly conditioned on the input image. To this end, we propose SwiftI2V, an efficient framework tailored for high-resolution I2V. Following the widely used two-stage design, it addresses the efficiency--fidelity dilemma by first generating a low-resolution motion reference to reduce token costs and ease the modeling burden, then performing a strongly image-conditioned 2K synthesis guided by the motion to recover input-faithful details with controlled overhead. Specifically, to make generation more scalable, SwiftI2V introduces Conditional Segment-wise Generation (CSG) to synthesize videos segment-by-segment with a bounded per-step token budget, and adopts bidirectional contextual interaction within each segment to improve cross-segment coherence and input fidelity. On VBench-I2V at 2K resolution, SwiftI2V achieves performance comparable to end-to-end baselines while reducing total GPU-time by 202x. Particularly, it enables practical 2K I2V generation on a single datacenter GPU (e.g., H800) or consumer GPU (e.g., RTX 4090).</p> + https://arxiv.org/abs/2605.06356 + Thu, 07 May 2026 00:00:00 +0000 + + + TIDE: Every Layer Knows the Token Beneath the Context + https://arxiv.org/abs/2605.06216 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ajay Jaiswal, Lauren Hannah, Han-Byul Kim, Duc Hoang, Mehrdad Farajtabar, Minsik Cho</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We revisit a universally accepted but under-examined design choice in every modern LLM: a token index is looked up once at the input embedding layer and then permanently discarded. This single-injection assumption induces two structural failures: (i) the Rare Token Problem, where a Zipf-type distribution of vocabulary causes rare-token embeddings are chronically under-trained due to receiving a fraction of the cumulative gradient signal compared to common tokens; and (ii) the Contextual Collapse Problem, where limited parameters models map distributionally similar tokens to indistinguishable hidden states. As an attempt to address both, we propose TIDE, which augments the standard transformer with EmbeddingMemory: an ensemble of K independent MemoryBlocks that map token indices to context-free semantic vectors, computed once and injected into every layer through a depth-conditioned softmax router with a learnable null bank. We theoretically and empirically establish the benefits of TIDE in addressing the issues associated with single-token identity injection as well as improve performance across multiple language modeling and downstream tasks.</p> + https://arxiv.org/abs/2605.06216 + Thu, 07 May 2026 00:00:00 +0000 + + + EMO: Pretraining Mixture of Experts for Emergent Modularity + https://arxiv.org/abs/2605.06663 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06663.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ryan Wang, Akshita Bhagia, Sewon Min</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset of experts per input, but in practice, restricting inference to a subset of experts for a given domain leads to severe performance degradation. This limits their practicality in memory-constrained settings, especially as models grow larger and sparser. We introduce EMO, an MoE designed for modularity-the independent use and composition of expert subsets-without requiring human-defined priors. Our key idea is to encourage tokens from similar domains to rely on similar experts. Since tokens within a document often share a domain, EMO restricts them to select experts from a shared pool, while allowing different documents to use different pools. This simple constraint enables coherent expert groupings to emerge during pretraining using document boundaries alone. We pretrain a 1B-active, 14B-total EMO on 1T tokens. As a full model, it matches standard MoE performance. Crucially, it enables selective expert use: retaining only 25% (12.5%) of experts incurs just a 1% (3%) absolute drop, whereas standard MoEs break under the same setting. We further find that expert subsets in EMO specialize at semantic levels (e.g., domains such as math or code), in contrast to the low-level syntactic specialization observed in standard MoEs. Altogether, our results demonstrate a path toward modular, memory-efficient deployment of large, sparse models and open new opportunities for composable architectures.</p> + https://arxiv.org/abs/2605.06663 + Thu, 07 May 2026 00:00:00 +0000 + + + UniPool: A Globally Shared Expert Pool for Mixture-of-Experts + https://arxiv.org/abs/2605.06665 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbin Huang, Han Shi, Chuanyang Zheng, Yimeng Wu, Guoxuan Chen, Xintong Yu, Yichun Yin, Hong Cheng</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes that every layer needs isolated expert capacity. However, recent analyses and our routing probe challenge this allocation rule: replacing a deeper layer's learned top-k router with uniform random routing drops downstream accuracy by only 1.0-1.6 points across multiple production MoE models. Motivated by this redundancy, we propose UniPool, an MoE architecture that treats expert capacity as a global architectural budget by replacing per-layer expert ownership with a single shared pool accessed by independent per-layer routers. To enable stable and balanced training under sharing, we introduce a pool-level auxiliary loss that balances expert utilization across the entire pool, and adopt NormRouter to provide sparse and scale-stable routing into the shared expert pool. Across five LLaMA-architecture model scales (182M, 469M, 650M, 830M, and 978M parameters) trained on 30B tokens from the Pile, UniPool consistently improves validation loss and perplexity over the matched vanilla MoE baselines. Across these scales, UniPool reduces validation loss by up to 0.0386 relative to vanilla MoE. Beyond raw loss improvement, our results identify pool size as an explicit depth-scaling hyperparameter: reduced-pool UniPool variants using only 41.6%-66.7% of the vanilla expert-parameter budget match or outperform layer-wise MoE at the tested scales. This shows that, under a shared-pool design, expert parameters need not grow linearly with depth; they can grow sublinearly while remaining more efficient and effective than vanilla MoE. Further analysis shows that UniPool's benefits compose with finer-grained expert decomposition.</p> + https://arxiv.org/abs/2605.06665 + Thu, 07 May 2026 00:00:00 +0000 + + + AI Co-Mathematician: Accelerating Mathematicians with Agentic AI + https://arxiv.org/abs/2605.06651 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Zheng, Ingrid von Glehn, Yori Zwols, Iuliya Beloshapka, Lars Buesing, Daniel M. Roy, Martin Wattenberg, Bogdan Georgiev, Tatiana Schmidt, Andrew Cowie, Fernanda Viegas, Dimitri Kanevsky, Vineet Kahlon, Hartmut Maennel, Sophia Alj, George Holland, Alex Davies, Pushmeet Kohli</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.</p> + https://arxiv.org/abs/2605.06651 + Thu, 07 May 2026 00:00:00 +0000 + + + Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key + https://arxiv.org/abs/2605.06638 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Wang, Zhaoyang Wang, Guangchen Lan, Xinpeng Wei, Sipeng Zhang, Guanwen Qiu, Abulhair Saparov</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with task difficulty has been hampered by the lack of controlled, scalable environments. We introduce ScaleLogic, a synthetic logical reasoning framework that offers independent control over two axes of difficulty: the depth of the required proof planning (i.e., the horizon) and the expressiveness of the underlying logic. Our proposed framework supports a wide range of logics: from simple implication-only logic ("if-then") towards more expressive first-order reasoning with conjunction ("and"), disjunction ("or"), negation ("not"), and universal quantification ("for all"). Using this framework, we show that the RL training compute T follows a power law with respect to reasoning depth D (T propto D^γ, R^{2} > 0.99), and that the scaling exponent γ increases monotonically with logical expressiveness, from 1.04 to 2.60. On downstream mathematics and general reasoning benchmarks, more expressive training settings yield both larger performance gains (up to +10.66 points) and more compute-efficient transfer compared to less expressive settings, demonstrating that what a model is trained on, not just how much it is trained, shapes downstream transfer. We further show that the power-law relationship holds across multiple RL methods, and curriculum-based training substantially improves scaling efficiency.</p> + https://arxiv.org/abs/2605.06638 + Thu, 07 May 2026 00:00:00 +0000 + + + A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping + https://arxiv.org/abs/2605.06200 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06200.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dingwei Chen, Zefang Zong, Zhipeng Ma, Leo Luo, Yang Li, Chengming Li, Peng Chen, Jie Jiang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of individual tool-calls within multi-turn interactions. Existing approaches to such process credit assignment either depend on separate external process reward models that introduce additional consumption, or tree-based structural rollout that merely redistributes the outcome signal while constraining trajectory diversity. A promising alternative leverages the per-turn change in the policy's predicted probability of the ground-truth, termed Information Gain (IG), as an intrinsic process signal without an external evaluator. However, prior work on leveraging IG signals within the RL training loop faces three systematic challenges: normalizing across turns that face heterogeneous positional contexts can distort the relative standing of individual turns, accumulating a variable number of terms causes advantage magnitudes to drift with trajectory depth, and a fixed clipping range governs policy updates identically for turns with vastly different IG signals. In this paper, we propose A^2TGPO (Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping), which retains IG as the intrinsic signal but re-designs how it is normalized, accumulated, and consumed: (i) turn-group normalization: normalizes IG within each (prompt, turn-index) group so that each turn is compared only against peers at the same interaction depth; (ii) variance-rescaled discounted accumulation: divides cumulative normalized IG by square root of accumulated terms to keep advantage magnitudes comparable across turn positions; and (iii) adaptive turn-level clipping: modulates each turn's clipping range based on its normalized IG, widening the update region for informative turns and narrowing it for uninformative ones.</p> + https://arxiv.org/abs/2605.06200 + Thu, 07 May 2026 00:00:00 +0000 + + + Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes + https://arxiv.org/abs/2605.05724 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjie Ning, Xiaochuan Li, Ji Zeng, Hao Kang, Chenyan Xiong</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal. The output is not a generated paper or a single model checkpoint, but an auditable trajectory of proposals, code diffs, experiments, scores, and failure labels. We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials. The central empirical finding is that lineage feedback lets agents turn evaluator outcomes, including crashes, budget overruns, size failures, and accuracy-gate misses, into later program-level recipe edits rather than one-shot suggestions. Across 1,197 headline-run trials plus 600 Parameter Golf control trials after one-time setup and launch, humans did not choose proposals, edit recipes, override scores, or repair failed trials during the search. In the three headline runs, the same submitted-trial loop reduces Parameter Golf validation bpb by 0.81%, raises NanoChat-D12 CORE by 38.7%, and reduces CIFAR-10 Airbench96 wallclock by 4.59%, with each task measured by its own external evaluator and legality checks. The trace includes a strict architecture-domain audit of 157 headline-run submissions and program rewrites such as a NanoChat attention-kernel path change. Within this scope the loop autonomously writes code, submits experiments, absorbs feedback, applies and combines known techniques inside each environment, and improves public starting recipes.</p> + https://arxiv.org/abs/2605.05724 + Thu, 07 May 2026 00:00:00 +0000 + + + StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction + https://arxiv.org/abs/2605.06642 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyuan Xue, Yifan Zhou, Zidong Wang, Shengji Tang, Philip Torr, Wanli Ouyang, Lei Bai, Zhenfei Yin</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance over strong baselines. StraTA reaches success rates of 93.1% on ALFWorld and 84.2% on WebShop. On SciWorld, StraTA attains a 63.5% overall score, outperforming frontier closed-source models.</p> + https://arxiv.org/abs/2605.06642 + Thu, 07 May 2026 00:00:00 +0000 + + + Continuous-Time Distribution Matching for Few-Step Diffusion Distillation + https://arxiv.org/abs/2605.06376 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Liu, Hao Yan, Mengting Chen, Taihang Hu, Zhengrong Yue, Zihao Pan, Jinsong Lan, Xiaoyong Zhu, Ming-Ming Cheng, Bo Zheng, Yaxing Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce self-consistency along the full PF-ODE trajectory to steer it toward the clean data manifold, vanilla DMD relies on sparse supervision at a few predefined discrete timesteps. This restricted discrete-time formulation and mode-seeking nature of the reverse KL divergence tends to exhibit visual artifacts and over-smoothed outputs, often necessitating complex auxiliary modules -- such as GANs or reward models -- to restore visual fidelity. In this work, we introduce Continuous-Time Distribution Matching (CDM), migrating the DMD framework from discrete anchoring to continuous optimization for the first time. CDM achieves this through two continuous-time designs. First, we replace the fixed discrete schedule with a dynamic continuous schedule of random length, so that distribution matching is enforced at arbitrary points along sampling trajectories rather than only at a few fixed anchors. Second, we propose a continuous-time alignment objective that performs active off-trajectory matching on latents extrapolated via the student's velocity field, improving generalization and preserving fine visual details. Extensive experiments on different architectures, including SD3-Medium and Longcat-Image, demonstrate that CDM provides highly competitive visual fidelity for few-step image generation without relying on complex auxiliary objectives. Code is available at https://github.com/byliutao/cdm.</p> + https://arxiv.org/abs/2605.06376 + Thu, 07 May 2026 00:00:00 +0000 + + + Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration + https://arxiv.org/abs/2605.05566 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05566.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Langlin Huang, Chengsong Huang, Jinyuan Li, Donghong Cai, Yuyi Yang, Jiaxin Huang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently suffers from the ``zero-advantage problem'': when all sampled rollouts for a query fail, the relative advantage collapses to zero. Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While simply increasing the sampling budget for these questions is a common remedy, the static sampling policy inherently constrains reasoning exploration, limiting the success rate. In this paper, we propose Lorem Perturbation for Exploration (LoPE), a simple yet effective training framework to break this exploration bottleneck. We posit that task-irrelevant prompt-space perturbations can shift the model's output distribution enough to unlock orthogonal reasoning pathways for hard questions. Specifically, LoPE prepends sequences stochastically assembled from Lorem Ipsum vocabulary (a pseudo-Latin placeholder text) to the prompts before resampling. Experiments across 1.7B, 4B, and 7B models demonstrate that LoPE significantly outperforms resampling with the original prompts. Further analysis reveals that other Latin-based random sequences with low perplexity are also effective perturbations. Our results establish LoPE as a strong baseline for broadening exploration in LLM reinforcement learning.</p> + https://arxiv.org/abs/2605.05566 + Thu, 07 May 2026 00:00:00 +0000 + + + SkillOS: Learning Skill Curation for Self-Evolving Agents + https://arxiv.org/abs/2605.06614 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existing approaches either rely on manual skill curation, prescribe heuristic skill operations, or train for short-horizon skill operations. However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents. SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience. To provide learning signals for curation, we design composite rewards and train on grouped task streams based on skill-relevant task dependencies, where earlier trajectories update the SkillRepo, and later related tasks evaluate these updates. Across multi-turn agentic tasks and single-turn reasoning tasks, SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency, with the learned skill curator generalizing across different executor backbones and task domains. Further analyses show that the learned curator produces more targeted skill use, while the skills in SkillRepo evolve into more richly structured Markdown files that encode higher-level meta-skills over time.</p> + https://arxiv.org/abs/2605.06614 + Thu, 07 May 2026 00:00:00 +0000 + + + MARBLE: Multi-Aspect Reward Balance for Diffusion RL + https://arxiv.org/abs/2605.06507 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Canyu Zhao, Hao Chen, Yunze Tong, Yu Qiao, Jiacheng Li, Chunhua Shen</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward R(x)=sum_k w_k R_k(x), or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training.</p> + https://arxiv.org/abs/2605.06507 + Thu, 07 May 2026 00:00:00 +0000 + + + When to Trust Imagination: Adaptive Action Execution for World Action Models + https://arxiv.org/abs/2605.06222 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Wang, Yue Zhang, Jiehong Lin, Kuncheng Luo, Jianan Wang, Zhongrui Wang, Xiaojuan Qi</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation by jointly predicting future visual observations and future actions. However, current WAMs typically execute a fixed number of predicted actions after each model inference, leaving the robot blind to whether the imagined future remains consistent with the actual physical rollout. In this work, we formulate adaptive WAM execution as a future-reality verification problem: the robot should execute longer when the WAM-predicted future remains reliable, and replan earlier when reality deviates from imagination. To this end, we propose Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that jointly reasons over predicted future actions, predicted visual dynamics, real observations, and language instructions to estimate whether the remaining action rollout can still be trusted. FFDC enables adaptive action chunk sizes as an emergent consequence of prediction-observation consistency, preserving the efficiency of long-horizon execution while restoring responsiveness in contact-rich or difficult phases. We further introduce Mixture-of-Horizon Training to improve long-horizon trajectory coverage for adaptive execution. Experiments on the RoboTwin benchmark and in the real world demonstrate that our method achieves a strong robustness-efficiency trade-off: on RoboTwin, it reduces WAM forward passes by 69.10% and execution time by 34.02%, while improving success rate by 2.54% over the short-chunk baseline; in real-world experiments, it improves success rate by 35%.</p> + https://arxiv.org/abs/2605.06222 + Thu, 07 May 2026 00:00:00 +0000 + + + MiA-Signature: Approximating Global Activation for Long-Context Understanding + https://arxiv.org/abs/2605.06416 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06416.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Li, Jiangnan Li, Mo Yu, Zheng Lin, Weiping Wang, Jie Zhou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.</p> + https://arxiv.org/abs/2605.06416 + Thu, 07 May 2026 00:00:00 +0000 + + + Continuous Latent Diffusion Language Model + https://arxiv.org/abs/2605.06548 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06548.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongcan Guo, Qinyu Zhao, Yian Zhao, Shen Nie, Rui Zhu, Qiushan Guo, Feng Wang, Tao Yang, Hengshuang Zhao, Guoqiang Wei, Yan Zeng</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation efficiency, scalable representation learning, and effective global semantic modeling. We propose Cola DLM, a hierarchical latent diffusion language model that frames text generation through hierarchical information decomposition. Cola DLM first learns a stable text-to-latent mapping with a Text VAE, then models a global semantic prior in continuous latent space with a block-causal DiT, and finally generates text through conditional decoding. From a unified Markov-path perspective, its diffusion process performs latent prior transport rather than token-level observation recovery, thereby separating global semantic organization from local textual realization. This design yields a more flexible non-autoregressive inductive bias, supports semantic compression and prior fitting in continuous space, and naturally extends to other continuous modalities. Through experiments spanning 4 research questions, 8 benchmarks, strictly matched ~2B-parameter autoregressive and LLaDA baselines, and scaling curves up to about 2000 EFLOPs, we identify an effective overall configuration of Cola DLM and verify its strong scaling behavior for text generation. Taken together, the results establish hierarchical continuous latent prior modeling as a principled alternative to strictly token-level language modeling, where generation quality and scaling behavior may better reflect model capability than likelihood, while also suggesting a concrete path toward unified modeling across discrete text and continuous modalities.</p> + https://arxiv.org/abs/2605.06548 + Thu, 07 May 2026 00:00:00 +0000 + + + Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning + https://arxiv.org/abs/2605.06130 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06130.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaorui Shi, Yuxin Chen, Zhengxi Lu, Yuchun Miao, Shugui Liu, Qi GU, Xunliang Cai, Xiang Wang, An Zhang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and distills new skills from experience. Existing methods optimize these capabilities in isolation or with separate reward sources, resulting in partial and conflicting evolution. We propose Skill1, a framework that trains a single policy to co-evolve skill selection, utilization, and distillation toward a shared task-outcome objective. The policy generates a query to search the skill library, re-ranks candidates to select one, solves the task conditioned on it, and distills a new skill from the trajectory. All learning derives from a single task-outcome signal. Its low-frequency trend credits selection and its high-frequency variation credits distillation. Experiments on ALFWorld and WebShop show that Skill1 outperforms prior skill-based and reinforcement learning baselines. Training dynamics confirm the co-evolution of the three capabilities, and ablations show that removing any credit signal degrades the evolution.</p> + https://arxiv.org/abs/2605.06130 + Thu, 07 May 2026 00:00:00 +0000