748 lines
231 KiB
XML
748 lines
231 KiB
XML
<?xml version='1.0' encoding='UTF-8'?>
|
||
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
|
||
<channel>
|
||
<title>Hugging Face Daily Papers</title>
|
||
<link>https://huggingface.co/papers</link>
|
||
<description>Daily research papers curated by the Hugging Face community.</description>
|
||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||
<generator>python-feedgen</generator>
|
||
<language>en</language>
|
||
<lastBuildDate>Mon, 11 May 2026 00:30:42 +0000</lastBuildDate>
|
||
<item>
|
||
<title>StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing</title>
|
||
<link>https://arxiv.org/abs/2605.02904</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02904</guid>
|
||
<pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2605.02913</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02913</guid>
|
||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO</title>
|
||
<link>https://arxiv.org/abs/2605.04077</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04077</guid>
|
||
<pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills</title>
|
||
<link>https://arxiv.org/abs/2604.20441</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.20441</guid>
|
||
<pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2605.00877</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00877</guid>
|
||
<pubDate>Sat, 25 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Diffusion Model as a Generalist Segmentation Learner</title>
|
||
<link>https://arxiv.org/abs/2604.24575</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.24575</guid>
|
||
<pubDate>Mon, 27 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Soft Anisotropic Diagrams for Differentiable Image Representation</title>
|
||
<link>https://arxiv.org/abs/2604.21984</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.21984</guid>
|
||
<pubDate>Mon, 27 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills</title>
|
||
<link>https://arxiv.org/abs/2604.24026</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.24026</guid>
|
||
<pubDate>Mon, 27 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>X2SAM: Any Segmentation in Images and Videos</title>
|
||
<link>https://arxiv.org/abs/2605.00891</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00891</guid>
|
||
<pubDate>Mon, 27 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Prior-Aligned Data Cleaning for Tabular Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2604.25154</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.25154</guid>
|
||
<pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum</title>
|
||
<link>https://arxiv.org/abs/2604.25907</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.25907</guid>
|
||
<pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?</title>
|
||
<link>https://arxiv.org/abs/2604.09408</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.09408</guid>
|
||
<pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2604.27124</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27124</guid>
|
||
<pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models</title>
|
||
<link>https://arxiv.org/abs/2405.13729</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2405.13729</guid>
|
||
<pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions</title>
|
||
<link>https://arxiv.org/abs/2604.23774</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.23774</guid>
|
||
<pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction</title>
|
||
<link>https://arxiv.org/abs/2604.27221</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27221</guid>
|
||
<pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark</title>
|
||
<link>https://arxiv.org/abs/2604.27582</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27582</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks</title>
|
||
<link>https://arxiv.org/abs/2604.27818</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27818</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO</title>
|
||
<link>https://arxiv.org/abs/2604.27488</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27488</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>When Do Diffusion Models learn to Generate Multiple Objects?</title>
|
||
<link>https://arxiv.org/abs/2605.00273</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00273</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments</title>
|
||
<link>https://arxiv.org/abs/2604.27776</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27776</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling</title>
|
||
<link>https://arxiv.org/abs/2604.28075</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.28075</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction</title>
|
||
<link>https://arxiv.org/abs/2604.27393</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27393</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation</title>
|
||
<link>https://arxiv.org/abs/2604.28196</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.28196</guid>
|
||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Healthcare AI GYM for Medical Agents</title>
|
||
<link>https://arxiv.org/abs/2605.02943</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02943</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Recovering Hidden Reward in Diffusion-Based Policies</title>
|
||
<link>https://arxiv.org/abs/2605.00623</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00623</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation</title>
|
||
<link>https://arxiv.org/abs/2605.00529</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00529</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2605.00380</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00380</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Trees to Flows and Back: Unifying Decision Trees and Diffusion Models</title>
|
||
<link>https://arxiv.org/abs/2605.00414</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00414</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer</title>
|
||
<link>https://arxiv.org/abs/2605.00503</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00503</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies</title>
|
||
<link>https://arxiv.org/abs/2605.00416</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00416</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2605.00347</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00347</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance</title>
|
||
<link>https://arxiv.org/abs/2605.00553</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00553</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs</title>
|
||
<link>https://arxiv.org/abs/2605.00814</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00814</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Map2World: Segment Map Conditioned Text to 3D World Generation</title>
|
||
<link>https://arxiv.org/abs/2605.00781</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00781</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Let ViT Speak: Generative Language-Image Pre-training</title>
|
||
<link>https://arxiv.org/abs/2605.00809</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00809</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL</title>
|
||
<link>https://arxiv.org/abs/2604.28123</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.28123</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors</title>
|
||
<link>https://arxiv.org/abs/2605.00658</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00658</guid>
|
||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Agentic AI Systems Should Be Designed as Marginal Token Allocators</title>
|
||
<link>https://arxiv.org/abs/2605.01214</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01214</guid>
|
||
<pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Prescriptive Scaling Laws for Data Constrained Training</title>
|
||
<link>https://arxiv.org/abs/2605.01640</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01640</guid>
|
||
<pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion</title>
|
||
<link>https://arxiv.org/abs/2605.01466</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01466</guid>
|
||
<pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue</title>
|
||
<link>https://arxiv.org/abs/2605.01371</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01371</guid>
|
||
<pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Hallucinations Undermine Trust; Metacognition is a Way Forward</title>
|
||
<link>https://arxiv.org/abs/2605.01428</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01428</guid>
|
||
<pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Linear-Time Global Visual Modeling without Explicit Attention</title>
|
||
<link>https://arxiv.org/abs/2605.01711</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01711</guid>
|
||
<pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis</title>
|
||
<link>https://arxiv.org/abs/2605.01717</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01717</guid>
|
||
<pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Motion-Aware Caching for Efficient Autoregressive Video Generation</title>
|
||
<link>https://arxiv.org/abs/2605.01725</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01725</guid>
|
||
<pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction</title>
|
||
<link>https://arxiv.org/abs/2605.05242</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05242</guid>
|
||
<pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>From Context to Skills: Can Language Models Learn from Context Skillfully?</title>
|
||
<link>https://arxiv.org/abs/2604.27660</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2604.27660</guid>
|
||
<pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Perceptual Flow Network for Visually Grounded Reasoning</title>
|
||
<link>https://arxiv.org/abs/2605.02730</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02730</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces</title>
|
||
<link>https://arxiv.org/abs/2605.02801</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02801</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments</title>
|
||
<link>https://arxiv.org/abs/2605.02240</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02240</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2605.02178</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02178</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Generative Modeling with Orbit-Space Particle Flow Matching</title>
|
||
<link>https://arxiv.org/abs/2605.02222</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02222</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors</title>
|
||
<link>https://arxiv.org/abs/2411.18966</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2411.18966</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AcademiClaw: When Students Set Challenges for AI Agents</title>
|
||
<link>https://arxiv.org/abs/2605.02661</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02661</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Video Generation with Predictive Latents</title>
|
||
<link>https://arxiv.org/abs/2605.02134</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02134</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness</title>
|
||
<link>https://arxiv.org/abs/2605.02396</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02396</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration</title>
|
||
<link>https://arxiv.org/abs/2605.03042</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03042</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MolmoAct2: Action Reasoning Models for Real-world Deployment</title>
|
||
<link>https://arxiv.org/abs/2605.02881</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02881</guid>
|
||
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>The Scaling Properties of Implicit Deductive Reasoning in Transformers</title>
|
||
<link>https://arxiv.org/abs/2605.04330</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04330</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A Benchmark for Interactive World Models with a Unified Action Generation Framework</title>
|
||
<link>https://arxiv.org/abs/2605.03941</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03941</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music</title>
|
||
<link>https://arxiv.org/abs/2605.03395</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03395</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback</title>
|
||
<link>https://arxiv.org/abs/2605.03848</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03848</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies</title>
|
||
<link>https://arxiv.org/abs/2605.03596</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03596</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination</title>
|
||
<link>https://arxiv.org/abs/2605.03571</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03571</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment</title>
|
||
<link>https://arxiv.org/abs/2605.04012</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04012</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation</title>
|
||
<link>https://arxiv.org/abs/2605.04128</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04128</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Audio-Visual Intelligence in Large Foundation Models</title>
|
||
<link>https://arxiv.org/abs/2605.04045</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04045</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems</title>
|
||
<link>https://arxiv.org/abs/2605.04018</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04018</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories</title>
|
||
<link>https://arxiv.org/abs/2605.04036</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04036</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>RLDX-1 Technical Report</title>
|
||
<link>https://arxiv.org/abs/2605.03269</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03269</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation</title>
|
||
<link>https://arxiv.org/abs/2605.03849</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.03849</guid>
|
||
<pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A Foundation Model for Zero-Shot Logical Rule Induction</title>
|
||
<link>https://arxiv.org/abs/2605.04916</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04916</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels</title>
|
||
<link>https://arxiv.org/abs/2605.04956</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04956</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>RemoteZero: Geospatial Reasoning with Zero Human Annotations</title>
|
||
<link>https://arxiv.org/abs/2605.04451</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04451</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding</title>
|
||
<link>https://arxiv.org/abs/2605.04962</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04962</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving</title>
|
||
<link>https://arxiv.org/abs/2605.04647</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04647</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>StableI2I: Spotting Unintended Changes in Image-to-Image Transition</title>
|
||
<link>https://arxiv.org/abs/2605.04453</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04453</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Lightning Unified Video Editing via In-Context Sparse Attention</title>
|
||
<link>https://arxiv.org/abs/2605.04569</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04569</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing</title>
|
||
<link>https://arxiv.org/abs/2605.02910</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.02910</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models</title>
|
||
<link>https://arxiv.org/abs/2605.05204</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05204</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World</title>
|
||
<link>https://arxiv.org/abs/2605.05163</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05163</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation</title>
|
||
<link>https://arxiv.org/abs/2605.04523</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04523</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents</title>
|
||
<link>https://arxiv.org/abs/2605.05185</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05185</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Stream-T1: Test-Time Scaling for Streaming Video Generation</title>
|
||
<link>https://arxiv.org/abs/2605.04461</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.04461</guid>
|
||
<pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>PianoCoRe: Combined and Refined Piano MIDI Dataset</title>
|
||
<link>https://arxiv.org/abs/2605.06627</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06627</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity</title>
|
||
<link>https://arxiv.org/abs/2605.05662</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05662</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models</title>
|
||
<link>https://arxiv.org/abs/2605.06196</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06196</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation</title>
|
||
<link>https://arxiv.org/abs/2605.06356</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06356</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>TIDE: Every Layer Knows the Token Beneath the Context</title>
|
||
<link>https://arxiv.org/abs/2605.06216</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06216</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>EMO: Pretraining Mixture of Experts for Emergent Modularity</title>
|
||
<link>https://arxiv.org/abs/2605.06663</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06663</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>UniPool: A Globally Shared Expert Pool for Mixture-of-Experts</title>
|
||
<link>https://arxiv.org/abs/2605.06665</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06665</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>AI Co-Mathematician: Accelerating Mathematicians with Agentic AI</title>
|
||
<link>https://arxiv.org/abs/2605.06651</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06651</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key</title>
|
||
<link>https://arxiv.org/abs/2605.06638</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06638</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping</title>
|
||
<link>https://arxiv.org/abs/2605.06200</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06200</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes</title>
|
||
<link>https://arxiv.org/abs/2605.05724</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05724</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction</title>
|
||
<link>https://arxiv.org/abs/2605.06642</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06642</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Continuous-Time Distribution Matching for Few-Step Diffusion Distillation</title>
|
||
<link>https://arxiv.org/abs/2605.06376</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06376</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration</title>
|
||
<link>https://arxiv.org/abs/2605.05566</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.05566</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>SkillOS: Learning Skill Curation for Self-Evolving Agents</title>
|
||
<link>https://arxiv.org/abs/2605.06614</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06614</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MARBLE: Multi-Aspect Reward Balance for Diffusion RL</title>
|
||
<link>https://arxiv.org/abs/2605.06507</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06507</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>When to Trust Imagination: Adaptive Action Execution for World Action Models</title>
|
||
<link>https://arxiv.org/abs/2605.06222</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06222</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>MiA-Signature: Approximating Global Activation for Long-Context Understanding</title>
|
||
<link>https://arxiv.org/abs/2605.06416</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06416</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Continuous Latent Diffusion Language Model</title>
|
||
<link>https://arxiv.org/abs/2605.06548</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06548</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
<item>
|
||
<title>Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning</title>
|
||
<link>https://arxiv.org/abs/2605.06130</link>
|
||
<description><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></description>
|
||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06130</guid>
|
||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||
</item>
|
||
</channel>
|
||
</rss>
|