bot: update RSS feed
This commit is contained in:
github-actions[bot]
402
feed.xml
402
feed.xml
@@ -7,202 +7,300 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Fri, 10 Apr 2026 00:09:11 +0000</lastBuildDate>
|
<lastBuildDate>Sat, 11 Apr 2026 00:07:49 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics</title>
|
<title>Structural Graph Probing of Vision-Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2604.06182</link>
|
<link>https://arxiv.org/abs/2603.27070</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Gong, Zhuohan Cai, Sunhao Dai, Yuqi Zhou, Zhangxuan Gu, Changhua Meng, Shuheng Shen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online benchmark for evaluating general-purpose mobile GUI agents under realistic, user-centric conditions. VenusBench-Mobile builds two core evaluation pillars: defining what to evaluate via user-intent-driven task design that reflects real mobile usage, and how to evaluate through a capability-oriented annotation scheme for fine-grained agent behavior analysis. Extensive evaluation of state-of-the-art mobile GUI agents reveals large performance gaps relative to prior benchmarks, indicating that VenusBench-Mobile poses substantially more challenging and realistic tasks and that current agents remain far from reliable real-world deployment. Diagnostic analysis further shows that failures are dominated by deficiencies in perception and memory, which are largely obscured by coarse-grained evaluations. Moreover, even the strongest agents exhibit near-zero success under environment variations, highlighting their brittleness in realistic settings. Based on these insights, we believe VenusBench-Mobile provides an important stepping stone toward robust real-world deployment of mobile GUI agents. Code and data are available at https://github.com/inclusionAI/UI-Venus/tree/VenusBench-Mobile.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.27070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu He, Yue Zhuo, Yu Zheng, Qi R. Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-language models (VLMs) achieve strong multimodal performance, yet how computation is organized across populations of neurons remains poorly understood. In this work, we study VLMs through the lens of neural topology, representing each layer as a within-layer correlation graph derived from neuron-neuron co-activations. This view allows us to ask whether population-level structure is behaviorally meaningful, how it changes across modalities and depth, and whether it identifies causally influential internal components under intervention. We show that correlation topology carries recoverable behavioral signal; moreover, cross-modal structure progressively consolidates with depth around a compact set of recurrent hub neurons, whose targeted perturbation substantially alters model output. Neural topology thus emerges as a meaningful intermediate scale for VLM interpretability: richer than local attribution, more tractable than full circuit recovery, and empirically tied to multimodal behavior. Code is publicly available at https://github.com/he-h/vlm-graph-probing.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06182</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2603.27070</guid>
|
||||||
<pubDate>Fri, 06 Feb 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sat, 28 Mar 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SEVerA: Verified Synthesis of Self-Evolving Agents</title>
|
<title>Automating Database-Native Function Code Synthesis with LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2603.25111</link>
|
<link>https://arxiv.org/abs/2604.06231</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Debangshu Banerjee, Changming Xu, Gagandeep Singh</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs, which are then tuned per task to improve performance. However, existing self-evolving agent frameworks provide no formal guarantees of safety or correctness. Because such programs are often executed autonomously on unseen inputs, this lack of guarantees raises reliability and security concerns. We formulate agentic code generation as a constrained learning problem, combining hard formal specifications with soft objectives capturing task utility. We introduce Formally Guarded Generative Models (FGGM), which allow the planner LLM to specify a formal output contract for each generative model call using first-order logic. Each FGGM call wraps the underlying model in a rejection sampler with a verified fallback, ensuring every returned output satisfies the contract for any input and parameter setting. Building on FGGM, we present SEVerA (Self-Evolving Verified Agents), a three-stage framework: Search synthesizes candidate parametric programs containing FGGM calls; Verification proves correctness with respect to hard constraints for all parameter values, reducing the problem to unconstrained learning; and Learning applies scalable gradient-based optimization, including GRPO-style fine-tuning, to improve the soft objective while preserving correctness. We evaluate SEVerA on Dafny program verification, symbolic math synthesis, and policy-compliant agentic tool use (τ^2-bench). Across tasks, SEVerA achieves zero constraint violations while improving performance over unconstrained and SOTA baselines, showing that formal behavioral constraints not only guarantee correctness but also steer synthesis toward higher-quality agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06231.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Zhou, Xuanhe Zhou, Qikang He, Guoliang Li, Bingsheng He, Quanqing Xu, Fan Wu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new application support and business migration. This growth causes an urgent demand for automatic database native function synthesis. While recent advances in LLM-based code generation (e.g., Claude Code) show promise, they are too generic for database-specific development. They often hallucinate or overlook critical context because database function synthesis is inherently complex and error-prone, where synthesizing a single function may involve registering multiple function units, linking internal references, and implementing logic correctly. To this end, we propose DBCooker, an LLM-based system for automatically synthesizing database native functions. It consists of three components. First, the function characterization module aggregates multi-source declarations, identifies function units that require specialized coding, and traces cross-unit dependencies. Second, we design operations to address the main synthesis challenges: (1) a pseudo-code-based coding plan generator that constructs structured implementation skeletons by identifying key elements such as reusable referenced functions; (2) a hybrid fill-in-the-blank model guided by probabilistic priors and component awareness to integrate core logic with reusable routines; and (3) three-level progressive validation, including syntax checking, standards compliance, and LLM-guided semantic verification. Finally, an adaptive orchestration strategy unifies these operations with existing tools and dynamically sequences them via the orchestration history of similar functions. Results show that DBCooker outperforms other methods on SQLite, PostgreSQL, and DuckDB (34.55% higher accuracy on average), and can synthesize new functions absent in the latest SQLite (v3.50).</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.25111</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.06231</guid>
|
||||||
<pubDate>Thu, 26 Mar 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Tunable Soft Equivariance with Guarantees</title>
|
<title>Training a Student Expert via Semi-Supervised Foundation Model Distillation</title>
|
||||||
<link>https://arxiv.org/abs/2603.26657</link>
|
<link>https://arxiv.org/abs/2604.03841</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.26657.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Ashiqur Rahman, Lim Jun Hao, Jeremiah Jiang, Teck-Yian Lim, Raymond A. Yeh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03841.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pardis Taghavi, Tian Liu, Renjie Li, Reza Langari, Zhengzhong Tu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses pre-trained vision foundation models (VFMs) into compact experts using limited labeled and abundant unlabeled data, and instantiate it for instance segmentation where per-pixel labels are particularly expensive. The framework unfolds in three stages: (1) domain adaptation of the VFM(s) via self-training with contrastive calibration, (2) knowledge transfer through a unified multi-objective loss, and (3) student refinement to mitigate residual pseudo-label bias. Central to our approach is an instance-aware pixel-wise contrastive loss that fuses mask and class scores to extract informative negatives and enforce clear inter-instance margins. By maintaining this contrastive signal across both adaptation and distillation, we align teacher and student embeddings and more effectively leverage unlabeled images. On Cityscapes and ADE20K, our approx 11times smaller student improves over its zero-shot VFM teacher(s) by +11.9 and +8.6 AP, surpasses adapted teacher(s) by +3.4 and +1.5 AP, and outperforms state-of-the-art SSKD methods on benchmarks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.26657</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.03841</guid>
|
||||||
<pubDate>Fri, 27 Mar 2026 17:56:25 +0000</pubDate>
|
<pubDate>Sat, 04 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning to Hint for Reinforcement Learning</title>
|
<title>QEIL v2: Heterogeneous Computing for Edge Intelligence via Roofline-Derived Pareto-Optimal Energy Modeling and Multi-Objective Orchestration</title>
|
||||||
<link>https://arxiv.org/abs/2604.00698</link>
|
<link>https://arxiv.org/abs/2602.06057</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Xia, Canwen Xu, Zhewei Yao, Julian McAuley, Yuxiong He</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal. For example, if a question is too hard for the reasoner, all sampled rollouts can be incorrect and receive zero reward. Recent work addresses this issue by adding hints or auxiliary scaffolds to such hard questions so that the reasoner produces mixed outcomes and recovers a non-zero update. However, existing hints are usually fixed rather than adapted to the current reasoner, and a hint that creates learning signal under the hinted input does not necessarily improve the no-hint policy used at test time. To this end, we propose Hint Learning for Reinforcement Learning (HiLL), a framework that jointly trains a hinter policy and a reasoner policy during RL. For each hard question, the hinter generates hints online conditioned on the current reasoner's incorrect rollout, allowing hint generation to adapt to the reasoner's evolving errors. We further introduce hint reliance, which measures how strongly correct hinted trajectories depend on the hint. We derive a transferability result showing that lower hint reliance implies stronger transfer from hinted success to no-hint success, and we use this result to define a transfer-weighted reward for training the hinter. Therefore, HiLL favors hints that not only recover informative GRPO groups, but also produce signals that are more likely to improve the original no-hint policy. Experiments across multiple benchmarks show that HiLL consistently outperforms GRPO and prior hint-based baselines, demonstrating the value of adaptive and transfer-aware hint learning for RL. The code is available at https://github.com/Andree-9/HiLL.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.06057.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Satyam Kumar, Saurabh Jha</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Deploying large language models (LLMs) on heterogeneous edge devices demands frameworks that jointly optimize energy efficiency, inference quality, and reliability. Our prior QEIL v1 (Kumar & Jha, 2026) achieved 4.82x IPW improvement but relied on static efficiency factors, greedy optimization, and unverified candidate selection. QEIL v2 replaces every static heuristic with physics-grounded, runtime-adaptive models. We introduce three device-workload metrics: DASI (roofline-derived compute utilization), CPQ (memory pressure from allocation theory), and Phi (thermal yield from CMOS leakage physics), forming a unified energy equation with every coefficient traceable to semiconductor physics. For optimization, PGSAM (Pareto-Guided Simulated Annealing with Momentum) simultaneously minimizes energy, latency, and device underutilization. At inference time, the EAC/ARDE selection cascade with CSVET early stopping provides progressive verification among repeated samples. Evaluated on WikiText-103, GSM8K, and ARC-Challenge across seven model families (125M-8B parameters, including one pre-quantized variant), QEIL v2 achieves 75.7% pass@k at 63.8W (IPW=0.9749), a 2.86x improvement over standard inference. When applied to a 4-bit Llama-3.1-8B, QEIL v2's physics-grounded routing achieves IPW=1.024 at 54.8W -- the first edge orchestration system to surpass the IPW=1.0 empirical reference mark, with the gain attributable entirely to QEIL v2's workload-adaptive device allocation on a model with reduced memory bandwidth requirements. Total energy drops 75.6% vs. standard with 38.3% latency reduction, zero thermal throttling, and 100% fault recovery across all benchmarks and model families.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.00698</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.06057</guid>
|
||||||
<pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.03995</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.03995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Chen, Deepti Ghadiyaram</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study examining how typographic attacks across multiple modalities adversely influence MLLMs. While prior work focuses narrowly on unimodal attacks, we expose the cross-modal fragility of MLLMs. We analyze the interactions between audio, visual, and text perturbations and reveal that coordinated multi-modal attack creates a significantly more potent threat than single-modality attacks (attack success rate = 83.43% vs 34.93%).Our findings across multiple frontier MLLMs, tasks, and common-sense reasoning and content moderation benchmarks establishes multi-modal typography as a critical and underexplored attack strategy in multi-modal reasoning. Code and data will be publicly available.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.03995</guid>
|
|
||||||
<pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Combee: Scaling Prompt Learning for Self-Improving Language Model Agents</title>
|
<title>Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills</title>
|
||||||
<link>https://arxiv.org/abs/2604.04247</link>
|
<link>https://arxiv.org/abs/2604.05333</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04247.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to improve accuracy based on previous agent runs. However, these methods primarily focus on single-agent or low-parallelism settings. This fundamentally limits their ability to efficiently learn from a large set of collected agentic traces. It would be efficient and beneficial to run prompt learning in parallel to accommodate the growing trend of learning from many agentic traces or parallel agent executions. Yet without a principled strategy for scaling, current methods suffer from quality degradation with high parallelism. To improve both the efficiency and quality of prompt learning, we propose Combee, a novel framework to scale parallel prompt learning for self-improving agents. Combee speeds up learning and enables running many agents in parallel while learning from their aggregate traces without quality degradation. To achieve this, Combee leverages parallel scans and employs an augmented shuffle mechanism; Combee also introduces a dynamic batch size controller to balance quality and delay. Evaluations on AppWorld, Terminal-Bench, Formula, and FiNER demonstrate that Combee achieves up to 17x speedup over previous methods with comparable or better accuracy and equivalent cost.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dawei Li, Zongxia Li, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Skill usage has become a core component of modern agent systems and can substantially improve agents' ability to complete complex tasks. In real-world settings, where agents must monitor and interact with numerous personal applications, web browsers, and other environment interfaces, skill libraries can scale to thousands of reusable skills. Scaling to larger skill sets introduces two key challenges. First, loading the full skill set saturates the context window, driving up token costs, hallucination, and latency. In this paper, we present Graph of Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then at inference time retrieves a bounded, dependency-aware skill bundle through hybrid semantic-lexical seeding, reverse-weighted Personalized PageRank, and context-budgeted hydration. On SkillsBench and ALFWorld, GoS improves average reward by 43.6% over the vanilla full skill-loading baseline while reducing input tokens by 37.8%, and generalizes across three model families: Claude Sonnet, GPT-5.2 Codex, and MiniMax. Additional ablation studies across skill libraries ranging from 200 to 2,000 skills further demonstrate that GoS consistently outperforms both vanilla skills loading and simple vector retrieval in balancing reward, token efficiency, and runtime.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.04247</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.05333</guid>
|
||||||
<pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>R3PM-Net: Real-time, Robust, Real-world Point Matching Network</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.05060</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yasaman Kashefbahrami, Erkut Akdag, Panagiotis Meletis, Evgeniya Balmashnova, Dip Goswami, Egor Bondarau</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of 1 and inlier RMSE of 0.029 cm in only 0.007s, approximately 7 times faster than the state-of-the-art method RegTR. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of 1 and inlier RMSE of 0.030 cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.05060</guid>
|
|
||||||
<pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.04913</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tommie Kerssies, Gabriele Berton, Ju He, Qihang Yu, Wufei Ma, Daan de Geus, Gijs Dubbelman, Liang-Chieh Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitly averages over possible futures, while existing generative world models remain computationally expensive. Recent work demonstrates that predicting the future in the feature space of a vision foundation model (VFM), rather than a latent space optimized for pixel reconstruction, requires significantly fewer world model parameters. However, most such approaches remain discriminative. In this work, we introduce DeltaTok, a tokenizer that encodes the VFM feature difference between consecutive frames into a single continuous "delta" token, and DeltaWorld, a generative world model operating on these tokens to efficiently generate diverse plausible futures. Delta tokens reduce video from a three-dimensional spatio-temporal representation to a one-dimensional temporal sequence, for example yielding a 1,024x token reduction with 512x512 frames. This compact representation enables tractable multi-hypothesis training, where many futures are generated in parallel and only the best is supervised. At inference, this leads to diverse predictions in a single forward pass. Experiments on dense forecasting tasks demonstrate that DeltaWorld forecasts futures that more closely align with real-world outcomes, while having over 35x fewer parameters and using 2,000x fewer FLOPs than existing generative world models. Code and weights: https://deltatok.github.io.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.04913</guid>
|
|
||||||
<pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>DeonticBench: A Benchmark for Reasoning over Rules</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.04443</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04443.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guangyao Dou, Luis Brena, Akhil Deo, William Jurayj, Jingyu Zhang, Nils Holzenberger, Benjamin Van Durme</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reasoning with complex, context-specific rules remains challenging for large language models (LLMs). In legal and policy settings, this manifests as deontic reasoning: reasoning about obligations, permissions, and prohibitions under explicit rules. While many recent benchmarks emphasize short-context mathematical reasoning, fewer focus on long-context, high-stakes deontic reasoning. To address this gap, we introduce DEONTICBENCH, a benchmark of 6,232 tasks across U.S. federal taxes, airline baggage policies, U.S. immigration administration, and U.S. state housing law. These tasks can be approached in multiple ways, including direct reasoning in language or with the aid of symbolic computation. Besides free-form chain-of-thought reasoning, DEONTICBENCH enables an optional solver-based workflow in which models translate statutes and case facts into executable Prolog, leading to formal problem interpretations and an explicit program trace. We release reference Prolog programs for all instances. Across frontier LLMs and coding models, best hard-subset performance reaches only 44.4% on SARA Numeric and 46.6 macro-F1 on Housing. We further study training with supervised fine-tuning and reinforcement learning for symbolic program generation. Although training improves Prolog generation quality, current RL methods still fail to solve these tasks reliably. Overall, DEONTICBENCH provides a benchmark for studying context-grounded rule reasoning in real-world domains under both symbolic and non-symbolic settings.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.04443</guid>
|
|
||||||
<pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.04734</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, Heuiseok Lim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Transferring knowledge from a cross-encoder teacher via Knowledge Distillation (KD) has become a standard paradigm for training retrieval models. While existing studies have largely focused on mining hard negatives to improve discrimination, the systematic composition of training data and the resulting teacher score distribution have received relatively less attention. In this work, we highlight that focusing solely on hard negatives prevents the student from learning the comprehensive preference structure of the teacher, potentially hampering generalization. To effectively emulate the teacher score distribution, we propose a Stratified Sampling strategy that uniformly covers the entire score spectrum. Experiments on in-domain and out-of-domain benchmarks confirm that Stratified Sampling, which preserves the variance and entropy of teacher scores, serves as a robust baseline, significantly outperforming top-K and random sampling in diverse settings. These findings suggest that the essence of distillation lies in preserving the diverse range of relative scores perceived by the teacher.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.04734</guid>
|
|
||||||
<pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Qualixar OS: A Universal Operating System for AI Agent Orchestration</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.06392</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varun Pratap Bhardwaj</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Qualixar OS, the first application-layer operating system for universal AI agent orchestration. Unlike kernel-level approaches (AIOS) or single-framework tools (AutoGen, CrewAI), Qualixar OS provides a complete runtime for heterogeneous multi-agent systems spanning 10 LLM providers, 8+ agent frameworks, and 7 transports. We contribute: (1) execution semantics for 12 multi-agent topologies including grid, forest, mesh, and maker patterns; (2) Forge, an LLM-driven team design engine with historical strategy memory; (3) three-layer model routing combining Q-learning, five strategies, and Bayesian POMDP with dynamic multi-provider discovery; (4) a consensus-based judge pipeline with Goodhart detection, JSD drift monitoring, and alignment trilemma navigation; (5) four-layer content attribution with HMAC signing and steganographic watermarks; (6) universal compatibility via the Claw Bridge supporting MCP and A2A protocols with a 25-command Universal Command Protocol; (7) a 24-tab production dashboard with visual workflow builder and skill marketplace. Qualixar OS is validated by 2,821 test cases across 217 event types and 8 quality modules. On a custom 20-task evaluation suite, the system achieves 100% accuracy at a mean cost of $0.000039 per task. Source-available under the Elastic License 2.0.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06392</guid>
|
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning</title>
|
<title>The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment</title>
|
||||||
<link>https://arxiv.org/abs/2604.05846</link>
|
<link>https://arxiv.org/abs/2604.06377</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)-driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at https://github.com/sunyuanfu/AgentGL.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma, Anjie Fang, Fardin Abdi, Viktor Rozgic, Zheng Du, Mohit Bansal, Tu Vu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through linear alignment. Based on this hypothesis, we introduce UNLOCK, a training-free and label-free framework that extracts a capability direction by contrasting activations between capability-present and capability-absent Source variants, aligns it with a Target model through a low-rank linear transformation, and applies it at inference time to elicit the behavior. Experiments on reasoning behaviors, including Chain-of-Thought (CoT) and mathematical reasoning, demonstrate substantial improvements across model scales without training. For example, transferring CoT reasoning from Qwen1.5-14B to Qwen1.5-7B yields an accuracy gain of 12.1% on MATH, and transferring a mathematical reasoning direction from Qwen3-4B-Base to Qwen3-14B-Base improves AGIEval Math accuracy from 61.1% to 71.3%, surpassing the 67.8% achieved by the 14B post-trained model. Our analysis shows that the success of transfer depends on the capabilities learned during pre-training, and that our intervention amplifies latent capabilities by sharpening the output distribution toward successful reasoning trajectories.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.05846</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.06377</guid>
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 07 Apr 2026 19:02:10 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment</title>
|
<title>Personalizing Text-to-Image Generation to Individual Taste</title>
|
||||||
<link>https://arxiv.org/abs/2604.05684</link>
|
<link>https://arxiv.org/abs/2604.07427</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05684.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongtae Hong, Youngjoon Jang, Jungseob Lee, Hyeonseok Moon, Heuiseok Lim</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> With the increasing accessibility and utilization of multilingual documents, Cross-Lingual Information Retrieval (CLIR) has emerged as an important research area. Conventionally, CLIR tasks have been conducted under settings where the language of documents differs from that of queries, and typically, the documents are composed in a single coherent language. In this paper, we highlight that in such a setting, the cross-lingual alignment capability may not be evaluated adequately. Specifically, we observe that, in a document pool where English documents coexist with another language, most multilingual retrievers tend to prioritize unrelated English documents over the related document written in the same language as the query. To rigorously analyze and quantify this phenomenon, we introduce various scenarios and metrics designed to evaluate the cross-lingual alignment performance of multilingual retrieval models. Furthermore, to improve cross-lingual performance under these challenging conditions, we propose a novel training strategy aimed at enhancing cross-lingual alignment. Using only a small dataset consisting of 2.8k samples, our method significantly improves the cross-lingual retrieval performance while simultaneously mitigating the English inclination problem. Extensive analyses demonstrate that the proposed method substantially enhances the cross-lingual alignment capabilities of most multilingual embedding models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik, Ameya Prabhu, Johan Wagemans, Matthias Bethge</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent subjectivity of aesthetic judgment. In this work, we introduce a novel dataset and predictive framework, called PAMELA, designed to model personalized image evaluations. Our dataset comprises 70,000 ratings across 5,000 diverse images generated by state-of-the-art models (Flux 2 and Nano Banana). Each image is evaluated by 15 unique users, providing a rich distribution of subjective preferences across domains such as art, design, fashion, and cinematic photography. Leveraging this data, we propose a personalized reward model trained jointly on our high-quality annotations and existing aesthetic assessment subsets. We demonstrate that our model predicts individual liking with higher accuracy than the majority of current state-of-the-art methods predict population-level preferences. Using our personalized predictor, we demonstrate how simple prompt optimization methods can be used to steer generations towards individual user preferences. Our results highlight the importance of data quality and personalization to handle the subjectivity of user preferences. We release our dataset and model to facilitate standardized research in personalized T2I alignment and subjective visual quality assessment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.05684</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07427</guid>
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.06427</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Xu, Philipp Jettkant, Laura Ruis</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits by studying whether models can discover multi-step planning strategies without supervision on intermediate steps and execute them latently, within a single forward pass. Using graph path-finding tasks that precisely control the number of required latent planning steps, we uncover a striking limitation unresolved by massive scaling: tiny transformers trained from scratch discover strategies requiring up to three latent steps, fine-tuned GPT-4o and Qwen3-32B reach five, and GPT-5.4 attains seven under few-shot prompting. Although the maximum latent planning depth models can learn during training is five, the discovered strategy generalizes up to eight latent steps at test-time. This reveals a dissociation between the ability to discover a latent strategy under final-answer supervision alone and the ability to execute it once discovered. If similar limits hold more broadly, strategies requiring multiple coordinated latent planning steps may need to be explicitly taught or externalized, lending credence to CoT monitoring.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06427</guid>
|
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.05643</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05643.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant intermediate reasoning content. In this work, we argue that a major source of such redundancy is inefficient reflection, which often manifests in two problematic patterns: Indiscriminate Reflection, where the model performs broad, low-impact checks throughout reasoning, and Repetitive Reflection, where it repeatedly re-verifies an already established conclusion. To address this, we introduce a graph-based CoT optimization framework. Specifically, we convert each linear CoT into a directed acyclic graph (DAG) with explicit dependency edges, and design a dual pruning strategy: branch-level pruning removes weakly contributing reflection branches, while depth-level pruning eliminates late-stage re-verification. We distill this behavior via a three-stage pipeline: (1) SFT to initialize the policy on pruned concise traces, (2) DPO to prefer correct but less redundant trajectories, and (3) GRPO with length penalty to jointly optimize answer correctness and efficiency. Experiments show that our approach reduces the average reasoning tokens by 42\% while maintaining or improving accuracy.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.05643</guid>
|
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Neural Computers</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.06425</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. Unlike conventional computers, which execute explicit programs, agents, which act over external execution environments, and world models, which learn environment dynamics, NCs aim to make the model itself the running computer. Our long-term goal is the Completely Neural Computer (CNC): the mature, general-purpose realization of this emerging machine form, with stable execution, explicit reprogramming, and durable capability reuse. As an initial step, we study whether early NC primitives can be learned solely from collected I/O traces, without instrumented program state. Concretely, we instantiate NCs as video models that roll out screen frames from instructions, pixels, and user actions (when available) in CLI and GUI settings. These implementations show that learned runtimes can acquire early interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain open. We outline a roadmap toward CNCs around these challenges. If overcome, CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06425</guid>
|
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>RAGEN-2: Reasoning Collapse in Agentic RL</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.06268</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input, and cannot tell whether reasoning actually responds to different inputs. In RAGEN-2, we find that even with stable entropy, models can rely on fixed templates that look diverse but are input-agnostic. We call this template collapse, a failure mode invisible to entropy and all existing metrics. To diagnose this failure, we decompose reasoning quality into within-input diversity (Entropy) and cross-input distinguishability (Mutual Information, MI), and introduce a family of mutual information proxies for online diagnosis. Across diverse tasks, mutual information correlates with final performance much more strongly than entropy, making it a more reliable proxy for reasoning quality. We further explain template collapse with a signal-to-noise ratio (SNR) mechanism. Low reward variance weakens task gradients, letting regularization terms dominate and erase cross-input reasoning differences. To address this, we propose SNR-Aware Filtering to select high-signal prompts per iteration using reward variance as a lightweight proxy. Across planning, math reasoning, web navigation, and code execution, the method consistently improves both input dependence and task performance.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06268</guid>
|
|
||||||
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos</title>
|
|
||||||
<link>https://arxiv.org/abs/2604.07273</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqian Wu, Rawal Khirodkar, Egor Zakharov, Timur Bagautdinov, Lei Xiao, Zhaoen Su, Shunsuke Saito, Xiaogang Jin, Junxuan Li</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present GenLCA, a diffusion-based generative model for generating and editing photorealistic full-body avatars from text and image inputs. The generated avatars are faithful to the inputs, while supporting high-fidelity facial and full-body animations. The core idea is a novel paradigm that enables training a full-body 3D diffusion model from partially observable 2D data, allowing the training dataset to scale to millions of real-world videos. This scalability contributes to the superior photorealism and generalizability of GenLCA. Specifically, we scale up the dataset by repurposing a pretrained feed-forward avatar reconstruction model as an animatable 3D tokenizer, which encodes unstructured video frames into structured 3D tokens. However, most real-world videos only provide partial observations of body parts, resulting in excessive blurring or transparency artifacts in the 3D tokens. To address this, we propose a novel visibility-aware diffusion training strategy that replaces invalid regions with learnable tokens and computes losses only over valid regions. We then train a flow-based diffusion model on the token dataset, inherently maintaining the photorealism and animatability provided by the pretrained avatar reconstruction model. Our approach effectively enables the use of large-scale real-world video data to train a diffusion model natively in 3D. We demonstrate the efficacy of our method through diverse and high-fidelity generation and editing results, outperforming existing solutions by a large margin. The project page is available at https://onethousandwu.com/GenLCA-Page.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07273</guid>
|
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models</title>
|
<title>CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation</title>
|
||||||
<link>https://arxiv.org/abs/2604.06912</link>
|
<link>https://arxiv.org/abs/2511.16428</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuheng Shi, Xiaohuan Pei, Linfeng Wen, Minjing Dong, Chang Xu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism with visually redundant tokens, severely bottlenecking inference throughput while ignoring spatial sparsity and query intent. To overcome this, we propose Q-Zoom, a query-aware adaptive high-resolution perception framework that operates in an efficient coarse-to-fine manner. First, a lightweight Dynamic Gating Network safely bypasses high-resolution processing when coarse global features suffice. Second, for queries demanding fine-grained perception, a Self-Distilled Region Proposal Network (SD-RPN) precisely localizes the task-relevant Region-of-Interest (RoI) directly from intermediate feature spaces. To optimize these modules efficiently, the gating network uses a consistency-aware generation strategy to derive deterministic routing labels, while the SD-RPN employs a fully self-supervised distillation paradigm. A continuous spatio-temporal alignment scheme and targeted fine-tuning then seamlessly fuse the dense local RoI with the coarse global layout. Extensive experiments demonstrate that Q-Zoom establishes a dominant Pareto frontier. Using Qwen2.5-VL-7B as a primary testbed, Q-Zoom accelerates inference by 2.52 times on Document & OCR benchmarks and 4.39 times in High-Resolution scenarios while matching the baseline's peak accuracy. Furthermore, when configured for maximum perceptual fidelity, Q-Zoom surpasses the baseline's peak performance by 1.1% and 8.1% on these respective benchmarks. These robust improvements transfer seamlessly to Qwen3-VL, LLaVA, and emerging RL-based thinking-with-image models. Project page is available at https://yuhengsss.github.io/Q-Zoom/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samer Abualhanud, Christian Grannemann, Max Mehltretter</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Self-supervised surround-view depth estimation enables dense, low-cost 3D perception with a 360° field of view from multiple minimally overlapping images. Yet, most existing methods suffer from depth estimates that are inconsistent across overlapping images. To address this limitation, we propose a novel geometry-guided method for calibrated, time-synchronized multi-camera rigs that predicts dense metric depth. Our approach targets two main sources of inconsistency: the limited receptive field in border regions of single-image depth estimation, and the difficulty of correspondence matching. We mitigate these two issues by extending the receptive field across views and restricting cross-view attention to a small neighborhood. To this end, we establish the neighborhood relationships between images by mapping the image-specific feature positions onto a shared cylinder. Based on the cylindrical positions, we apply an explicit spatial attention mechanism, with non-learned weighting, that aggregates features across images according to their distances on the cylinder. The modulated features are then decoded into a depth map for each view. Evaluated on the DDAD and nuScenes datasets, our method improves both cross-view depth consistency and overall depth accuracy compared with state-of-the-art approaches. Code is available at https://abualhanud.github.io/CylinderDepthPage.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06912</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2511.16428</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization</title>
|
<title>Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images</title>
|
||||||
<link>https://arxiv.org/abs/2604.07343</link>
|
<link>https://arxiv.org/abs/2604.07338</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response quality are prevalent, evaluating how well reward models account for individual user preferences remains an open challenge. To bridge this gap, we introduce Personalized RewardBench, a novel benchmark designed to rigorously assess reward models' capacity to model personalized preferences. We construct chosen and rejected response pairs based on strict adherence to (or violation of) user-specific rubrics, ensuring that preference distinctions are uniquely tailored to the individual. In particular, human evaluations confirm that the primary discriminative factor between pairs is strictly personal preference, with both responses maintaining high general quality (e.g., correctness, relevance and helpfulness). Extensive testing reveals that existing state-of-the-art reward models struggle significantly with personalization, peaking at an accuracy of just 75.94%. Crucially, because an effective reward model benchmark should predict a reward model's performance on downstream tasks, we conduct experiments demonstrating that our benchmark exhibits a significantly higher correlation with downstream performance in both Best-of-N (BoN) sampling and Proximal Policy Optimization (PPO) compared to existing baselines. These findings establish Personalized RewardBench as a robust and accurate proxy for evaluating reward models' performance in downstream applications.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07338.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuechen Jiang, Enze Zhang, Md Mohsinul Kabir, Qianqian Xie, Stavroula Golfomitsou, Konstantinos Arvanitis, Sophia Ananiadou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in vision-language models (VLMs) have improved image captioning for cultural heritage. However, inferring structured cultural metadata (e.g., creator, origin, period) from visual input remains underexplored. We introduce a multi-category, cross-cultural benchmark for this task and evaluate VLMs using an LLM-as-Judge framework that measures semantic alignment with reference annotations. To assess cultural reasoning, we report exact-match, partial-match, and attribute-level accuracy across cultural regions. Results show that models capture fragmented signals and exhibit substantial performance variation across cultures and metadata types, leading to inconsistent and weakly grounded predictions. These findings highlight the limitations of current VLMs in structured cultural metadata inference beyond visual perception.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07343</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07338</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MoRight: Motion Control Done Right</title>
|
<title>POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP</title>
|
||||||
<link>https://arxiv.org/abs/2604.07348</link>
|
<link>https://arxiv.org/abs/2604.06938</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaowei Liu, Xuanchi Ren, Tianchang Shen, Huan Ling, Saurabh Gupta, Shenlong Wang, Sanja Fidler, Jun Gao</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangled motion control, allowing users to separately control the object motion and adjust camera viewpoint; and (2) motion causality, ensuring that user-driven actions trigger coherent reactions from other objects rather than merely displacing pixels. Existing methods fall short on both fronts: they entangle camera and object motion into a single tracking signal and treat motion as kinematic displacement without modeling causal relationships between object motion. We introduce MoRight, a unified framework that addresses both limitations through disentangled motion modeling. Object motion is specified in a canonical static-view and transferred to an arbitrary target camera viewpoint via temporal cross-view attention, enabling disentangled camera and object control. We further decompose motion into active (user-driven) and passive (consequence) components, training the model to learn motion causality from data. At inference, users can either supply active motion and MoRight predicts consequences (forward reasoning), or specify desired passive outcomes and MoRight recovers plausible driving actions (inverse reasoning), all while freely adjusting the camera viewpoint. Experiments on three benchmarks demonstrate state-of-the-art performance in generation quality, motion controllability, and interaction awareness.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06938.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiyun Won, Heemin Yang, Woohyeok Kim, Jungseul Ok, Sunghyun Cho</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent work has explored optimizing image signal processing (ISP) pipelines for various tasks by composing predefined modules and adapting them to task-specific objectives. However, jointly optimizing module sequences and parameters remains challenging. Existing approaches rely on neural architecture search (NAS) or step-wise reinforcement learning (RL), but NAS suffers from a training-inference mismatch, while step-wise RL leads to unstable training and high computational overhead due to stage-wise decision-making. We propose POS-ISP, a sequence-level RL framework that formulates modular ISP optimization as a global sequence prediction problem. Our method predicts the entire module sequence and its parameters in a single forward pass and optimizes the pipeline using a terminal task reward, eliminating the need for intermediate supervision and redundant executions. Experiments across multiple downstream tasks show that POS-ISP improves task performance while reducing computational cost, highlighting sequence-level optimization as a stable and efficient paradigm for task-aware ISP. The project page is available at https://w1jyun.github.io/POS-ISP</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07348</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.06938</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Fast Spatial Memory with Elastic Test-Time Training</title>
|
<title>GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents</title>
|
||||||
<link>https://arxiv.org/abs/2604.07350</link>
|
<link>https://arxiv.org/abs/2604.07429</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07350.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqiao Ma, Xueyang Yu, Haoyu Zhen, Yuncong Yang, Joyce Chai, Chuang Gan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically instantiated with a single large chunk spanning the full input sequence, falling short of the broader goal of handling arbitrarily long sequences in a single pass. We propose Elastic Test-Time Training inspired by elastic weight consolidation, that stabilizes LaCT fast-weight updates with a Fisher-weighted elastic prior around a maintained anchor state. The anchor evolves as an exponential moving average of past fast weights to balance stability and plasticity. Based on this updated architecture, we introduce Fast Spatial Memory (FSM), an efficient and scalable model for 4D reconstruction that learns spatiotemporal representations from long observation sequences and renders novel view-time combinations. We pre-trained FSM on large-scale curated 3D/4D data to capture the dynamics and semantics of complex spatial environments. Extensive experiments show that FSM supports fast adaptation over long sequences and delivers high-quality 3D/4D reconstruction with smaller chunks and mitigating the camera-interpolation shortcut. Overall, we hope to advance LaCT beyond the bounded single-chunk setting toward robust multi-chunk adaptation, a necessary step for generalization to genuinely longer sequences, while substantially alleviating the activation-memory bottleneck.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07429.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingyu Ouyang, Siyuan Hu, Kevin Qinghong Lin, Hwee Tou Ng, Mike Zheng Shou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mistakes. Video games offer an ideal testbed with rich visual observations and closed-loop interaction, demanding fine-grained perception, long-horizon planning, and precise control. However, systematically evaluating these capabilities is currently hindered by heterogeneous action interfaces and heuristic verification. To this end, we introduce GameWorld, a benchmark designed for standardized and verifiable evaluation of MLLMs as generalist game agents in browser environments. Two game agent interfaces are studied: (i) computer-use agents that directly emit keyboard and mouse controls, and (ii) generalist multimodal agents that act in a semantic action space via deterministic Semantic Action Parsing. GameWorld contains 34 diverse games and 170 tasks, each paired with state-verifiable metrics for outcome-based evaluation. The results across 18 model-interface pairs suggest that even the best performing agent is far from achieving human capabilities on video games. Extensive experiments of repeated full-benchmark reruns demonstrate the robustness of the benchmark, while further studies on real-time interaction, context-memory sensitivity, and action validity expose more challenges ahead for game agents. Together, by offering a standardized, verifiable, and reproducible evaluation framework, GameWorld lays a robust foundation for advancing research on multimodal game agents and beyond. The project page is at https://gameworld-bench.github.io.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07350</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07429</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching</title>
|
<title>Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference</title>
|
||||||
<link>https://arxiv.org/abs/2604.06757</link>
|
<link>https://arxiv.org/abs/2604.07394</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06757.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qisheng Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts, and editing instructions, can be unified into a single visual representation. We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. To support this, we introduce VisPrompt-5M, a large-scale dataset of 5 million visual prompt pairs spanning diverse tasks including physics-aware force dynamics and trajectory prediction, alongside VP-Bench, a rigorously curated benchmark assessing instruction faithfulness, spatial precision, visual realism, and content consistency. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance across all unified generation tasks, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07394.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8timesA800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to 2.8times and 2.0times in the prefill and decode stages.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06757</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07394</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders</title>
|
<title>OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence</title>
|
||||||
<link>https://arxiv.org/abs/2604.07340</link>
|
<link>https://arxiv.org/abs/2604.07296</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07340.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Teng Li, Ziyuan Huang, Cong Chen, Yangfu Li, Yuanhuiyi Lyu, Dandan Zheng, Chunhua Shen, Jun Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this strategy often leads to latent representation collapse, which degrades generative performance. Instead of relying on increasingly complex architectures or multi-stage training schemes, TC-AE addresses this challenge from the perspective of the token space, the key bridge between pixels and image latents, through two complementary innovations: Firstly, we study token number scaling by adjusting the patch size in ViT under a fixed latent budget, and identify aggressive token-to-latent compression as the key factor that limits effective scaling. To address this issue, we decompose token-to-latent compression into two stages, reducing structural information loss and enabling effective token number scaling for generation. Secondly, to further mitigate latent representation collapse, we enhance the semantic structure of image tokens via joint self-supervised training, leading to more generative-friendly latents. With these designs, TC-AE achieves substantially improved reconstruction and generative performance under deep compression. We hope our research will advance ViT-based tokenizer for visual generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07296.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianhui Liu, Haoze Sun, Wenbo Li, Yanbing Zhang, Rui Yang, Zhiliang Zhu, Yijun Yang, Shenghe Zheng, Nan Jiang, Jiaxiu Jiang, Haoyang Huang, Tien-Tsin Wong, Nan Duan, Xiaojuan Qi</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Spatial understanding is a fundamental cornerstone of human-level intelligence. Nonetheless, current research predominantly focuses on domain-specific data production, leaving a critical void: the absence of a principled, open-source engine capable of fully unleashing the potential of high-quality spatial data. To bridge this gap, we elucidate the design principles of a robust data generation system and introduce OpenSpatial -- an open-source data engine engineered for high quality, extensive scalability, broad task diversity, and optimized efficiency. OpenSpatial adopts 3D bounding boxes as the fundamental primitive to construct a comprehensive data hierarchy across five foundational tasks: Spatial Measurement (SM), Spatial Relationship (SR), Camera Perception (CP), Multi-view Consistency (MC), and Scene-Aware Reasoning (SAR). Leveraging this scalable infrastructure, we curate OpenSpatial-3M, a large-scale dataset comprising 3 million high-fidelity samples. Extensive evaluations demonstrate that versatile models trained on our dataset achieve state-of-the-art performance across a wide spectrum of spatial reasoning benchmarks. Notably, the best-performing model exhibits a substantial average improvement of 19 percent, relatively. Furthermore, we provide a systematic analysis of how data attributes influence spatial perception. By open-sourcing both the engine and the 3M-scale dataset, we provide a robust foundation to accelerate future research in spatial intelligence.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07340</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07296</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling</title>
|
<title>HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents</title>
|
||||||
<link>https://arxiv.org/abs/2604.06916</link>
|
<link>https://arxiv.org/abs/2604.07430</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06916.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignment gains. However, scaling rollouts on large-scale foundational diffusion models (e.g., FLUX.1-12B) imposes a heavy computational burden. To alleviate this bottleneck, we explore the integration of FP4 quantization into Diffusion RL rollouts. Yet, we identify that naive quantized pipelines inherently introduce risks of performance degradation. To overcome this dilemma between efficiency and training integrity, we propose Sol-RL (Speed-of-light RL), a novel FP4-empowered Two-stage Reinforcement Learning framework. First, we utilize high-throughput NVFP4 rollouts to generate a massive candidate pool and extract a highly contrastive subset. Second, we regenerate these selected samples in BF16 precision and optimize the policy exclusively on them. By decoupling candidate exploration from policy optimization, Sol-RL integrates the algorithmic mechanisms of rollout scaling with the system-level throughput gains of NVFP4. This synergistic algorithm-hardware design effectively accelerates the rollout phase while reserving high-fidelity samples for optimization. We empirically demonstrate that our framework maintains the training integrity of BF16 precision pipeline while fully exploiting the throughput gains enabled by FP4 arithmetic. Extensive experiments across SANA, FLUX.1, and SD3.5-L substantiate that our approach delivers superior alignment performance across multiple metrics while accelerating training convergence by up to 4.64times, unlocking the power of massive rollout scaling at a fraction of the cost.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07430.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tencent Robotics X, HY Vision Team, Xumin Yu, Zuyan Liu, Ziyi Wang, He Zhang, Yongming Rao, Fangfu Liu, Yani Zhang, Ruowen Zhao, Oran Wang, Yves Liang, Haitao Lin, Minghui Wang, Yubo Dong, Kevin Cheng, Bolin Ni, Rui Huang, Han Hu, Zhengyou Zhang, Linus, Shunyu Yao</p><p><b>Upvotes:</b> 126</p><p><b>Summary:</b> We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Vision-Language Models (VLMs) and the demands of embodied agents, our models are developed to enhance the core capabilities required by embodied intelligence: spatial and temporal visual perception, alongside advanced embodied reasoning for prediction, interaction, and planning. The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning. To support the fine-grained visual perception essential for embodied tasks, we adopt a Mixture-of-Transformers (MoT) architecture to enable modality-specific computing. By incorporating latent tokens, this design effectively enhances the perceptual representation of the models. To improve reasoning capabilities, we introduce an iterative, self-evolving post-training paradigm. Furthermore, we employ on-policy distillation to transfer the advanced capabilities of the large model to the smaller variant, thereby maximizing the performance potential of the compact model. Extensive evaluations across 22 benchmarks, spanning visual perception, spatial reasoning, and embodied understanding, demonstrate the effectiveness of our approach. Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro. In downstream robot control experiments, we leverage our robust VLM foundation to train an effective Vision-Language-Action (VLA) model, achieving compelling results in real-world physical evaluations. Code and models are open-sourced at https://github.com/Tencent-Hunyuan/HY-Embodied.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.06916</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07430</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling</title>
|
<title>Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability</title>
|
||||||
<link>https://arxiv.org/abs/2604.07209</link>
|
<link>https://arxiv.org/abs/2604.06628</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Hujun Bao, Hongjia Zhai, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xianbin Liu, Xiaojun Xiang, Xiaoyu Zhang, Xinyu Chen, Yifu Wang, Yipeng Chen, Zhenzhou Fan, Zhewen Le, Zhichao Ye, Ziqiang Zhao</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06628.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu</p><p><b>Upvotes:</b> 152</p><p><b>Summary:</b> A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that cross-domain generalization is not absent but conditional, jointly shaped by optimization dynamics, training data, and base-model capability. Some reported failures are under-optimization artifacts: cross-domain performance first degrades before recovering and improving with extended training (a dip-and-recovery pattern), so shorttraining checkpoints can underestimate generalization. Data quality and structure both matter: low-quality solutions broadly hurt generalization,while verified long-CoT traces yield consistent cross-domain gains. Model capability is essential: stronger models internalize transferable procedural patterns (e.g., backtracking) even from a toy arithmetic game, while weaker ones imitate surface verbosity. This generalization is asymmetric, however: reasoning improves while safety degrades, reframing the question from whether reasoning SFT generalizes to under what conditions and at what cost.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07209</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.06628</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MARS: Enabling Autoregressive Models Multi-Token Generation</title>
|
<title>RewardFlow: Generate Images by Optimizing What You Reward</title>
|
||||||
<link>https://arxiv.org/abs/2604.07023</link>
|
<link>https://arxiv.org/abs/2604.08536</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07023.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08536.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Onkar Susladkar, Dong-Hwan Jang, Tushar Prakash, Adheesh Juvekar, Vedant Shah, Ayush Barik, Nabeel Bashir, Muntasir Wahed, Ritish Shrirao, Ismini Lourentzou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic alignment, perceptual fidelity, localized grounding, object consistency, and human preference, and further introduces a differentiable VQA-based reward that provides fine-grained semantic supervision through language-vision reasoning. To coordinate these heterogeneous objectives, we design a prompt-aware adaptive policy that extracts semantic primitives from the instruction, infers edit intent, and dynamically modulates reward weights and step sizes throughout sampling. Across several image editing and compositional generation benchmarks, RewardFlow delivers state-of-the-art edit fidelity and compositional alignment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.07023</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08536</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning</title>
|
<title>ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2604.04746</link>
|
<link>https://arxiv.org/abs/2604.08064</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Zhang, Junjiao Tian, Zhipeng Fan, Kunpeng Li, Jialiang Wang, Weifeng Chen, Markos Georgopoulos, Felix Juefei-Xu, Yuxiang Bao, Julian McAuley, Manling Li, Zecheng He</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on text-image interleaved datasets also imagine the chain of intermediate states? In this paper, we introduce process-driven image generation, a multi-step paradigm that decomposes synthesis into an interleaved reasoning trajectory of thoughts and actions. Rather than generating images in a single step, our approach unfolds across multiple iterations, each consisting of 4 stages: textual planning, visual drafting, textual reflection, and visual refinement. The textual reasoning explicitly conditions how the visual state should evolve, while the generated visual intermediate in turn constrains and grounds the next round of textual reasoning. A core challenge of process-driven generation stems from the ambiguity of intermediate states: how can models evaluate each partially-complete image? We address this through dense, step-wise supervision that maintains two complementary constraints: for the visual intermediate states, we enforce the spatial and semantic consistency; for the textual intermediate states, we preserve the prior visual knowledge while enabling the model to identify and correct prompt-violating elements. This makes the generation process explicit, interpretable, and directly supervisable. To validate proposed method, we conduct experiments under various text-to-image generation benchmarks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chonghan Qin, Xiachong Feng, Weitao Ma, Xiaocheng Feng, Lingpeng Kong</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically apply learned procedures or avoid failed actions without explicit reminders. We introduce ImplicitMemBench, the first systematic benchmark evaluating implicit memory through three cognitively grounded constructs drawn from standard cognitive-science accounts of non-declarative memory: Procedural Memory (one-shot skill acquisition after interference), Priming (theme-driven bias via paired experimental/control instances), and Classical Conditioning (Conditioned Stimulus--Unconditioned Stimulus (CS--US) associations shaping first decisions). Our 300-item suite employs a unified Learning/Priming-Interfere-Test protocol with first-attempt scoring. Evaluation of 17 models reveals severe limitations: no model exceeds 66% overall, with top performers DeepSeek-R1 (65.3%), Qwen3-32B (64.1%), and GPT-5 (63.0%) far below human baselines. Analysis uncovers dramatic asymmetries (inhibition 17.6% vs. preference 75.0%) and universal bottlenecks requiring architectural innovations beyond parameter scaling. ImplicitMemBench reframes evaluation from "what agents recall" to "what they automatically enact".</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.04746</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08064</guid>
|
||||||
<pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08340</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08340.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruizhi Zhang, Ye Huang, Yuangang Pan, Chuanfu Shen, Zhilin Liu, Ting Xie, Wen Li, Lixin Duan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While Vision-Language Models (VLMs) have achieved remarkable progress in static visual understanding, their deployment in complex 3D embodied environments remains severely limited. Existing benchmarks suffer from four critical deficiencies: (1) passive perception tasks circumvent interactive dynamics; (2) simplified 2D environments fail to assess depth perception; (3) privileged state leakage bypasses genuine visual processing; and (4) human evaluation is prohibitively expensive and unscalable. We introduce PokeGym, a visually-driven long-horizon benchmark instantiated within Pokemon Legends: Z-A, a visually complex 3D open-world Role-Playing Game. PokeGym enforces strict code-level isolation: agents operate solely on raw RGB observations while an independent evaluator verifies success via memory scanning, ensuring pure vision-based decision-making and automated, scalable assessment. The benchmark comprises 30 tasks (30-220 steps) spanning navigation, interaction, and mixed scenarios, with three instruction granularities (Visual-Guided, Step-Guided, Goal-Only) to systematically deconstruct visual grounding, semantic reasoning, and autonomous exploration capabilities. Our evaluation reveals a key limitation of current VLMs: physical deadlock recovery, rather than high-level planning, constitutes the primary bottleneck, with deadlocks showing a strong negative correlation with task success. Furthermore, we uncover a metacognitive divergence: weaker models predominantly suffer from Unaware Deadlocks (oblivious to entrapment), whereas advanced models exhibit Aware Deadlocks (recognizing entrapment yet failing to recover). These findings highlight the need to integrate explicit spatial intuition into VLM architectures. The code and benchmark will be available on GitHub.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08340</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08503</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08503.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ying Shen, Jerry Xiong, Tianjiao Yu, Ismini Lourentzou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However, emerging evidence suggests that simply scaling data and model size does not endow these systems with an understanding of the underlying physical laws that govern real-world dynamics. Existing approaches often fail to capture or enforce such physical consistency, resulting in unrealistic motion and dynamics. In his work, we investigate whether integrating the inference of latent physical properties directly into the video generation process can equip models with the ability to produce physically plausible videos. To this end, we propose Phantom, a Physics-Infused Video Generation model that jointly models the visual content and latent physical dynamics. Conditioned on observed video frames and inferred physical states, Phantom jointly predicts latent physical dynamics and generates future video frames. Phantom leverages a physics-aware video representation that serves as an abstract yet informaive embedding of the underlying physics, facilitating the joint prediction of physical dynamics alongside video content without requiring an explicit specification of a complex set of physical dynamics and properties. By integrating the inference of physical-aware video representation directly into the video generation process, Phantom produces video sequences that are both visually realistic and physically consistent. Quantitative and qualitative results on both standard video generation and physics-aware benchmarks demonstrate that Phantom not only outperforms existing methods in terms of adherence to physical dynamics but also delivers competitive perceptual fidelity.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08503</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08124</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuzhan Hao, Wenfeng Feng, Guochao Jiang, Guofeng Quan, Guohua Liu, Yuewei Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents often rely on a process of stochastic exploration guided by carefully crafted outcome rewards, leading to inefficient reasoning trajectories and unstable training. To address these issues, we propose a novel framework, Hierarchical Experience (HiExp), to enhance the performance and training stability of search agents. Specifically, we extract empirical knowledge through contrastive analysis and a multi-level clustering mechanism, transforming raw reasoning trajectories into hierarchical experience knowledge. By leveraging experience-aligned training, we effectively regularize stochastic exploration, evolving it into a strategic and experience-driven search process. Extensive evaluations on multiple complex agentic search and mathematical reasoning benchmarks demonstrate that our approach not only achieves substantial performance gains but also exhibits strong cross-task and cross-algorithm generalization.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08124</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>On the Global Photometric Alignment for Low-Level Vision</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08172</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08172.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingjia Li, Tianle Du, Hainuo Wang, Qiming Hu, Xiaojie Guo</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Supervised low-level vision models rely on pixel-wise losses against paired references, yet paired training sets exhibit per-pair photometric inconsistency, say, different image pairs demand different global brightness, color, or white-balance mappings. This inconsistency enters through task-intrinsic photometric transfer (e.g., low-light enhancement) or unintended acquisition shifts (e.g., de-raining), and in either case causes an optimization pathology. Standard reconstruction losses allocate disproportionate gradient budget to conflicting per-pair photometric targets, crowding out content restoration. In this paper, we investigate this issue and prove that, under least-squares decomposition, the photometric and structural components of the prediction-target residual are orthogonal, and that the spatially dense photometric component dominates the gradient energy. Motivated by this analysis, we propose Photometric Alignment Loss (PAL). This flexible supervision objective discounts nuisance photometric discrepancy via closed-form affine color alignment while preserving restoration-relevant supervision, requiring only covariance statistics and tiny matrix inversion with negligible overhead. Across 6 tasks, 16 datasets, and 16 architectures, PAL consistently improves metrics and generalization. The implementation is in the appendix.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08172</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors</title>
|
||||||
|
<link>https://arxiv.org/abs/2601.20524</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.20524.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent approaches leverage vision-language models (VLMs), such as CLIP, to transfer high-level concept knowledge, methods based on purely vision foundation models (VFMs), like DINOv2, have lagged behind in performance. We argue that this gap stems from two practical issues: (i) limited diversity in existing auxiliary anomaly detection datasets and (ii) overly shallow VFM adaptation strategies. To address both challenges, we propose AnomalyVFM, a general and effective framework that turns any pretrained VFM into a strong zero-shot anomaly detector. Our approach combines a robust three-stage synthetic dataset generation scheme with a parameter-efficient adaptation mechanism, utilising low-rank feature adapters and a confidence-weighted pixel loss. Together, these components enable modern VFMs to substantially outperform current state-of-the-art methods. More specifically, with RADIO as a backbone, AnomalyVFM achieves an average image-level AUROC of 94.1% across 9 diverse datasets, surpassing previous methods by significant 3.3 percentage points. Project Page: https://maticfuc.github.io/anomaly_vfm/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2601.20524</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Small Vision-Language Models are Smart Compressors for Long Video Understanding</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08120</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Fei, Jun Chen, Zechun Liu, Yunyang Xiong, Chong Zhou, Wei Wen, Junlin Han, Mingchen Zhuge, Saksham Suri, Qi Qian, Shuming Liu, Lemeng Wu, Raghuraman Krishnamoorthi, Vikas Chandra, Mohamed Elhoseiny, Chenchen Zhu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse sampling or uniform pooling, blindly sacrifice fidelity by discarding decisive moments and wasting bandwidth on irrelevant backgrounds. We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding. Tempo leverages a Small Vision-Language Model (SVLM) as a local temporal compressor, casting token reduction as an early cross-modal distillation process to generate compact, intent-aligned representations in a single forward pass. To enforce strict budgets without breaking causality, we introduce Adaptive Token Allocation (ATA). Exploiting the SVLM's zero-shot relevance prior and semantic front-loading, ATA acts as a training-free O(1) dynamic router. It allocates dense bandwidth to query-critical segments while compressing redundancies into minimal temporal anchors to maintain the global storyline. Extensive experiments show our 6B architecture achieves state-of-the-art performance with aggressive dynamic compression (0.5-16 tokens/frame). On the extreme-long LVBench (4101s), Tempo scores 52.3 under a strict 8K visual budget, outperforming GPT-4o and Gemini 1.5 Pro. Scaling to 2048 frames reaches 53.7. Crucially, Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency rather than greedily padded context windows.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08120</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Lighting-grounded Video Generation with Renderer-based Agent Reasoning</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.07966</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07966.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqi Cai, Taoyu Yang, Zheng Chang, Si Li, Han Jiang, Shuchen Weng, Boxin Shi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Diffusion models have achieved remarkable progress in video generation, but their controllability remains a major limitation. Key scene factors such as layout, lighting, and camera trajectory are often entangled or only weakly modeled, restricting their applicability in domains like filmmaking and virtual production where explicit scene control is essential. We present LiVER, a diffusion-based framework for scene-controllable video generation. To achieve this, we introduce a novel framework that conditions video synthesis on explicit 3D scene properties, supported by a new large-scale dataset with dense annotations of object layout, lighting, and camera parameters. Our method disentangles these properties by rendering control signals from a unified 3D representation. We propose a lightweight conditioning module and a progressive training strategy to integrate these signals into a foundational video diffusion model, ensuring stable convergence and high fidelity. Our framework enables a wide range of applications, including image-to-video and video-to-video synthesis where the underlying 3D scene is fully editable. To further enhance usability, we develop a scene agent that automatically translates high-level user instructions into the required 3D control signals. Experiments show that LiVER achieves state-of-the-art photorealism and temporal consistency while enabling precise, disentangled control over scene factors, setting a new standard for controllable video generation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07966</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08362</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08362.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Chen, Ruoxi Xu, Boxi Cao, Ruotong Pan, Yunfei Zhang, Yifei Hu, Yong Du, Tingting Gao, Yaojie Lu, Yingfei Sun, Xianpei Han, Le Sun, Xiangyu Wu, Hongyu Lin</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenarios, narrow action spaces, or synthetic data, failing to capture the holistic nature of authentic human behavior. To bridge this gap, we introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data, integrating long-horizon, cross-scenario, and heterogeneous behavioral patterns into a unified framework. Based on this benchmark, we first provide empirical evidence that previous datasets with isolated scenarios suffer from tunnel vision, whereas real-world decision-making relies on long-term, cross-scenario causal chains. Extensive evaluations of state-of-the-art LLMs reveal that current models struggle to accurately simulate these complex behaviors, with performance plateauing even as context windows expand. Crucially, a systematic comparison between simulated and authentic behaviors uncovers a fundamental structural bias: LLMs tend to converge toward a positive average person, exhibiting hyper-activity, persona homogenization, and a Utopian bias. This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08362</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>ViVa: A Video-Generative Value Model for Robot Reinforcement Learning</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08168</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jindi Lv, Hao Li, Jie Li, Yifei Nie, Fankun Kong, Yang Wang, Xiaofeng Wang, Zheng Zhu, Chaojun Ni, Qiuping Deng, Hengtao Li, Jiancheng Lv, Guan Huang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and delayed feedback. Reinforcement learning addresses this via value functions, which assess task progress and guide policy improvement. However, existing value models built on vision-language models (VLMs) struggle to capture temporal dynamics, undermining reliable value estimation in long-horizon tasks. In this paper, we propose ViVa, a video-generative value model that repurposes a pretrained video generator for value estimation. Taking the current observation and robot proprioception as input, ViVa jointly predicts future proprioception and a scalar value for the current state. By leveraging the spatiotemporal priors of a pretrained video generator, our approach grounds value estimation in anticipated embodiment dynamics, moving beyond static snapshots to intrinsically couple value with foresight. Integrated into RECAP, ViVa delivers substantial improvements on real-world box assembly. Qualitative analysis across all three tasks confirms that ViVa produces more reliable value signals, accurately reflecting task progress. By leveraging spatiotemporal priors from video corpora, ViVa also generalizes to novel objects, highlighting the promise of video-generative models for value estimation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08168</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08544</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08544.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunsong Zhou, Hangxu Liu, Xuekun Jiang, Xing Shen, Yuanzhen Zhou, Hui Wang, Baole Fang, Yang Tian, Mulin Yu, Qiaojun Yu, Li Ma, Hengjie Li, Hanqing Wang, Jia Zeng, Jiangmiao Pang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that far exceed the variability of rigids. Although simulation promises relief from the cost of real-world data acquisition, prevailing sim-to-real pipelines remain rooted in rigid-body abstractions, producing mismatched geometry, fragile soft dynamics, and motion primitives poorly suited for cloth interaction. We posit that simulation fails not for being synthetic, but for being ungrounded. To address this, we introduce SIM1, a physics-aligned real-to-sim-to-real data engine that grounds simulation in the physical world. Given limited demonstrations, the system digitizes scenes into metric-consistent twins, calibrates deformable dynamics through elastic modeling, and expands behaviors via diffusion-based trajectory generation with quality filtering. This pipeline transforms sparse observations into scaled synthetic supervision with near-demonstration fidelity. Experiments show that policies trained on purely synthetic data achieve parity with real-data baselines at a 1:15 equivalence ratio, while delivering 90% zero-shot success and 50% generalization gains in real-world deployment. These results validate physics-aligned simulation as scalable supervision for deformable manipulation and a practical pathway for data-efficient policy learning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08544</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08526</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08526.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Johanna Karras, Yuanhao Wang, Yingwei Li, Ira Kemelmacher-Shlizerman</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Given a person and a garment image, virtual try-on (VTO) aims to synthesize a realistic image of the person wearing the garment, while preserving their original pose and identity. Although recent VTO methods excel at visualizing garment appearance, they largely overlook a crucial aspect of the try-on experience: the accuracy of garment fit -- for example, depicting how an extra-large shirt looks on an extra-small person. A key obstacle is the absence of datasets that provide precise garment and body size information, particularly for "ill-fit" cases, where garments are significantly too large or too small. Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size. In this paper, we take the first steps towards solving this open problem. We introduce FIT (Fit-Inclusive Try-on), a large-scale VTO dataset comprising over 1.13M try-on image triplets accompanied by precise body and garment measurements. We overcome the challenges of data collection via a scalable synthetic strategy: (1) We programmatically generate 3D garments using GarmentCode and drape them via physics simulation to capture realistic garment fit. (2) We employ a novel re-texturing framework to transform synthetic renderings into photorealistic images while strictly preserving geometry. (3) We introduce person identity preservation into our re-texturing model to generate paired person images (same person, different garments) for supervised training. Finally, we leverage our FIT dataset to train a baseline fit-aware virtual try-on model. Our data and results set the new state-of-the-art for fit-aware virtual try-on, as well as offer a robust benchmark for future research. We will make all data and code publicly available on our project page: https://johannakarras.github.io/FIT.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08526</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Structured Distillation of Web Agent Capabilities Enables Generalization</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.07776</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07776.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xing Han Lù, Siva Reddy</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These results demonstrate that structured trajectory synthesis from a single frontier teacher is sufficient to produce competitive, locally deployable web agents. Project page: https://agent-as-annotators.github.io</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07776</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08209</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiduo Jia, Muzhi Zhu, Hao Zhong, Mingyu Liu, Yuling Xi, Hao Chen, Bin Qin, Yongjie Yang, Zhenbo Luo, Chunhua Shen</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> To extend the reinforcement learning post-training paradigm to omni-modal models for concurrently bolstering video-audio understanding and collaborative reasoning, we propose OmniJigsaw, a generic self-supervised framework built upon a temporal reordering proxy task. Centered on the chronological reconstruction of shuffled audio-visual clips, this paradigm strategically orchestrates visual and auditory signals to compel cross-modal integration through three distinct strategies: Joint Modality Integration, Sample-level Modality Selection, and Clip-level Modality Masking. Recognizing that the efficacy of such proxy tasks is fundamentally tied to puzzle quality, we design a two-stage coarse-to-fine data filtering pipeline, which facilitates the efficient adaptation of OmniJigsaw to massive unannotated omni-modal data. Our analysis reveals a ``bi-modal shortcut phenomenon'' in joint modality integration and demonstrates that fine-grained clip-level modality masking mitigates this issue while outperforming sample-level modality selection. Extensive evaluations on 15 benchmarks show substantial gains in video, audio, and collaborative reasoning, validating OmniJigsaw as a scalable paradigm for self-supervised omni-modal learning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08209</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08539</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08539.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenbo Hu, Xin Chen, Yan Gao-Tian, Yihe Deng, Nanyun Peng, Kai-Wei Chang</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal generalist models remains heavily constrained by two primary challenges: the extreme variance in reward topologies across diverse visual tasks, and the inherent difficulty of balancing fine-grained perception with multi-step reasoning capabilities. To address these issues, we introduce Gaussian GRPO (G^2RPO), a novel RL training objective that replaces standard linear scaling with non-linear distributional matching. By mathematically forcing the advantage distribution of any given task to strictly converge to a standard normal distribution, N(0,1), G^2RPO theoretically ensures inter-task gradient equity, mitigates vulnerabilities to heavy-tail outliers, and offers symmetric update for positive and negative rewards. Leveraging the enhanced training stability provided by G^2RPO, we introduce two task-level shaping mechanisms to seamlessly balance perception and reasoning. First, response length shaping dynamically elicits extended reasoning chains for complex queries while enforce direct outputs to bolster visual grounding. Second, entropy shaping tightly bounds the model's exploration zone, effectively preventing both entropy collapse and entropy explosion. Integrating these methodologies, we present OpenVLThinkerV2, a highly robust, general-purpose multimodal model. Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08539</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>MolmoWeb: Open Visual Web Agent and Open Data for the Open Web</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08516</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08516.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tanmay Gupta, Piper Wolters, Zixian Ma, Peter Sushko, Rock Yuren Pang, Diego Llanes, Yue Yang, Taira Anderson, Boyuan Zheng, Zhongzheng Ren, Harsh Trivedi, Taylor Blanton, Caleb Ouellette, Winson Han, Ali Farhadi, Ranjay Krishna</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Web agents--autonomous systems that navigate and execute tasks on the web on behalf of users--have the potential to transform how people interact with the digital world. However, the most capable web agents today rely on proprietary models with undisclosed training data and recipes, limiting scientific understanding, reproducibility, and community-driven progress. We believe agents for the open web should be built in the open. To this end, we introduce (1) MolmoWebMix, a large and diverse mixture of browser task demonstrations and web-GUI perception data and (2) MolmoWeb, a family of fully open multimodal web agents. Specifically, MolmoWebMix combines over 100K synthetic task trajectories from multiple complementary generation pipelines with 30K+ human demonstrations, atomic web-skill trajectories, and GUI perception data, including referring expression grounding and screenshot question answering. MolmoWeb agents operate as instruction-conditioned visual-language action policies: given a task instruction and a webpage screenshot, they predict the next browser action, requiring no access to HTML, accessibility trees, or specialized APIs. Available in 4B and 8B size, on browser-use benchmarks like WebVoyager, Online-Mind2Web, and DeepShop, MolmoWeb agents achieve state-of-the-art results outperforming similar scale open-weight-only models such as Fara-7B, UI-Tars-1.5-7B, and Holo1-7B. MolmoWeb-8B also surpasses set-of-marks (SoM) agents built on much larger closed frontier models like GPT-4o. We further demonstrate consistent gains through test-time scaling via parallel rollouts with best-of-N selection, achieving 94.7% and 60.5% pass@4 (compared to 78.2% and 35.3% pass@1) on WebVoyager and Online-Mind2Web respectively. We will release model checkpoints, training data, code, and a unified evaluation harness to enable reproducibility and accelerate open research on web agents.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08516</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>DMax: Aggressive Parallel Decoding for dLLMs</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08302</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08302.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zigeng Chen, Gongfan Fang, Xinyin Ma, Ruonan Yu, Xinchao Wang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigates error accumulation in parallel decoding, enabling aggressive decoding parallelism while preserving generation quality. Unlike conventional masked dLLMs that decode through a binary mask-to-token transition, DMax reformulates decoding as a progressive self-refinement from mask embeddings to token embeddings. At the core of our approach is On-Policy Uniform Training, a novel training strategy that efficiently unifies masked and uniform dLLMs, equipping the model to recover clean tokens from both masked inputs and its own erroneous predictions. Building on this foundation, we further propose Soft Parallel Decoding. We represent each intermediate decoding state as an interpolation between the predicted token embedding and the mask embedding, enabling iterative self-revising in embedding space. Extensive experiments across a variety of benchmarks demonstrate the effectiveness of DMax. Compared with the original LLaDA-2.0-mini, our method improves TPF on GSM8K from 2.04 to 5.47 while preserving accuracy. On MBPP, it increases TPF from 2.71 to 5.86 while maintaining comparable performance. On two H200 GPUs, our model achieves an average of 1,338 TPS at batch size 1. Code is available at: https://github.com/czg1225/DMax</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08302</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08545</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shilin Yan, Jintao Tong, Hongwei Xue, Xiaojun Tang, Yangyang Wang, Kunyu Shi, Guannan Zhang, Ruixuan Li, Yixiong Zou</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> The advent of agentic multimodal models has empowered systems to actively interact with external environments. However, current agents suffer from a profound meta-cognitive deficit: they struggle to arbitrate between leveraging internal knowledge and querying external utilities. Consequently, they frequently fall prey to blind tool invocation, resorting to reflexive tool execution even when queries are resolvable from the raw visual context. This pathological behavior precipitates severe latency bottlenecks and injects extraneous noise that derails sound reasoning. Existing reinforcement learning protocols attempt to mitigate this via a scalarized reward that penalizes tool usage. Yet, this coupled formulation creates an irreconcilable optimization dilemma: an aggressive penalty suppresses essential tool use, whereas a mild penalty is entirely subsumed by the variance of the accuracy reward during advantage normalization, rendering it impotent against tool overuse. To transcend this bottleneck, we propose HDPO, a framework that reframes tool efficiency from a competing scalar objective to a strictly conditional one. By eschewing reward scalarization, HDPO maintains two orthogonal optimization channels: an accuracy channel that maximizes task correctness, and an efficiency channel that enforces execution economy exclusively within accurate trajectories via conditional advantage estimation. This decoupled architecture naturally induces a cognitive curriculum-compelling the agent to first master task resolution before refining its self-reliance. Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08545</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08224</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyu Zhou, Huacan Chai, Wenteng Chen, Zihan Guo, Rong Shan, Yuanyi Song, Tianyi Xu, Yingxuan Yang, Aofan Yu, Weiming Zhang, Congming Zheng, Jiachen Zhu, Zeyu Zheng, Zhuosheng Zhang, Xingyu Lou, Changwang Zhang, Zhihui Fu, Jun Wang, Weiwen Liu, Jianghao Lin, Weinan Zhang</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the model to recover internally are now externalized into memory stores, reusable skills, interaction protocols, and the surrounding harness that makes these modules reliable in practice. This paper reviews that shift through the lens of externalization. Drawing on the idea of cognitive artifacts, we argue that agent infrastructure matters not merely because it adds auxiliary components, but because it transforms hard cognitive burdens into forms that the model can solve more reliably. Under this view, memory externalizes state across time, skills externalize procedural expertise, protocols externalize interaction structure, and harness engineering serves as the unification layer that coordinates them into governed execution. We trace a historical progression from weights to context to harness, analyze memory, skills, and protocols as three distinct but coupled forms of externalization, and examine how they interact inside a larger agent system. We further discuss the trade-off between parametric and externalized capability, identify emerging directions such as self-evolving harnesses and shared agent infrastructure, and discuss open challenges in evaluation, governance, and the long-term co-evolution of models and external infrastructure. The result is a systems-level framework for explaining why practical agent progress increasingly depends not only on stronger models, but on better external cognitive infrastructure.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08224</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08455</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08455.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tongbo Chen, Zhengxi Lu, Zhan Xu, Guocheng Shao, Shaohan Zhao, Fei Tang, Yong Du, Kaitao Song, Yizhou Liu, Yuchen Yan, Wenqi Zhang, Xu Tan, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Personalized mobile agents that infer user preferences and calibrate proactive assistance hold great promise as everyday digital assistants, yet existing benchmarks fail to capture what this requires. Prior work evaluates preference recovery from static histories or intent prediction from fixed contexts. Neither tests whether an agent can elicit missing preferences through interaction, nor whether it can decide when to intervene, seek consent, or remain silent in a live GUI environment. We introduce KnowU-Bench, an online benchmark for personalized mobile agents built on a reproducible Android emulation environment, covering 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks. Unlike prior work that treats user preferences as static context, KnowU-Bench hides the user profile from the agent and exposes only behavioral logs, forcing genuine preference inference rather than context lookup. To support multi-turn preference elicitation, it instantiates an LLM-driven user simulator grounded in structured profiles, enabling realistic clarification dialogues and proactive consent handling. Beyond personalization, KnowU-Bench provides comprehensive evaluation of the complete proactive decision chain, including grounded GUI execution, consent negotiation, and post-rejection restraint, evaluated through a hybrid protocol combining rule-based verification with LLM-as-a-Judge scoring. Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions requiring user preference inference or intervention calibration, even for frontier models like Claude Sonnet 4.6. The core bottlenecks are not GUI navigation but preference acquisition and intervention calibration, exposing a fundamental gap between competent interface operation and trustworthy personal assistance.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08455</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LPM 1.0: Video-based Character Performance Model</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.07823</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07823.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ailing Zeng, Casper Yang, Chauncey Ge, Eddie Zhang, Garvey Xu, Gavin Lin, Gilbert Gu, Jeremy Pi, Leo Li, Mingyi Shi, Sheng Bi, Steven Tang, Thorn Hang, Tobey Guo, Vincent Li, Xin Tong, Yikang Li, Yuchen Sun, Yue, Zhao, Yuhan Lu, Yuwei Li, Zane Zhang, Zeshi Yang, Zi Ye</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Learning such performance from video is a promising alternative to traditional 3D pipelines. However, existing video models struggle to jointly achieve high expressiveness, real-time inference, and long-horizon identity stability, a tension we call the performance trilemma. Conversation is the most comprehensive performance scenario, as characters simultaneously speak, listen, react, and emote while maintaining identity over time. To address this, we present LPM 1.0 (Large Performance Model), focusing on single-person full-duplex audio-visual conversational performance. Concretely, we build a multimodal human-centric dataset through strict filtering, speaking-listening audio-video pairing, performance understanding, and identity-aware multi-reference extraction; train a 17B-parameter Diffusion Transformer (Base LPM) for highly controllable, identity-consistent performance through multimodal conditioning; and distill it into a causal streaming generator (Online LPM) for low-latency, infinite-length interaction. At inference, given a character image with identity-aware references, LPM 1.0 generates listening videos from user audio and speaking videos from synthesized audio, with text prompts for motion control, all at real-time speed with identity-stable, infinite-length generation. LPM 1.0 thus serves as a visual engine for conversational agents, live streaming characters, and game NPCs. To systematically evaluate this setting, we propose LPM-Bench, the first benchmark for interactive character performance. LPM 1.0 achieves state-of-the-art results across all evaluated dimensions while maintaining real-time inference.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.07823</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08364</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun, Yuanpeng Tu, Fei Shen, Weidong Zhang, Cairong Zhao, Jun Zhang</p><p><b>Upvotes:</b> 79</p><p><b>Summary:</b> In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We achieve this by leveraging the consistent text-to-image style mapping capability of current large generative models, which can generate images in the same style from a given style description. Building on this foundation, we curate a diverse and balanced prompt gallery with 170K style prompts and 400K content prompts, and generate a large-scale style dataset MegaStyle-1.4M via content-style prompt combinations. With MegaStyle-1.4M, we propose style-supervised contrastive learning to fine-tune a style encoder MegaStyle-Encoder for extracting expressive, style-specific representations, and we also train a FLUX-based style transfer model MegaStyle-FLUX. Extensive experiments demonstrate the importance of maintaining intra-style consistency, inter-style diversity and high-quality for style dataset, as well as the effectiveness of the proposed MegaStyle-1.4M. Moreover, when trained on MegaStyle-1.4M, MegaStyle-Encoder and MegaStyle-FLUX provide reliable style similarity measurement and generalizable style transfer, making a significant contribution to the style transfer community. More results are available at our project website https://jeoyal.github.io/MegaStyle/.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08364</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>ClawBench: Can AI Agents Complete Everyday Online Tasks?</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08523</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Zhang, Yubo Wang, Yipeng Zhu, Penghui Du, Junwen Miao, Xuan Lu, Wendong Xu, Yunzhuo Hao, Songcheng Cai, Xiaochen Wang, Huaisong Zhang, Xian Wu, Yi Lu, Minyi Lei, Kai Zou, Huifeng Yin, Ping Nie, Liang Chen, Dongfu Jiang, Wenhu Chen, Kelsey R. Allen</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework of 153 simple tasks that people need to accomplish regularly in their lives and work, spanning 144 live platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require demanding capabilities beyond existing benchmarks, such as obtaining relevant information from user-provided documents, navigating multi-step workflows across diverse platforms, and write-heavy operations like filling in many detailed forms correctly. Unlike existing benchmarks that evaluate agents in offline sandboxes with static pages, ClawBench operates on production websites, preserving the full complexity, dynamic nature, and challenges of real-world web interaction. A lightweight interception layer captures and blocks only the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 7 frontier models show that both proprietary and open-source models can complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%. Progress on ClawBench brings us closer to AI agents that can function as reliable general-purpose assistants.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08523</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08546</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyang Sun, Yu Chen, Xin Zhou, Xiaofan Li, Xiwu Chen, Dingkang Liang, Xiang Bai</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA , a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsistencies by selecting discriminative self- and cross-attention heads to derive a countable latent layout. It then refines this layout conservatively and modulates cross-attention to guide regeneration. On the introduced CountBench, NUMINA improves counting accuracy by up to 7.4% on Wan2.1-1.3B, and by 4.9% and 5.5% on 5B and 14B models, respectively. Furthermore, CLIP alignment is improved while maintaining temporal consistency. These results demonstrate that structural guidance complements seed search and prompt enhancement, offering a practical path toward count-accurate text-to-video diffusion. The code is available at https://github.com/H-EmbodVis/NUMINA.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08546</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SkillClaw: Let Skills Evolve Collectively with Agentic Evolver</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08377</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang, Yong Wang, Yiming Hu, Tongwen Huang, Xiangxiang Chu</p><p><b>Upvotes:</b> 143</p><p><b>Summary:</b> Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08377</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization</title>
|
||||||
|
<link>https://arxiv.org/abs/2604.08476</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.08476.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning quality: generated Chain-of-Thought (CoT) traces are frequently inconsistent with the final answer and poorly grounded in the visual evidence. We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own models trained with standard Group Relative Policy Optimization (GRPO). We characterize CoT reasoning quality along two complementary axes: "logical consistency" (does the CoT entail the final answer?) and "visual grounding" (does each reasoning step accurately describe objects, attributes, and spatial relationships in the image?). To address this, we propose Faithful GRPO (FGRPO), a variant of GRPO that enforces consistency and grounding as constraints via Lagrangian dual ascent. FGRPO incorporates batch-level consistency and grounding constraints into the advantage computation within a group, adaptively adjusting the relative importance of constraints during optimization. We evaluate FGRPO on Qwen2.5-VL-7B and 3B backbones across seven spatial datasets. Our results show that FGRPO substantially improves reasoning quality, reducing the inconsistency rate from 24.5% to 1.7% and improving visual grounding scores by +13%. It also improves final answer accuracy over simple GRPO, demonstrating that faithful reasoning enables better answers.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.08476</guid>
|
||||||
|
<pubDate>Thu, 09 Apr 2026 17:15:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user