bot: update RSS feed
This commit is contained in:
github-actions[bot]
456
feed.xml
456
feed.xml
@@ -7,377 +7,307 @@
|
|||||||
<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>Mon, 18 May 2026 00:17:57 +0000</lastBuildDate>
|
<lastBuildDate>Tue, 19 May 2026 00:21:25 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning</title>
|
<title>Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism</title>
|
||||||
<link>https://arxiv.org/abs/2605.13852</link>
|
<link>https://arxiv.org/abs/2605.12524</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13852.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real images, using renders of synthetic 3D assets, where annotations for control signals are available. While this approach can learn the desired controls, it often compromises the realism of the images due to domain gap between photographs and renders. We observe that this issue largely arises from the model learning an unintended association between the presence of control signals and the synthetic appearance of the images. To address this, we introduce Realiz3D, a lightweight framework for training diffusion models, that decouples controls and visual domain. The key idea is to explicitly learn visual domain, real or synthetic, separately from other control signals by introducing a co-variate that, fed into small residual adapters, shifts the domain. Then, the generator can be trained to gain controllability, without fitting to specific visual domain. In this way, the model can be guided to produce realistic images even when controls are applied. We enhance control transferability to the real domain by leveraging insights about roles of different layers and denoising steps in diffusion-based generators, informing new training and inference strategies that further mitigate the gap. We demonstrate the advantages of Realiz3D in tasks as text-to-multiview generation and texturing from 3D inputs, producing outputs that are 3D-consistent and photorealistic.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12524.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Konstantine Arkoudas, Serafim Batzoglou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof gap-filling. Tasks are expressed in minimal formal notation, especially NDL, a compact natural-deduction language that fits in short prompts and supports precise, auditable verification. This yields mechanical, reproducible, and fine-grained evaluation rather than judgments by humans or LLMs. ProofGrid covers a calibrated difficulty spectrum, from foundational reasoning tests to structurally rich challenge tasks that no current model solves, while minimizing reliance on domain knowledge, solver delegation, and long-context artifacts. We also develop a comparative framework for reasoning benchmarks and use it to situate ProofGrid relative to existing work in terms of representation, verification guarantees, and reasoning depth. Methodologically, we introduce an instrumented proof-checking pipeline that tolerates minor surface deviations while locating the first substantive reasoning failure, improving measurement resolution and separating proof planning from low-level execution noise. Using this pipeline, we evaluate a broad range of open and proprietary models. Results show rapid progress but substantial remaining limits: frontier models perform well on several foundational tasks, yet difficult tasks, especially those requiring global combinatorial reasoning or low-level proof synthesis, remain far from solved. We also identify epistemic instability, where models generate flawed proofs yet correctly reject those local inferences in isolation, and formalize this with an Epistemic Stability Index. Finally, we complement accuracy with 2PL IRT analyses, Wright maps, and a normalized task-discrimination measure based on Fisher information.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13852</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.12524</guid>
|
||||||
<pubDate>Wed, 25 Mar 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RouteProfile: Elucidating the Design Space of LLM Profiles for Routing</title>
|
<title>Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding</title>
|
||||||
<link>https://arxiv.org/abs/2605.00180</link>
|
<link>https://arxiv.org/abs/2605.02290</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.00180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjun Xu, Hongji Pu, Tao Feng, Haozhen Zhang, Jiaxuan You, Ge Liu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> As the large language model (LLM) ecosystem expands, individual models exhibit varying capabilities across queries, benchmarks, and domains, motivating the development of LLM routing. While prior work has largely focused on router mechanism design, LLM profiles, which capture model capabilities, remain underexplored. In this work, we ask: How does LLM profile design affect routing performance across different routers? Addressing this question helps clarify the role of profiles in routing, disentangle profile design from router design, and enable fairer comparison and more principled development of routing systems. To this end, we view LLM profiling as a structured information integration problem over heterogeneous interaction histories. We develop a general design space of LLM profiles, named RouteProfile, along four key dimensions: organizational form, representation type, aggregation depth, and learning configuration. Through systematic evaluation across three representative routers under both standard and new-LLM generalization settings, we show that: (1) structured profiles consistently outperform flat ones; (2) query-level signals are more reliable than coarse domain-level signals; and (3) generalization to newly introduced models benefits most from structured profiles under trainable configurations. Overall, our work highlights LLM profile design as an important direction for future routing research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.02290.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taewon Yun, Jisu Shin, Jeonghwan Choi, Seunghwan Bang, Hwanjun Song</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking collaboration among heterogeneous teachers and lacking dynamic exploration, which leads to redundant sampling and missed complementary reasoning. We introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity-based scoring and beam search. This enables heterogeneous LRMs to jointly construct coherent reasoning trajectories while efficiently preserving diverse, high-potential hypotheses. Experiments show that CoRD produces higher-quality reasoning data and achieves near teacher-level student performance with fewer, structured supervision signals, without substantial efficiency overhead. CoRD further generalizes well to out-of-domain and open-ended settings. The dataset and model are available at https://github.com/DISL-Lab/CoRD{https://github.com/DISL-Lab/CoRD}.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.00180</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.02290</guid>
|
||||||
<pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 04 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild</title>
|
<title>MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware</title>
|
||||||
<link>https://arxiv.org/abs/2605.01018</link>
|
<link>https://arxiv.org/abs/2605.05945</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.01018.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junzhe Huang, Xiaoxiao Sun, Yan Yang, Yuxuan Hou, Ruotian Zhang, Sirui Li, Hehe Fan, Serena Yeung-Levy, Xin Yu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its importance, current evaluations rely largely on structured-text tables or clean rendered images, leaving the visual complexity of in-the-wild table images underexplored. Such images feature varied layouts and diverse domains that demand sophisticated structural perception and numerical reasoning. To bridge this gap, we introduce WildTableBench, the first question-answering benchmark for naturally occurring table images from real-world settings. WildTableBench comprises 402 high-information-density table images collected from online forums and websites across diverse domains, together with 928 manually annotated and verified questions spanning 17 subtypes across five categories. We evaluate 21 frontier proprietary and open-source multimodal foundation models on this benchmark. Only one model exceeds 50% accuracy, while all remaining models range from 4.1% to 49.9%. We further conduct diagnostic analyses to characterize model failures and reveal persistent weaknesses in structural perception and reasoning. These results and analyses provide useful insights into current model capabilities and establish WildTableBench as a valuable diagnostic benchmark for table image understanding.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.05945.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathor, Pratyush Patnaik, Shubhanshu Khatana</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The recent advancement of Vision Language Action (VLA) models has driven a critical demand for large scale egocentric datasets. However, existing datasets are often limited by short episode durations, typically spanning only a few minutes, which fails to capture the long horizon temporal dependencies necessary for complex robotic task execution. To bridge this gap, we present MobileEgo Anywhere, a framework designed to facilitate the collection of robust, hour plus egocentric trajectories using commodity mobile hardware. We leverage the ubiquitous sensor suites of modern smartphones to provide high fidelity, long term camera pose tracking, effectively removing the high hardware barriers associated with traditional robotics data collection. Our contributions are three fold: (1) we release a novel dataset comprising 200 hours of diverse, long form egocentric data with persistent state tracking; (2) we open source a mobile application that enables any user to record egocentric data, and (3) we provide a comprehensive processing pipeline to convert raw mobile captures into standardized, training ready formats for Vision Language Action model and foundation model research. By democratizing the data collection process, this work enables the massive scale acquisition of long horizon data across varied global environments, accelerating the development of generalizable robotic policies.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.01018</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.05945</guid>
|
||||||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Long Context Pre-Training with Lighthouse Attention</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.06554</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Peng, Subho Ghosh, Jeffrey Quesnelle</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based hierarchical attention algorithm that wraps around ordinary SDPA and can be easily removed towards the end of the training. Our hierarchical selection is also gradient-free, which exempts us from dealing with a complicated and potentially inefficient backward pass kernel. Our contribution is three-fold: (i) A subquadratic hierarchical pre- and post-processing step that does adaptive compression and decompression of the sequence. (ii) A symmetrical compression strategy that pools queries, keys and values at the same time, while preserving left-to-right causality, which greatly improves parallelism. (iii) A two stage training approach which we pre-train for the majority of the time with Lighthouse Attention and recover a full attention model at the end with a short training. We run preliminary small scale LLM pre-training experiments that show the effectiveness of our method compared to full attention training with all other settings matched, where we achieve a faster total training time and lower final loss after the recovery phase. Full code is available at: https://github.com/ighoshsubho/lighthouse-attention</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06554</guid>
|
|
||||||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?</title>
|
<title>Steered LLM Activations are Non-Surjective</title>
|
||||||
<link>https://arxiv.org/abs/2605.06527</link>
|
<link>https://arxiv.org/abs/2604.09839</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.06527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxiang Chao, Yihan Bai, Rui Sheng, Tianle Li, Yushi Sun</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failure mode, Implicit Conflict: a later observation invalidates an earlier memory without explicit negation, requiring contextual inference and commonsense reasoning to detect. To rigorously evaluate this capability, we introduce STALE, a benchmark of 400 expert-validated conflict scenarios (1,200 evaluation queries across three probing dimensions) spanning over 100 everyday topics with contexts up to 150K tokens. We propose a three-dimensional probing framework that tests State Resolution (detecting that a prior belief is outdated), Premise Resistance (rejecting queries that falsely presuppose a stale state), and Implicit Policy Adaptation (proactively applying updated states in downstream behavior). A systematic evaluation of frontier LLMs and specialized memory frameworks reveals a pervasive gap between retrieving updated evidence and acting on it, with even the best evaluated model achieving only 55.2% overall accuracy. Models often accept outdated assumptions embedded in a user's query, and they struggle to recognize when a change in one aspect of the user's state should invalidate related memories. To establish an initial baseline for state-aware memory, we further present CUPMem, a prototype that strengthens write-time revision through structured state consolidation and propagation-aware search, suggesting that explicit state adjudication is a promising direction for robust agentic memory.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.09839.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aayush Mishra, Daniel Khashabi, Anqi Liu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating activations into human-readable explanations) and safety research (e.g., jailbreakability). However, it is unclear whether steered behavior is realizable by any textual prompt. In this work, we cast this question as a surjectivity problem: for a fixed model, does every steered activation admit a preimage under the model's natural forward pass? Under practical assumptions, we prove that activation steering pushes the residual stream off the manifold of states reachable from discrete prompts. Almost surely, no prompt can reproduce the same internal behavior induced by steering. We also illustrate this finding empirically across three widely used LLMs. Our results establish a formal separation between white-box steerability and black-box prompting. We therefore caution against interpreting the ease and success of activation steering as evidence of prompt-based interpretability or vulnerability, and argue for evaluation protocols that explicitly decouple white-box and black-box interventions.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.06527</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2604.09839</guid>
|
||||||
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RewardHarness: Self-Evolving Agentic Post-Training</title>
|
<title>MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal</title>
|
||||||
<link>https://arxiv.org/abs/2605.08703</link>
|
<link>https://arxiv.org/abs/2605.07249</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxuan Zhang, Penghui Du, Bo Li, Cong Wei, Junwen Miao, Huaisong Zhang, Songcheng Cai, Yubo Wang, Dongfu Jiang, Yuyu Zhang, Ping Nie, Wenhu Chen, Changqian Yu, Kelsey R. Allen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency gap: humans can often infer the target evaluation criteria from only a few examples, while models are usually trained on hundreds of thousands of comparisons. We present RewardHarness, a self-evolving agentic reward framework that reframes reward modeling as context evolution rather than weight optimization. Instead of learning from large-scale annotations, RewardHarness aligns with human preferences by iteratively evolving a library of tools and skills from as few as 100 preference demonstrations. Given a source image, candidate edited images, and an editing instruction, an Orchestrator selects the most relevant subset of tools and skills from the maintained library, and a frozen Sub-Agent uses them to construct a reasoning chain that produces a preference judgment. By comparing predicted judgments with ground-truth preferences and analyzing successes and failures in the reasoning process, the Orchestrator automatically refines its library of tools and skills without additional human annotation. Using only 0.05% of the EditReward preference data, RewardHarness achieves 47.4% average accuracy on image-editing evaluation benchmarks, surpassing GPT-5 by 5.3 points. When used as a reward signal for GRPO fine-tuning, RL-tuned models achieve 3.52 on ImgEdit-Bench. Project page: https://rewardharness.com.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07249.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> 0</p><p><b>Summary:</b> Multilingual Information Retrieval is increasingly important in real-world search settings, where users issue queries over mixed-language corpora. Existing evaluations mainly reward language-agnostic semantic relevance, treating relevant passages equally regardless of language. Yet retrieval utility also depends on the language of the retrieved passages: users may prefer results they can read and verify in the query language, and query--passage language mismatch can complicate downstream grounding and answer verification in Retrieval-Augmented Generation systems. To evaluate this language-aware dimension, we introduce MLAIRE, a Multilingual Language-Aware Information Retrieval Evaluation protocol that disentangles cross-lingual semantic retrieval from query-language preference. MLAIRE constructs controlled pools with parallel passages across languages, enabling measurement of semantic retrieval accuracy and query-language preference when equivalent translations are available. We propose language-aware metrics, including Language Preference Rate (LPR) and Lang-nDCG, together with a 4-way decomposition separating semantic and query-language preference failures. Evaluating 31 dense, sparse, and late-interaction retrievers, we show that standard metrics obscure distinct behaviors: semantically strong retrievers may return correct content in a non-query language, while retrievers with stronger query-language preference may retrieve less semantically relevant passages.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.08703</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.07249</guid>
|
||||||
|
<pubDate>Fri, 08 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.08614</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Devin Yasith De Silva, Dhaval Patel, Christodoulos Constantinides, Shuxin Lin, Nianjun Zhou, Paul J Adams, Sal Rosato, Nicolas Constantinides, Deborah L. McGuinness, Jayant Kalagnanam</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.08614</guid>
|
||||||
<pubDate>Sat, 09 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sat, 09 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models</title>
|
<title>Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction</title>
|
||||||
<link>https://arxiv.org/abs/2605.09681</link>
|
<link>https://arxiv.org/abs/2602.09016</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.09681.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng Ji, Zhizhou Zhong, Jun Zhang, Qin Yang, XiTai Jin, Ying Qin, Wenhan Luo, Shuiyang Mao, Wei Liu, Huan Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video diffusion models still suffer from significant attention complexity and severe memory overhead due to the redundant key-value (KV) caches across historical frames, which limits scalability. In this paper, we tackle this challenge by introducing KV cache compression into autoregressive video diffusion. We observe that attention heads in mainstream AR diffusion models exhibit markedly distinct attention patterns and functional roles that remain stable across samples and denoising steps. Building on our empirical study of head-wise functional specialization, we divide the attention heads into two categories: static heads, which focus on transitions across autoregressive chunks and intra-frame fidelity, and dynamic heads, which govern inter-frame motion and consistency. We then propose Forcing-KV, a hybrid KV cache compression strategy that performs structured static pruning for static heads and dynamic pruning based on segment-wise similarity for dynamic heads. While maintaining output quality, our method achieves a generation speed of over 29 frames per second on a single NVIDIA H200 GPU along with 30% cache memory reduction, delivering up to 1.35x and 1.50x speedups on LongLive and Self Forcing at 480P resolution, and further scaling to 2.82x speedup at 1080P resolution. Code and demo videos are provided at https://zju-jiyicheng.github.io/Forcing-KV-Page.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.09016.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Phung, Hadar Averbuch-Elor</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computational tasks involving floorplans such as automated understanding or CAD workflows. However, existing techniques struggle in faithfully generating the structure and semantics conveyed by complex floorplans that depict large indoor spaces with many rooms and a varying numbers of polygon corners. To this end, we propose Raster2Seq, framing floorplan reconstruction as a sequence-to-sequence task in which floorplan elements--such as rooms, windows, and doors--are represented as labeled polygon sequences that jointly encode geometry and semantics. Our approach introduces an autoregressive decoder that learns to predict the next corner conditioned on image features and previously generated corners using guidance from learnable anchors. These anchors represent spatial coordinates in image space, hence allowing for effectively directing the attention mechanism to focus on informative image regions. By embracing the autoregressive mechanism, our method offers flexibility in the output format, enabling for efficiently handling complex floorplans with numerous rooms and diverse polygon structures. Our method achieves state-of-the-art performance on standard benchmarks such as Structure3D, CubiCasa5K, and Raster2Graph, while also demonstrating strong generalization to more challenging datasets like WAFFLE, which contain diverse room structures and complex geometric variations.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.09681</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2602.09016</guid>
|
||||||
<pubDate>Sun, 10 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>PREPING: Building Agent Memory without Tasks</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.13880</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yumin Choi, Sangwoo Park, Minki Kang, Jinheon Baek, Sung Ju Hwang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic tasks become redundant, infeasible, and ultimately uninformative, and memory further degrades quickly due to unfiltered trajectories. To overcome this, we present Preping, a proposer-guided memory construction framework. At its core is proposer memory, a structured control state that shapes future practice. A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals. Experiments on AppWorld, BFCL v3, and MCP-Universe show that Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost 2.99times lower on AppWorld and 2.23times lower on BFCL v3 than online memory construction. Further analyses reveal that the main benefit does not come from synthetic volume alone, but from proposer-side control over feasibility, redundancy, and coverage, combined with selective memory updates.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13880</guid>
|
|
||||||
<pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation</title>
|
<title>No One Knows the State of the Art in Geospatial Foundation Models</title>
|
||||||
<link>https://arxiv.org/abs/2605.10912</link>
|
<link>https://arxiv.org/abs/2605.12678</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10912.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuangrui Ding, Xuanlang Dai, Long Xing, Shengyuan Ding, Ziyu Liu, Yang JingYi, Penghui Yang, Zhixiong Zhang, Xilin Wei, Xinyu Fang, Yubo Ma, Haodong Duan, Jing Shao, Jiaqi Wang, Dahua Lin, Kai Chen, Yuhang Zang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks. Yet the published work about these models does not give reviewers or users enough information to tell which model fits a given task. We argue that nobody knows what the current state of the art is in geospatial foundation models. The methods may be useful, but the GFM literature does not standardize evaluations, training and testing protocols, released weights, or pretraining controls well enough for anyone to compare or rank them. In a 152-paper audit, we find 46 cross-paper disagreements of at least 10 points for the same model, benchmark, and protocol; 94/126 papers with extractable pretraining data use a configuration no other paper uses; and 39% of GFM papers release no model weights. This lack of community standards can be solved. We propose six concrete expectations: named-license weight release, shared core evaluations, copied-versus-rerun baseline annotations, variance reporting, one shared evaluation harness, and data-vs-architecture-vs-algorithm controls. These gaps are a coordination failure, not a fault of any individual lab; the authors of this paper, like many others in the GFM community, have contributed to them. Rather than just critiquing the community, we aim to provide concrete steps toward a shared understanding of how to innovate GFMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.10912</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.12678</guid>
|
||||||
<pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>PreScam: A Benchmark for Predicting Scam Progression from Early Conversations</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.12243</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12243.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixiang Sun, Shang Ma, Yiyang Li, Tianyi Ma, Zehong Wang, Colby Nelson, Xusheng Xiao, Yanfang Ye</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Conversational scams, such as romance and investment scams, are emerging as a major form of online fraud. Unlike one-shot scam lures such as fake lottery or unpaid toll messages, they unfold through multi-turn conversations in which scammers gradually manipulate victims using evolving psychological techniques. However, existing research mainly focuses on static scam detection or synthetic scams, leaving open whether language models can understand how real-world scams progress over time. We introduce PreScam, a benchmark for modeling scam progression from early conversations. Built from user-submitted scam reports, PreScam filters and structures 177,989 raw reports into 11,573 conversational scam instances spanning 20 scam categories. Each instance is hierarchically structured according to the scam lifecycle defined by the proposed scam kill chain, and further annotated at the turn level with scammer psychological actions and victim responses. We benchmark models on two tasks: real-time termination prediction, which estimates whether a conversation is approaching the termination stage, and scammer action prediction, which forecasts the scammer's subsequent actions. Results show a clear gap between surface-level fluency and progression modeling: supervised encoders substantially outperform zero-shot LLMs on real-time termination prediction, while next-action prediction remains only moderately successful even for strong LLMs. Taken together, these results show that current models can capture some scam-related cues, yet still struggle to track how risk escalates and how manipulation unfolds across turns.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.12243</guid>
|
|
||||||
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning</title>
|
<title>Follow the Mean: Reference-Guided Flow Matching</title>
|
||||||
<link>https://arxiv.org/abs/2605.11458</link>
|
<link>https://arxiv.org/abs/2605.10302</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11458.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Han, Tiangang Zhang, Huaibin Wang, Yilun Sun</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods, however, has gone unquestioned: the teacher always sees the full reference reasoning. We argue that this default itself is part of the problem and identify a teacher-side exposure mismatch: when the teacher conditions on reasoning far beyond the student's current competence, the resulting token targets become too strong to absorb. A controlled fixed-exposure sweep makes this concrete on two fronts: 1) full exposure is not reliably the best choice, and 2) student-teacher mismatch grows monotonically as the teacher sees more privileged reasoning. This motivates treating teacher exposure not as a fixed hyperparameter but as a learnable training-time control variable. We therefore propose Adaptive Teacher Exposure for Self-Distillation (ATESD). ATESD models the reveal ratio with a lightweight Beta-policy controller conditioned on compact training-state statistics, and uses one sampled exposure for a short hold window of student updates. To make this exposure controller learnable, we optimize it with a discounted learning-progress reward that scores each held decision by its effect on the student's future improvement rather than its immediate loss change, addressing the delayed credit assignment induced by on-policy distillation. Experiments on AIME 24, AIME 25, and HMMT 25 across Qwen3-{1.7B, 4B, 8B} show that ATESD consistently outperforms competitive self-distillation and RL baselines, improving over OPSD by +0.95, +2.05, and +2.33 Average@12 points respectively, and establishing adaptive teacher exposure as an effective new axis for reasoning self-distillation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10302.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pedro M. P. Curvo, Maksim Zhdanov, Floor Eijkelboom, Jan-Willem van de Meent</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation through examples. For deterministic interpolants, the velocity field is solely governed by a conditional endpoint mean; shifting this mean shifts the flow itself. This yields a simple principle for controllable generation: steer a pretrained model by changing the reference set it follows. We instantiate this idea in two forms. Reference-Mean Guidance is training-free: it computes a closed-form endpoint-mean correction from a reference bank and applies it to a frozen FLUX.2-klein (4B) model, enabling control of color, identity, style, and structure while keeping the prompt, seed, and weights fixed. Semi-Parametric Guidance amortizes the same idea through an explicit mean anchor and learned residual refiner, matching unconditional DiT-B/4 quality on AFHQv2 while allowing the reference set to be swapped at inference time. These results point to a broader direction: generative models that adapt through data, not parameter updates.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.11458</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.10302</guid>
|
||||||
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding</title>
|
<title>OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation</title>
|
||||||
<link>https://arxiv.org/abs/2605.07637</link>
|
<link>https://arxiv.org/abs/2605.12038</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.07637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valeriy Vyaltsev, Alsu Sagirova, Anton Andreychuk, Oleg Bulichev, Yuri Kuratov, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Multi-agent pathfinding (MAPF) is a widely used abstraction for multi-robot trajectory planning problems, where multiple homogeneous agents move simultaneously within a shared environment. Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. Such methods frame MAPF (from a single agent perspective) as a Dec-POMDP where at each time step an agent has to decide an action based on the local observation and typically solve the problem via reinforcement learning or imitation learning. We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing. We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers, including IL and RL-based approaches, across diverse metrics in a diverse range of (unseen) test scenarios. Remarkably, the introduced communication mechanism does not compromise LC-MAPF's scalability, a common bottleneck for communication-based MAPF solvers.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12038.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiren Song, Xiyao Deng, Pei Yang, Yihan Wang, Mike Zheng Shou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Cross-embodiment video generation aims to transfer motions across different humanoid embodiments, such as human-to-robot and robot-to-robot, enabling scalable data generation for embodied intelligence. A major challenge in this setting is that motion dynamics are partly transferable across embodiments, whereas appearance and morphology remain embodiment-specific. Existing approaches often entangle these factors, and many require paired data for every target embodiment, which limits scalability to new robots. We present OmniHumanoid, a framework that factorizes transferable motion learning and embodiment-specific adaptation. Our method learns a shared motion transfer model from motion-aligned paired videos spanning multiple embodiments, while adapting to a new embodiment using only unpaired videos through lightweight embodiment-specific adapters. To reduce interference between motion transfer and embodiment adaptation, we further introduce a branch-isolated attention design that separates motion conditioning from embodiment-specific modulation. In addition, we construct a synthetic cross-embodiment dataset with motion-aligned paired videos rendered across diverse humanoid assets, scenes, and viewpoints. Experiments on both synthetic and real-world benchmarks show that OmniHumanoid achieves strong motion fidelity and embodiment consistency, while enabling scalable adaptation to unseen humanoid embodiments without retraining the shared motion model.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.07637</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.12038</guid>
|
||||||
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks</title>
|
<title>Hölder Policy Optimisation</title>
|
||||||
<link>https://arxiv.org/abs/2605.14051</link>
|
<link>https://arxiv.org/abs/2605.12058</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusuke Ozaki, Dhaval Patel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long workflows, leading to brittle failures and avoidable tool and API cost. We propose SPIN, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control. SPIN enforces a strict DAG contract through \_validate\_plan\_text and repair prompting, producing executable plans before downstream execution, and then evaluates DAG prefixes incrementally to stop when the current prefix is sufficient to answer the query. On AssetOpsBench, across 261 scenarios, SPIN reduces executed tasks from 1061 to 623 and improves Accomplished from 0.638 to 0.706, while reducing tool calls from 11.81 to 6.82 per run. On MCP Bench, the same wrapper improves planning, grounding, and dependency related scores for both GPT OSS1 and Llama 4 Maverick.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Chen, Dingli Liang, Yihang Chen, Ziqin Gong, Chenyang Le, Zhaokai Wang, Jiachen Zhu, Lingyu Yang, Jianghao Lin, Weinan Zhang, Jun Wang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level probabilities within each sequence. Relying on a fixed aggregation mechanism for this step fundamentally limits the algorithm's adaptability. Empirically, we observe a critical trade-off: certain fixed aggregations frequently suffer from training collapse, while others fail to yield satisfactory performance. To resolve this, we propose HölderPO, a generalised policy optimisation framework unifying token-level probability aggregation via the Hölder mean. By explicitly modulating the parameter p, our framework provides continuous control over the trade-off between gradient concentration and variance bounds. Theoretically, we prove that a larger p concentrates the gradient to amplify sparse learning signals, whereas a smaller p strictly bounds gradient variance. Because no static configuration can universally resolve this concentration-stability trade-off, we instantiate the framework with a dynamic annealing algorithm that progressively schedules p across the training lifecycle. Extensive evaluations demonstrate superior stability and convergence over existing baselines. Specifically, our approach achieves a state-of-the-art average accuracy of 54.9% across multiple mathematical benchmarks, yielding a substantial 7.2% relative gain over standard GRPO and secures an exceptional 93.8% success rate on ALFWorld.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14051</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.12058</guid>
|
||||||
|
<pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.14040</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shan Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We audit the multimodal-physics evaluation pipeline end-to-end and document three undetected construction practices that distort how the field measures vision-language reasoning: train-eval contamination, translation drift, and MCQ saturation. (1) Public training pools (UGPhysics-Train, SciInstruct, MMK12) pass single-stage 5-gram-Jaccard audits with zero hits across all six public physics evals; a three-stage audit (Jaccard -> mxbai-embed-large cosine -> Haiku-4.5 LLM-judge) surfaces 134 near-duplicates and 4,846 paraphrase candidates in SciInstruct alone. (2) A 17-pp Sonnet 4.5 delta on 59 paired Estonian-English olympiad problems (30.5% vs. 13.6%; sign test p=0.011, McNemar p=0.021, paired bootstrap 95% CI [+5.1, +28.9] pp). (3) A 46-pp format-and-novelty gradient on identical Sonnet weights between MCQ (79.7% on PhyX) and open-ended olympiad evaluation (33.4% on PhysOlym-A). We release four artifacts addressing these gaps: PhysCorp-A (6,432-record three-stage-audited multimodal corpus), PhysR1Corp (2,268-record closed-form RL pool), PhysOlym-A (500-problem, 99.8% novel-source held-out olympiad eval with native difficulty labels and an EN/ET bilingual subset), and Physics-R1, a reference GSPO+DAPO recipe cold-started from Qwen3-VL-8B-Thinking. Across 3 seeds, Physics-R1 lifts the audited corpus over the 8B base by +18.3 pp on PhysOlym-A liberal (8.0 -> 26.3 +/- 1.7; 7.1 pp behind Sonnet 4.5), +15.7 pp on PhysReason (23.9 -> 39.6 +/- 6.4; ahead of Qwen3-VL-32B and Gemini 2.5 Pro), +6.9 pp on OlympiadBench-Physics (46.2 +/- 1.5), and +4.1 pp on PhyX MCQ (77.8 +/- 0.3).</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14040</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Topology-Preserving Neural Operator Learning via Hodge Decomposition</title>
|
<title>HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts</title>
|
||||||
<link>https://arxiv.org/abs/2605.13834</link>
|
<link>https://arxiv.org/abs/2605.13997</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13834.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongzhe Zheng, Tao Zhong, Christine Allen-Blanchette</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resolves spectral interference by isolating unlearnable topological degrees of freedom from learnable geometric dynamics, enabling an additive approximation confined to structure-preserving subspaces. Building on Hodge theory and operator splitting, we derive a principled operator-level decomposition. The result is a Hybrid Eulerian-Lagrangian architecture with an algebraic-level inductive bias we call Hodge Spectral Duality (HSD). In our framework, we use discrete differential forms to capture topology-dominated components and an orthogonal auxiliary ambient space to represent complex local dynamics. Our method achieves superior accuracy and efficiency on geometric graphs with enhanced fidelity to physical invariants. Our code is available at https://github.com/ContinuumCoder/Hodge-Spectral-Duality</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13997.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Zhong, Dongzhe Zheng, Christine Allen-Blanchette</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost without retraining. A subtle obstruction blocks every existing compressor in this family: three experts can each be pairwise compatible yet form an irreducible cycle when merged together, so any score that ranks experts on pairwise signals is structurally blind to which triples are jointly mergeable. We show the obstruction is a precise mathematical object, the harmonic kernel of the simplicial Laplacian on a 2-complex whose vertices are experts, whose edges carry KL merge barriers, and whose faces carry triplet barriers; Hodge-decomposing the edge-barrier signal isolates the kernel exactly. We turn the diagnostic into a selection objective: HodgeCover greedily covers the harmonic-critical edges and triplet-critical triangles, and a hybrid variant of HodgeCover pairs it with off-the-shelf weight pruning on survivors. On three open-weight Sparse MoE backbones under aggressive expert reduction, HodgeCover matches state-of-the-art learning-free baselines on the expert-reduction axis, leads on the aggressive-compression frontier of the hybrid axis, and uniquely balances retained mass across all four Hodge components. These results show that exposing the harmonic kernel of a learned MoE structure changes which compressor wins at the regime that matters most.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13834</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.13997</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation</title>
|
<title>Learning POMDP World Models from Observations with Language-Model Priors</title>
|
||||||
<link>https://arxiv.org/abs/2605.12034</link>
|
<link>https://arxiv.org/abs/2605.13740</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12034.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Che Liu, Lichao Ma, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Xuerui Yang, Fei Tian</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer a query. We study whether current omni-modal benchmarks separate visual shortcuts from genuine audio-visual-language evidence integration, and how post-training behaves under a visually debiased evaluation setting. We audit nine omni-modal benchmarks with visual-only probing, remove visually solvable queries, and retain full subsets when filtering is undefined or would make comparisons unstable. This yields OmniClean, a cleaned evaluation view with 8,551 retained queries from 16,968 audited queries. On OmniClean, we evaluate OmniBoost, a three-stage post-training recipe based on Qwen2.5-Omni-3B: mixed bi-modal SFT, mixed-modality RLVR, and SFT on self-distilled data. Balanced bi-modal SFT gives limited and uneven gains, RLVR provides the first broad improvement, and self-distillation reshapes the benchmark profile. After SFT on self-distilled data, the 3B model reaches performance comparable to, and in aggregate slightly above, Qwen3-Omni-30B-A3B-Instruct without using a stronger omni-modal teacher. These results show that omni-modal progress is easier to interpret when evaluation controls visual leakage, and that small omni-modal models can benefit from staged post-training with self-distilled omni-query supervision. Project page: https://cheliu-computation.github.io/omni/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13740.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valentin Six, Frederik Panse, Mathis Fajeau, Lancelot Da Costa, Mridul Sharma, Alfonso Amayuelas, Tim Z. Xiao, David Hyland, Philipp Hennig, Bernhard Schölkopf</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment works. Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for such internal world models, but learning them from observation-action trajectories alone is challenging and typically requires extensive environment interaction. We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge, and introduce Pinductor (POMDP-inductor): an LLM proposes candidate POMDP models from a few observation-action trajectories and iteratively refines them to optimize a belief-based likelihood score. Despite using strictly less information, Pinductor matches the performance and sample efficiency of LLM-based POMDP learning methods that assume privileged access to the hidden state, while significantly surpassing the sample efficiency of tabular POMDP baselines. Further results show that performance scales with LLM capability and degrades gracefully as semantic information about the environment is withheld. Together, these results position language-model priors as a practical tool for sample-efficient world-model learning under partial observability, and a step toward generalist agents in real-world environments. Code is available at https://github.com/atomresearch/pinductor.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.12034</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.13740</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution</title>
|
<title>Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation</title>
|
||||||
<link>https://arxiv.org/abs/2605.13027</link>
|
<link>https://arxiv.org/abs/2605.11739</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13027.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihang Xu, Xiaoyang Liu, Zheng Chen, Yulun Zhang, Xiaokang Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Text image super-resolution (Text-SR) requires more than visually plausible detail synthesis: slight errors in stroke topology may alter character identity and break readability. Existing methods improve text fidelity with stronger recognition-based or generative priors, yet they still face two unresolved challenges under severe degradation: the text condition extracted from low-quality inputs can itself be unreliable, and a plausible global prior does not fully determine fine-grained stroke boundaries. We present PRISM, a single-step diffusion-based Text-SR framework that addresses these two challenges through Flow-Matching Prior Rectification (FMPR) and a Structure-guided Uncertainty-aware Residual Encoder (SURE). FMPR constructs a privileged training-time prior from paired low-quality/high-quality latents and learns a flow matching that transports degraded embeddings toward this restoration-oriented prior space, yielding more accurate and reliable global text guidance. SURE further predicts uncertainty-aware structural residuals to selectively absorb reliable local boundary evidence while suppressing ambiguous stroke cues. Together, these components enable explicit global prior rectification and local structure refinement within a single diffusion restoration pass. Experiments on both synthetic and real-world benchmarks show that PRISM achieves state-of-the-art performance with millisecond-level inference. Our dataset and code will be available at https://github.com/faithxuz/PRISM.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11739.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Cai, Ding Cao, Liang Lin, Chunxi Luo, Xin Xu, Kai Yang, Weijie Liu, Saiyong Yang, Tianxiang Zhao, Guangzhong Sun, Guiquan Liu, Junfeng Fang</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level mechanisms underlying OPD's efficiency remain poorly understood. In this work, we argue that OPD's efficiency stems from a form of ``foresight'': it establishes a stable update trajectory toward the final model early in training. This foresight manifests in two aspects. First, at the Module-Allocation Level, OPD identifies regions with low marginal utility and concentrates updates on modules that are more critical to reasoning. Second, at the Update-Direction Level, OPD exhibits stronger low-rank concentration, with its dominant subspaces aligning closely with the final update subspace early in training. Building on these findings, we propose EffOPD, a plug-and-play acceleration method that speeds up OPD by adaptively selecting an extrapolation step size and moving along the current update direction. EffOPD requires no additional trainable modules or complex hyperparameter tuning, and achieves an average training acceleration of 3times while maintaining comparable final performance. Overall, our findings provide a parameter-dynamics perspective for understanding the efficiency of OPD and offer practical insights for designing more efficient post-training methods for large language models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13027</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.11739</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>BOOKMARKS: Efficient Active Storyline Memory for Role-playing</title>
|
<title>CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence</title>
|
||||||
<link>https://arxiv.org/abs/2605.14169</link>
|
<link>https://arxiv.org/abs/2605.12882</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Letian Peng, Ziche Liu, Yiming Huang, Longfei Yun, Kun Zhou, Yupeng Hou, Jingbo Shang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling) mainly rely on recurrent summarization, whose compression inevitably discards important details. To address this issue, we propose a search-based memory framework called BOOKMARKS, which actively initializes, maintains, and updates task-relevant pieces of bookmarks for the current task (e.g., character acting). A bookmark is structured as the answer to a question at a specific point in the storyline. For each current task, BOOKMARKS selects reusable existing bookmarks or initializes new ones (at storyline beginning) with useful questions. These bookmarks are then synchronized to the current story point, with their answers updated accordingly, so they can be efficiently reused in future grounding rounds. Compared with recurrent summarization, BOOKMARKS offers (1) active grounding for capturing task-specific details and (2) passive updating to avoid unnecessary computation. In implementation, BOOKMARKS supports concept, behavior, and state searches, each powered by an efficient synchronization method. BOOKMARKS significantly outperforms RPA memory baselines on 85 characters from 16 artifacts, demonstrating the effectiveness of search-based memory for RPAs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.12882.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongsheng Ma, Jiayu Li, Zhengren Wang, Yijie Wang, Jiahao Kong, Weijun Zeng, Jutao Xiao, Jie Yang, Wentao Zhang, Bin Wang, Conghui He</p><p><b>Upvotes:</b> 161</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical failure mode: a model can land on the correct answer while grounding it in the wrong passage -- a critical risk in high-stakes domains like law, finance, and medicine, where every conclusion must be traceable to a specific source region. To address this, we introduce CiteVQA, a benchmark that requires models to return element-level bounding-box citations alongside each answer, evaluating both jointly. CiteVQA comprises 1,897 questions across 711 PDFs spanning seven domains and two languages, averaging 40.6 pages per document. To ensure fidelity and scalability, the ground-truth citations are generated by an automated pipeline-which identifies crucial evidence via masking ablation-and are subsequently validated through expert review. At the core of our evaluation is Strict Attributed Accuracy (SAA), which credits a prediction only when the answer and the cited region are both correct. Auditing 20 MLLMs reveals a pervasive Attribution Hallucination: models frequently produce the right answer while citing the wrong region. The strongest system (Gemini-3.1-Pro-Preview) achieves an SAA of only 76.0, and the strongest open-source MLLM reaches just 22.5. Ultimately, towards trustworthy document intelligence, CiteVQA exposes a reliability gap that answer-only evaluations overlook, providing the instrumentation needed to close it. Our repository is available at https://github.com/opendatalab/CiteVQA.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14169</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.12882</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves</title>
|
<title>Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces</title>
|
||||||
<link>https://arxiv.org/abs/2605.14068</link>
|
<link>https://arxiv.org/abs/2605.14786</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirreza Mohseni, Mona Mohammadi, Morteza Saghafian, Naser Talebizadeh Saradari</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of 756 images of pairwise non-intersecting Jordan curves across easy, polygonal, topographic-inspired, maze-like, and dense counting configurations. Each image is annotated with a rooted tree encoding the containment relations between planar regions. We formulate the task as structured prediction: given an image, a model must recover the full rooted containment tree induced by the curves. Despite the visual simplicity of the task, the strongest evaluated model, Gemini 3.1 Pro, achieves only 71.1\% tree-generation accuracy on CurveBench-Easy and 19.1\% on CurveBench-Hard. We further demonstrate benchmark utility through RLVR-style fine-tuning of open-weight vision-language models. Our trained Qwen3-VL-8B model improves over Qwen-3-VL-8B-Thinking from 2.8\% to 33.3\% tree-generation accuracy on CurveBench-Easy, exceeding GPT-5.4 and Claude Opus 4.5 under our evaluation protocol. The remaining gap, especially on CurveBench-Hard, shows that exact topology-aware visual reasoning remains far from solved.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14786.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> William Lugoloobi, Samuelle Marro, Jabez Magomere, Joss Wright, Chris Russell</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96\% F1. We formalise this attack surface by demonstrating that classifiers trained on agent actions generalise across model sizes and families. We further show that strong classifiers can be trained from few interaction traces and that agent identity can be inferred early within an episode. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our harness and a labelled corpus of agent traces https://github.com/KabakaWilliam/known_actions{here}.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14068</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14786</guid>
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.13169</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13169.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changpeng Wang, Xin Lin, Junhan Liu, Yuheng Liu, Zhen Wang, Donglian Qi, Yunfeng Yan, Xi Chen</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation, robotic search, and 3D scene understanding, 360-degree panoramic sensing offers a form of supersensing by capturing the entire surrounding environment at once. However, existing MLLM pipelines typically decompose panoramas into multiple perspective views, leaving the spherical structure of equirectangular projection (ERP) largely implicit. In this paper, we study pano-native understanding, which requires an MLLM to reason over an ERP panorama as a continuous, observer-centered space. To this end, we first define the key abilities for pano-native understanding, including semantic anchoring, spherical localization, reference-frame transformation, and depth-aware 3D spatial reasoning. We then build a large-scale metadata construction pipeline that converts mixed-source ERP panoramas into geometry-aware, language-grounded, and depth-aware supervision, and instantiate these signals as capability-aligned instruction tuning data. On the model side, we introduce PanoWorld with Spherical Spatial Cross-Attention, which injects spherical geometry into the visual stream. We further construct PanoSpace-Bench, a diagnostic benchmark for evaluating ERP-native spatial reasoning. Experiments show that PanoWorld substantially outperforms both proprietary and open-source baselines on PanoSpace-Bench, H* Bench, and R2R-CE Val-Unseen benchmarks. These results demonstrate that robust panoramic reasoning requires dedicated pano-native supervision and geometry-aware model adaptation. All source code and proposed data will be publicly released.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13169</guid>
|
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.13941</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Liu, Xinyu Ye, Peng Xia, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deployment. We argue that truly adaptive memory requires co-evolution at two levels: the stored knowledge and the retrieval mechanism that queries it. We present EvolveMem, a self-evolving memory architecture that exposes its full retrieval configuration as a structured action space optimized by an LLM-powered diagnosis module. In each evolution round, the module reads per-question failure logs, identifies root causes, and proposes targeted configuration adjustments; a guarded meta-analyzer applies them with automatic revert-on-regression and explore-on-stagnation safeguards. This closed-loop self-evolution realizes an AutoResearch process: the system autonomously conducts iterative research cycles on its own architecture, replacing manual configuration tuning. Starting from a minimal baseline, the process converges autonomously, discovering effective retrieval strategies including entirely new configuration dimensions not present in the original action space. On LoCoMo, EvolveMem outperforms the strongest baseline by 25.7% relative and achieves a 78.0% relative improvement over the minimal baseline. On MemBench, EvolveMem exceeds the strongest baseline by 18.9% relative. Evolved configurations transfer across benchmarks with positive rather than catastrophic transfer, indicating that the self-evolution process captures universal retrieval principles rather than benchmark-specific heuristics. Code is available at https://github.com/aiming-lab/SimpleMem.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13941</guid>
|
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.13301</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yafu Li, Runzhe Zhan, Haoran Zhang, Shunkai Zhang, Yizhuo Li, Zhilin Wang, Jiacheng Chen, Futing Wang, Xuyang Hu, Yuchen Fan, Bangjie Xu, Yucheng Su, Xinmiao Han, Chenxi Li, Haodi Lei, Yufeng Zhao, Zejin Lin, Qianjia Cheng, Tong Zhu, Xiaoye Qu, Ganqu Cui, Peng Ye, Yun Luo, Zhouchen Lin, Yu Qiao, Bowen Zhou, Ning Ding, Yu Cheng</p><p><b>Upvotes:</b> 140</p><p><b>Summary:</b> Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reaching gold-medal-level performance on International Mathematical Olympiad (IMO) and International Physics Olympiad (IPhO) problems. In this paper, we introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver. The recipe first uses a reverse-perplexity curriculum for SFT to instill rigorous proof-search and self-checking behaviors, then scales these behaviors through a two-stage RL pipeline that progresses from RL with verifiable rewards to more delicate proof-level RL, and finally boosts solving performance with test-time scaling. Applying this recipe, we train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps. The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens, while achieving gold-medal-level performance on mathematical and physical olympiad competitions, including IMO 2025/USAMO 2026 and IPhO 2024/2025. It also demonstrates strong generalization of scientific reasoning to domains beyond mathematics and physics.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.13301</guid>
|
|
||||||
<pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.11459</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.11459.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanyan Zhang, Chaoda Song, Vikash Singh, Xinpeng Li, Kai Ye, Zhe Hu, Zhongzhu Pu, Yu Yin, Vipin Chaudhary</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Vision-Language-Action (VLA) models achieve remarkable flexibility and generalization beyond classical control paradigms. However, most prevailing VLAs are trained under a single-frame observation paradigm, which leaves them structurally blind to temporal dynamics. Consequently, these models degrade severely in non-stationary scenarios, even when trained or finetuned on dynamic datasets. Existing approaches either require expensive retraining or suffer from latency bottlenecks and poor temporal consistency across action chunks. We propose Pace-and-Path Correction, a training-free, closed-form inference-time operator that wraps any chunked-action VLA. From a single quadratic cost, joint minimization yields a unified solution that decomposes orthogonally into two distinct channels. The pace channel compresses execution along the planned direction, while the path channel applies an orthogonal spatial offset, jointly absorbing the perceived dynamics within the chunk window. We evaluate our approach on a comprehensive diagnostic benchmark MoveBench designed to isolate motion as the sole controlled variable. Empirical results demonstrate that our framework consistently outperforms state-of-the-art training-free wrappers and dynamic-adaptive methods and improves success rates by up to 28.8% and 25.9% in absolute terms over foundational VLA models in dynamic-only and static-dynamic mixed environments, respectively.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.11459</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Quantitative Video World Model Evaluation for Geometric-Consistency</title>
|
<title>AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting</title>
|
||||||
<link>https://arxiv.org/abs/2605.15185</link>
|
<link>https://arxiv.org/abs/2506.01015</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxin Wu, Yihao Pi, Yinling Zhang, Yuheng Li, Xueyan Zou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human judgment or learned graders, which can be subjective and weakly diagnostic for geometric failures. We introduce PDI-Bench (Perspective Distortion Index), a quantitative framework for auditing geometric coherence in generated videos. Given a generated clip, we obtain object-centric observations via segmentation and point tracking (e.g., SAM 2, MegaSaM, and CoTracker3), lift them to 3D world-space coordinates via monocular reconstruction, and compute a set of projective-geometry residuals capturing three failure dimensions: scale-depth alignment, 3D motion consistency, and 3D structural rigidity. To support systematic evaluation, we build PDI-Dataset, covering diverse scenarios designed to stress these geometric constraints. Across state-of-the-art video generators, PDI reveals consistent geometry-specific failure modes that are not captured by common perceptual metrics, and provides a diagnostic signal for progress toward physically grounded video generation and physical world model. Our code and dataset can be found at https://pdi-bench.github.io/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01015.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyuan Liu, Yuanhong Chen, Chong Wang, Junlin Han, Junde Wu, Can Peng, Jingkun Chen, Yu Tian, Gustavo Carneiro</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it propagates through the network. In this work, we propose AuralSAM2, which integrates audio into SAM2 while largely preserving its promptable segmentation capability. Its core module, AuralFuser, fuses audio and visual features to generate sparse and dense prompts. Guided by audio and built upon SAM2's feature pyramid, these prompts propagate auditory cues across visual layers, reinforcing cross-modal influence. To further align modalities, we introduce an audio-guided contrastive loss that emphasises auditory relevance in dominant visual features. Our method achieves notable accuracy gains on public benchmarks with only minimal impact on the interactive efficiency of promptable segmentation. Our code is available at https://github.com/yyliu01/AuralSAM2.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15185</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2506.01015</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Nexus : An Agentic Framework for Time Series Forecasting</title>
|
<title>Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution</title>
|
||||||
<link>https://arxiv.org/abs/2605.14389</link>
|
<link>https://arxiv.org/abs/2605.15138</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14389.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar, Nanyun Peng, Vishy Tirumalashetty, Chun-Liang Li, Rui Zhang, Jinsung Yoon, Tomas Pfister</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Time series forecasting is not just numerical extrapolation, but often requires reasoning with unstructured contextual data such as news or events. While specialized Time Series Foundation Models (TSFMs) excel at forecasting based on numerical patterns, they remain unaware to real-world textual signals. Conversely, while LLMs are emerging as zero-shot forecasters, their performance remains uneven across domains and contextual grounding. To bridge this gap, we introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages: isolating macro-level and micro-level temporal fluctuations, and integrating contextual information when available before synthesizing a final forecast. This decomposition enables Nexus to adapt from seasonal signals to volatile, event-driven information without relying on external statistical anchors or monolithic prompting. We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized, depending critically on how numerical and contextual reasoning are organized. Evaluated on data strictly succeeding LLM knowledge cutoffs spanning Zillow real estate metrics and volatile stock market equities, Nexus consistently matches or outperforms state-of-the-art TSFMs and strong LLM baselines. Beyond numerical accuracy, Nexus produces high-quality reasoning traces that explicitly show the fundamental drivers behind each forecast. Our results establish that real-world forecasting is an agentic reasoning problem extending well beyond only sequence modeling.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact but a systematic dual failure: gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model. Both failures trace to the same root cause: across all baselines, per-parameter updates lie 47-828x below the NF4 quantization bin width; updates diffused across billions of parameters cannot clear quantization bin boundaries, a consequence we formalize as a sparsity-permanence tradeoff. We present MANSU (Mechanistic-Aligned Null-Space Unlearning), which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph, circuit-restricted null-space projection with a diagonal-Fisher retain bound, and a per-parameter magnitude floor guaranteeing quantization survival by construction. We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression, a distinction existing metrics cannot make. Across multiple model families and hazard benchmarks, MANSU is the first method to jointly satisfy all four properties with margin on each (meaningful forgetting, retain preservation, non-positive PTQ gap, and structural erasure), while gradient-based baselines recover up to +0.05 accuracy under compression.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14389</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15138</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LiSA: Lifelong Safety Adaptation via Conservative Policy Induction</title>
|
<title>GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding</title>
|
||||||
<link>https://arxiv.org/abs/2605.14454</link>
|
<link>https://arxiv.org/abs/2605.15250</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14454.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra, Mihir Parmar, Phillip Wallis, Bharath Chandrasekhar, Kyomin Jung, Tomas Pfister, Long T. Le</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete deployment harms. In these settings, guardrail failures are no longer merely answer-quality errors: they can leak secrets, authorize unsafe actions, or block legitimate work. The hardest failures are often contextual: whether an action is acceptable depends on local privacy norms, organizational policies, and user expectations that resist pre-deployment specification. This creates a practical gap: guardrails must adapt to their own operating environments, yet deployment feedback is typically limited to sparse, noisy user-reported failures, and repeated fine-tuning is often impractical. To address this gap, we propose LiSA (Lifelong Safety Adaptation), a conservative policy induction framework that improves a fixed base guardrail through structured memory. LiSA converts occasional failures into reusable policy abstractions so that sparse reports can generalize beyond individual cases, adds conflict-aware local rules to prevent overgeneralization in mixed-label contexts, and applies evidence-aware confidence gating via a posterior lower bound, so that memory reuse scales with accumulated evidence rather than empirical accuracy alone. Across PrivacyLens+, ConFaide+, and AgentHarm, LiSA consistently outperforms strong memory-based baselines under sparse feedback, remains robust under noisy user feedback even at 20% label-flip rates, and pushes the latency--performance frontier beyond backbone model scaling. Ultimately, LiSA offers a practical path to secure AI agents against the unpredictable long tail of real-world edge risks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15250.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanxu Meng</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. Its trained weights, however, expose only one decoding path - an absorbed MQA form - which ties efficient inference to H100-class compute-bandwidth ratios, forfeits tensor parallelism along the head axis, and yields no Multi-Token Prediction (MTP) gain on commodity inference GPUs such as the export-restricted H20. We propose Group-Query Latent Attention (GQLA), a minimal modification of MLA whose trained weights expose two algebraically equivalent decoding paths over the same parameters: an MQA-absorb path identical to MLA's, and a GQA path with a per-group expanded cache. The runtime picks the path that matches the target hardware - no retraining, no custom kernels - so a single set of GQLA weights pins the rooflines of both H100 (MQA-absorb, s_q=1) and H20 (GQA + MTP, s_q=2), while supporting up to 8-way zero-redundancy tensor parallelism on the GQA path. To avoid pretraining from scratch we extend TransMLA into TransGQLA, which converts a pretrained GQA checkpoint into a GQLA model; on LLaMA-3-8B it compresses the per-token KV cache to 28.125% of the GQA baseline on the MQA-absorb path while structurally preserving GQA-level traffic on the per-group path.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14454</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15250</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE</title>
|
<title>ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing</title>
|
||||||
<link>https://arxiv.org/abs/2605.14438</link>
|
<link>https://arxiv.org/abs/2605.15375</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14438.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juntong Wu, Jialiang Cheng, Qishen Yin, Yue Dai, Yuliang Yan, Fuyu Lv, Ou Dan, Li Yuan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and suboptimal inference latency. Existing acceleration methods either require costly retraining with architectural changes or suffer from severe performance drop at high sparsity due to train-inference mismatch. To address these limitations, we propose BEAM (Binary Expert Activation Masking), a novel method that learns token-adaptive expert selection via trainable binary masks. With a straight-through estimator and an auxiliary regularization loss, BEAM induces dynamic expert sparsity through end-to-end training while maintaining model capability. We further implement an efficient custom CUDA kernel for BEAM, ensuring seamless integration with the vLLM inference framework. Experiments show that BEAM retains over 98\% of the original model's performance while reducing MoE layer FLOPs by up to 85\%, achieving up to 2.5times faster decoding and 1.4times higher throughput, demonstrating its effectiveness as a practical, plug-and-play solution for efficient MoE inference.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Blaž Rolih, Matic Fučka, Filip Wolf, Luka Čehovin Zajc</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Remote sensing change detection (RSCD) aims to localise changes between two images of the same geographic region. In practice, change masks often follow region-level annotation conventions rather than purely local appearance differences, making them context-dependent and occasionally ambiguous. Most state-of-the-art methods utilise per-pixel discriminative classification, which produces a single prediction per input and fails to explicitly model the changed region as a coherent whole. A natural alternative is generative formulation, which can model a distribution of plausible masks, enabling sampling to capture ambiguity and encourage global consistency. However, existing generative RSCD approaches typically lag behind strong discriminative baselines due to the high computational cost of pixel-space generation and the complexity of their conditioning mechanisms. To address the limitations of prior discriminative and generative methods, we propose ChangeFlow, a generative framework that reformulates change detection as the synthesis of a change mask in latent space via rectified flow. ChangeFlow is guided by a structured yet lightweight conditioning signal, and its stochastic design naturally supports sampling-based prediction ensembling. Namely, aggregating multiple predicted change masks improves robustness, while sample agreement provides a practical confidence estimation that highlights ambiguous regions. Across four benchmarks, ChangeFlow achieves an average F1 of 80.4\%, improving by 1.3 points on average over the previous best method, while maintaining inference speed comparable to recent strong baselines. Project page: https://blaz-r.github.io/changeflow_cd</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14438</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15375</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance</title>
|
<title>Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards</title>
|
||||||
<link>https://arxiv.org/abs/2605.15012</link>
|
<link>https://arxiv.org/abs/2605.14539</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Yan, Alexander G. Schwing, Yu-Xiong Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has achieved great success in developing Large Language Models (LLMs) with chain-of-thought rollouts for many tasks such as math and coding. Nevertheless, RLVR struggles with sample efficiency on difficult problems where correct rollouts are hard to generate. Prior works propose to address this issue via demonstration-guided RLVR, i.e., to conduct Supervised FineTuning (SFT) when RL fails; however, SFT often requires a lot of data, which can be expensive to acquire. In this paper, we propose FEST, a FEw-ShoT demonstration-guided RLVR algorithm. It attains compelling results with only 128 demonstrations randomly selected from an SFT dataset. We find that three components are vital for the success: supervised signal, on-policy signal, and decaying weights on the few-shot SFT dataset to prevent overfitting from multiple-epoch training. On several benchmarks, FEST outperforms baselines with magnitudes less SFT data, even matching their performance with full dataset.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14539.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengjie Ren, Jie Lou, Boxi Cao, Xueru Wen, Hongyu Lin, Xianpei Han, Le Sun, Xing Yu, Yaojie Lu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit assignment, resulting in ambiguous optimization signals and underutilization of the useful information embedded in failed trajectories. To address this challenge, we propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision, without relying on any external signals. By jointly optimizing correction samples derived from the model's own failed attempts together with the standard RLVR objective, CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors. Extensive experiments across 11 benchmarks spanning mathematical reasoning and code generation demonstrate that CIPO consistently and significantly outperforms strong baselines in both reasoning and correction performance. Moreover, CIPO yields stronger pass@K gains, indicating that it improves the model's intrinsic reasoning capacity rather than merely redistributing probability mass over existing correct answers.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15012</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14539</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Ideology Prediction of German Political Texts</title>
|
<title>Auditing Agent Harness Safety</title>
|
||||||
<link>https://arxiv.org/abs/2605.14352</link>
|
<link>https://arxiv.org/abs/2605.14271</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14352.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sinclair Schneider, Florian Steuber, Joao A. G. Schneider, Gabi Dreo Rodosek</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Elections represent a crucial milestone in a nation's ongoing development. To better understand the political rhetoric from various movements, ranging from left to right, we propose a transformer-based model capable of projecting the political orientation of a text on a continuous left-to-right spectrum, represented by a normalized scalar d between -1 and 1. This approach enables analysts to focus on specific segments of the political landscape, such as conservatives, while excluding liberal and far-right movements. Such a task can only be achieved with multiclass classifiers, provided that the desired orientation is incorporated within one of their predefined classes. To determine the most suitable foundation model among 13 candidate transformers for this task, we constructed four distinct corpora. One corpus comprised annotated plenary notes from the German Bundestag, while another was based on an official online decision-making tool, Wahl-O-Mat. The third corpus consisted of articles from 33 newspapers, each identified by its political orientation, and the fourth included 535,200 tweets from 597 members of the 20th and 21st German Bundestag. To mitigate overfitting, we used two distinct corpora for training and two for testing, respectively. For in-domain performance, DeBERTa-large achieved the highest F1 score F1=0.844 as well as for the X (Twitter) out-of-domain test ACC=0.864. Regarding the newspaper out-of-domain test, Gemma2-2B excelled (MAE = 0.172). This study demonstrates that transformer models can recognize political framing in German news at the level of public opinion polls. Our findings suggest that both the model architecture and the availability of domain-specific training data can be as influential as model size for estimating political bias. We discuss methodological limitations and outline directions for improving the robustness of bias measurement.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14271.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhi Liu, Yichen Guo, Yepeng Liu, Yuzhe Yang, Qianqi Yan, Xuandong Zhao, Wenyue Hua, Sheng Liu, Sharon Li, Yuheng Bu, Xin Eric Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses unauthorized resources or leaks context to the wrong agent. Output-level evaluation cannot see these failures, yet most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination. The central question is whether the harness respects user intent, permission boundaries, and information-flow constraints throughout execution. To address this gap, we propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability, with a focus on multi-agent harnesses where these risks are most pronounced. We further introduce HarnessAudit-Bench, a benchmark of 210 tasks across eight real-world domains, instantiated in both single-agent and multi-agent configurations with embedded safety constraints. Evaluating ten harness configurations across frontier models and three multi-agent frameworks, we find that: (i) task completion is misaligned with safe execution, and violations accumulate with trajectory length; (ii) safety risks vary across domains, task types, and agent roles; (iii) most violations concentrate in resource access and inter-agent information transfer; and (iv) multi-agent collaboration expands the safety risk surface, while harness design sets the upper bound of safe deployment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14352</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14271</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LLM-based Detection of Manipulative Political Narratives</title>
|
<title>FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction</title>
|
||||||
<link>https://arxiv.org/abs/2605.14354</link>
|
<link>https://arxiv.org/abs/2605.15320</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sinclair Schneider, Florian Steuber, Gabi Dreo Rodosek</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context. To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing. The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters. Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie, Hao Li, Gordon Guocheng Qian, Jian Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline FLAME extraction. We further propose a three-stage training curriculum that achieves both broad generalization and high-fidelity reconstruction: (i) scalable pretraining on extensive monocular video data with over 1M identities to learn strong generalizable priors; (ii) multi-view fine-tuning on a small but high-quality dataset of 360-degree captures to enhance geometric fidelity and extreme-view awareness; and (iii) optional personalization that adapts to specific identities for maximum fidelity within 500 optimization steps. Extensive experiments demonstrate that FFAvatar sets a new standard for identity preservation, geometric consistency, and animation fidelity. On the NeRSemble benchmark, it outperforms the state-of-the-art LAM by a substantial 5.5 PSNR gain. Furthermore, FFAvatar enables real-time deployment, reconstructing avatars in 2 seconds without personalization and 10 seconds with personalization, while supporting 49 FPS animation on a single NVIDIA A100 GPU.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14354</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15320</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning</title>
|
<title>MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning</title>
|
||||||
<link>https://arxiv.org/abs/2605.14876</link>
|
<link>https://arxiv.org/abs/2605.14212</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14876.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanbo Cheng, Limin Lin, Ruo Zhang, Yicheng Pan, Jun Du</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from parameter scaling. While recent multi-step reasoning approaches show promise, they are hindered by ungrounded planning hallucinations lacking verification, monolithic post-hoc reflection, long-context optimization instabilities, and prohibitive inference latency. To overcome these bottlenecks, we propose the Closed-Loop Visual Reasoning (CLVR) framework, a comprehensive system that deeply couples visual-language logical planning with pixel-level diffusion generation. CLVR introduces an automated data engine with step-level visual verification to synthesize reliable reasoning trajectories, and proposes Proxy Prompt Reinforcement Learning (PPRL) to resolve long-context optimization instabilities by distilling interleaved multimodal histories into explicit reward signals for accurate causal attribution. Furthermore, to mitigate the severe latency bottleneck caused by iterative denoising, we propose Δ-Space Weight Merge (DSWM), a theoretically grounded method that fuses alignment weights with off-the-shelf distillation priors, reducing the per-step inference cost to just 4 NFEs without requiring expensive re-distillation. Extensive experiments demonstrate that CLVR outperforms existing open-source baselines across multiple benchmarks and approaches the performance of proprietary commercial models, unlocking general test-time scaling capabilities for complex visual generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14212.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaolun Zhang, Yujie Zhao, Nan Wang, Yiran Wu, Jiayu Chang, Yizhao Chen, Qingyun Wu, Jishen Zhao, Huazheng Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free test-time search or optimize the meta-level designer while keeping downstream execution agents frozen, which creating a frozen-executor ceiling and leaving the end-to-end training of self-designing and self-executing agentic models unexplored. To address this, we introduce MetaAgent-X, an end-to-end reinforcement learning framework that jointly optimizes automatic MAS design and execution. MetaAgent-X enables script-based MAS generation, execution rollout collection, and credit assignment for both designer and executor trajectories. To support stable and scalable optimization, we propose Executor Designer Hierarchical Rollout and Stagewise Co-evolution to improve training stability and expose the dynamics of designer-executor co-evolution. MetaAgent-X consistently outperforms existing automatic MAS baselines, achieving up to 21.7% gains. Comprehensive ablations show that both designer and executor improve throughout training, and that effective automatic MAS learning follows a stagewise co-evolution process. These results establish end-to-end trainable automatic MAS as a practical paradigm for building self-designing and self-executing agentic models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14876</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14212</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Dynamic Latent Routing</title>
|
<title>From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing</title>
|
||||||
<link>https://arxiv.org/abs/2605.14323</link>
|
<link>https://arxiv.org/abs/2605.15181</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14323.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangyuan Yu, Xin Su, Amir Abdullah</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the "search, select, update" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT. Mechanistic analyses and targeted code ablations show that DLR learns structured routing behaviors with distinct causal roles.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15181.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14323</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15181</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FutureSim: Replaying World Events to Evaluate Adaptive Agents</title>
|
<title>Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution</title>
|
||||||
<link>https://arxiv.org/abs/2605.15188</link>
|
<link>https://arxiv.org/abs/2605.15301</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15188.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shashwat Goel, Nikhil Chandak, Arvindh Arun, Ameya Prabhu, Steffen Staab, Moritz Hardt, Maksym Andriushchenko, Jonas Geiping</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we propose building grounded simulations that replay real-world events in the order they occurred. We build FutureSim, where agents forecast world events beyond their knowledge cutoff while interacting with a chronological replay of the world: real news articles arriving and questions resolving over the simulated period. We evaluate frontier agents in their native harness, testing their ability to predict world events over a three-month period from January to March 2026. FutureSim reveals a clear separation in their capabilities, with the best agent's accuracy being 25%, and many having worse Brier skill score than making no prediction at all. Through careful ablations, we show how FutureSim offers a realistic setting to study emerging research directions like long-horizon test-time adaptation, search, memory, and reasoning about uncertainty. Overall, we hope our benchmark design paves the way to measure AI progress on open-ended adaptation spanning long time-horizons in the real world.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Li, Jinyu Tian, Rili Feng, Yuqiao Du, Chong Zheng, Chenyu Wang, Chenchen Liu, Shihao Li, Xinping Lei, Yifan Yao, Weihao Xie, Letian Zhu, Jiaheng Liu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on static retrieval and discard the valuable problem-solving and debugging experience gained from previous tasks. To address this, we present Solvita, an agentic evolution framework that enables continuous learning without requiring weight updates to the underlying LLM. Solvita reorganizes problem-solving into a closed-loop system of strategy selection, program synthesis, certified supervision, and targeted hacking, executed by four specialized agents: Planner, Solver, Oracle, and Hacker. Crucially, each agent is paired with a trainable, graph-structured knowledge network. As the system operates, outcome signals, such as pass/fail verdicts, test certification quality, and adversarial vulnerabilities discovered by the Hacker, are recast as reinforcement learning updates to these network weights. This allows the agents to dynamically route future queries based on past successes and failures, effectively accumulating transferable reasoning experience over time. Evaluated across CodeContests, APPS, AetherCode, and live Codeforces rounds, Solvita establishes a new state-of-the-art among code-generation agents, outperforming existing multi-agent pipelines and nearly doubling the accuracy of single-pass baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15188</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15301</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image</title>
|
<title>ReactiveGWM: Steering NPC in Reactive Game World Models</title>
|
||||||
<link>https://arxiv.org/abs/2605.14984</link>
|
<link>https://arxiv.org/abs/2605.15256</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Qian, Zimin Xia, Changkun Liu, Shuailei Ma, Wen Wang, Zeran Ke, Bin Tan, Hang Zhang, Gui-Song Xia</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satellite-to-street data. We introduce Sat3DGen to address these fundamental challenges, which embodies a geometry-first methodology. This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy, explicitly countering the primary sources of geometric error. This geometry-centric strategy yields a dramatic leap in both 3D accuracy and photorealism. For validation, we first constructed a new benchmark by pairing the VIGOR-OOD test set with high-resolution DSM data. On this benchmark, our method improves geometric RMSE from 6.76m to 5.20m. Crucially, this geometric leap also boosts photorealism, reducing the Fréchet Inception Distance (FID) from sim40 to 19 against the leading method, Sat2Density++, despite using no extra tailored image-quality modules. We demonstrate the versatility of our high-quality 3D assets through diverse downstream applications, including semantic-map-to-3D synthesis, multi-camera video generation, large-scale meshing, and unsupervised single-image Digital Surface Model (DSM) estimation. The code has been released on https://github.com/qianmingduowan/Sat3DGen.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeqing Wang, Danze Chen, Zhaohu Xing, Zizhao Tong, Yinhan Zhang, Xingyi Yang, Yeying Jin</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merely as background pixels, these models cannot capture interactions between the player and NPC. In that sense, they act as passive video renderers rather than real simulation engines, lacking the physical understanding needed to model action-induced NPC reactivities. We introduce ReactiveGWM, a reactive game world model that synthesizes dynamic interactions between the player and NPC. Instead of entangling all interaction dynamics, ReactiveGWM explicitly decouples player controls from NPC behaviors. Player actions are injected into the diffusion backbone via a lightweight additive bias, while high-level NPC responses (e.g., Offense, Control, Defense) are grounded through cross-attention modules. Crucially, these modules learn a game-agnostic representation of interactive logic. This enables zero-shot strategy transfer: our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games. This instantly unlocks steerable NPC interactions without any domain-specific retraining. Evaluated on two Street Fighter games, ReactiveGWM maintains fine-grain player controllability while achieving robust, prompt-aligned NPC strategy adherence, paving the way for scalable, strategy-rich interaction with the NPC.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14984</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15256</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Aligning Latent Geometry for Spherical Flow Matching in Image Generation</title>
|
<title>InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation</title>
|
||||||
<link>https://arxiv.org/abs/2605.15193</link>
|
<link>https://arxiv.org/abs/2605.14333</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15193.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tuna Han Salih Meral, Kaan Oktay, Hidir Yesiltepe, Adil Kaan Akan, Pinar Yanardag</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Latent flow matching for image generation usually transports Gaussian noise to variational autoencoder latents along linear paths. Both endpoints, however, concentrate in thin spherical shells, and a Euclidean chord leaves those shells even when preprocessing aligns their radii. By decomposing each latent token into radial and angular components, we show through component-swap probes that decoded perceptual and semantic content is carried predominantly by direction, with radius contributing much less. We therefore project data latents onto a fixed token radius, use the radial projection of Gaussian noise as the spherical prior, finetune the decoder with the encoder frozen, and replace linear interpolation with spherical linear interpolation. The resulting geodesic paths stay on the sphere at every timestep, and their velocity targets are purely angular by construction. Under matched training, the method consistently improves class-conditional ImageNet-256 FID across different image tokenizers, leaves the diffusion architecture unchanged, and requires no auxiliary encoder or representation-alignment objective.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Jiayi Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attribute this gap to standard discrete-tokenizer objectives being weakly aligned with text legibility and facial fidelity, as these objectives typically optimize generic reconstruction while compressing diverse content uniformly. To address this, we propose InsightTok, a simple yet effective discrete visual tokenization framework that enhances text and face fidelity through localized, content-aware perceptual losses. With a compact 16k codebook and a 16x downsampling rate, InsightTok significantly outperforms prior tokenizers in text and face reconstruction without compromising general reconstruction quality. These gains consistently transfer to autoregressive image generation in InsightAR, producing images with clearer text and more faithful facial details. Overall, our results highlight the potential of specialized supervision in tokenizer training for advancing discrete image generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15193</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.14333</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation</title>
|
<title>MMSkills: Towards Multimodal Skills for General Visual Agents</title>
|
||||||
<link>https://arxiv.org/abs/2605.14269</link>
|
<link>https://arxiv.org/abs/2605.13527</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14269.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yidong Huang, Zun Wang, Han Lin, Dong-Ki Kim, Shayegan Omidshafiei, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general video quality, extending it to human motion remains bottlenecked by a reward signal that cannot reliably score motion realism. Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion, and often assign high scores to videos with floating bodies or physically implausible movements. To address this, we propose PhyMotion, a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility. Concretely, we recover SMPL body meshes from generated videos, retarget them onto a humanoid in the MuJoCo physics simulator, and evaluate the resulting motion along three axes: kinematic plausibility, contact and balance consistency, and dynamic feasibility. Each component provides a continuous and interpretable signal tied to a specific aspect of motion quality, allowing the reward to capture which aspects of motion are physically correct or violated. Experiments show that PhyMotion achieves stronger correlation with human judgments than existing reward formulations. These gains carry over to RL-based post-training, where optimizing PhyMotion leads to larger and more consistent improvements than optimizing existing rewards, improving motion realism across both autoregressive and bidirectional video generators under both automatic metrics and blind human evaluation (+68 Elo gain). Ablations show that the three axes provide complementary supervision signals, while the reward preserves overall video generation quality with only modest training overhead.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.13527.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kangning Zhang, Shuai Shao, Qingyao Li, Jianghao Lin, Lingyue Fu, Shijian Wang, Wenxiang Jiao, Yuan Lu, Weiwen Liu, Weinan Zhang, Yong Yu</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however, procedural knowledge is inherently multimodal: reuse depends not only on what operation to perform, but also on recognizing the relevant state, interpreting visual evidence of progress or failure, and deciding what to do next. We formalize this requirement as multimodal procedural knowledge and address three practical challenges: (I) what a multimodal skill package should contain; (II) where such packages can be derived from public interaction experience; and (III) how agents can consult multimodal evidence at inference time without excessive image context or over-anchoring to reference screenshots. We introduce MMSkills, a framework for representing, generating, and using reusable multimodal procedures for runtime visual decision making. Each MMSkill is a compact, state-conditioned package that couples a textual procedure with runtime state cards and multi-view keyframes. To construct these packages, we develop an agentic trajectory-to-skill Generator that transforms public non-evaluation trajectories into reusable multimodal skills through workflow grouping, procedure induction, visual grounding, and meta-skill-guided auditing. To use them, we introduce a branch-loaded multimodal skill agent: selected state cards and keyframes are inspected in a temporary branch, aligned with the live environment, and distilled into structured guidance for the main agent. Experiments across GUI and game-based visual-agent benchmarks show that MMSkills consistently improve both frontier and smaller multimodal agents, suggesting that external multimodal procedural knowledge complements model-internal priors.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14269</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.13527</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis</title>
|
<title>PhysBrain 1.0 Technical Report</title>
|
||||||
<link>https://arxiv.org/abs/2605.14392</link>
|
<link>https://arxiv.org/abs/2605.15298</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yucheng Shi, Zhenwen Liang, Kishan Panaganti, Dian Yu, Wenhao Yu, Haitao Mi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a data-generation loop into an environment-construction loop, where each artifact is a reusable executable object that samples instances, computes references, and scores responses. Whether this vision sustains improvement hinges on a single property: the environments must exhibit stable solve--verify asymmetry, the model must be able to write an oracle once that it cannot reliably execute in natural language on fresh instances. This asymmetry takes two complementary forms. Some tasks are algorithmically hard to reason through but trivial as code: a dynamic program or graph traversal, compiled once, yields unboundedly many calibrated instances. Others are intrinsically hard to solve but easy to verify, like planted subset-sum or constraint satisfaction. Both create a durable gap between proposing and solving that the policy cannot close by gaming the verifier, and it is this gap that keeps reward informative as the learner improves. We instantiate this view in EvoEnv, a single-policy generator, solver method that synthesizes Python environments from ten seeds and admits them only after staged validation, semantic self-review, solver-relative difficulty calibration, and novelty checks. The strongest evidence comes from the already-strong regime: on Qwen3-4B-Thinking, fixed public-data RLVR and fixed hand-crafted environment RLVR reduce the average, while EvoEnv improves it from 72.4 to 74.8, a relative gain of 3.3%. Stable self-improvement, we suggest, depends not on producing more synthetic data, but on models learning to construct worlds whose difficulty stays structurally beyond their own reach.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15298.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijie Lian, Bin Yu, Xiaopeng Lin, Changti Wu, Hang Yuan, Xiaolin Hu, Zhaolong Shen, Yuzhuo Miao, Haishan Liu, Yuxuan Tian, Yukun Shi, Cong Huang, Kai Chen</p><p><b>Upvotes:</b> 129</p><p><b>Summary:</b> Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a complementary route: converting large-scale human egocentric video into structured physical commonsense supervision before robot adaptation. Our data engine extracts scene elements, spatial dynamics, action execution, and depth-aware relations, then turns them into question-answer supervision for training PhysBrain VLMs. The resulting physical priors are further transferred to VLA policies through a capability-preserving and language-sensitive adaptation design. Across multimodal QA benchmarks and embodied control benchmarks, including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa, PhysBrain 1.0 achieves SOTA results and shows especially strong out-of-domain performance on SimplerEnv. These results suggest that scaling physical commonsense from human interaction video can provide an effective bridge from multimodal understanding to robot action.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14392</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15298</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Does Synthetic Layered Design Data Benefit Layered Design Decomposition?</title>
|
<title>Look Before You Leap: Autonomous Exploration for LLM Agents</title>
|
||||||
<link>https://arxiv.org/abs/2605.15167</link>
|
<link>https://arxiv.org/abs/2605.16143</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15167.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kam Man Wu, Haolin Yang, Qingyu Chen, Yihu Tang, Jingye Chen, Qifeng Chen</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recent advances in image generation have made it easy to produce high-quality images. However, these outputs are inherently flattened, entangling foreground elements, background, and text within a fixed canvas. As a result, flexible post-generation editing remains challenging, revealing a clear last-mile gap toward practical usability. Existing approaches either rely on scarce proprietary layered assets or construct partially synthetic data from limited structural priors. However, both strategies face fundamental challenges in scalability. In this work, we investigate whether pure synthetic layered data can improve graphic design decomposition. We make the assumption that, in graphic design, effective decomposition does not require modeling inter-layer dependencies as precisely as in natural-image composition, since design elements are often intentionally arranged as modular and semantically separable components. Concretely, we conduct a data-centric study based on CLD baseline, which is a state-of-the-art layer decomposition framework. Based on the baseline, we construct our own synthetic dataset, SynLayers, generate textual supervision using vision language models, and automate inference inputs with VLM-predicted bounding boxes. Our study reveals three key findings: (1) even training with purely synthetic data can outperform non-scalable alternatives such as the widely used PrismLayersPro dataset, demonstrating its viability as a scalable and effective substitute; (2) performance consistently improves with increased training data scale, while gains begin to saturate at around 50K samples; and (3) synthetic data enables balanced control over layer-count distributions, avoiding the layer-count imbalance commonly observed in real-world datasets. We hope this data-centric study encourages broader adoption of synthetic data as a practical foundation for layered design editing systems.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Ye, Wentao Shi, Yuxin Liu, Yu Wang, Zhengzhou Cai, Yaorui Shi, Qi Gu, Xunliang Cai, Fuli Feng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-specific information. We identify autonomous exploration as a critical yet underexplored capability for building adaptive agents. To formalize and quantify this capability, we introduce Exploration Checkpoint Coverage, a verifiable metric that measures how broadly an agent discovers key states, objects, and affordances. Our systematic evaluation reveals that agents trained with standard task-oriented reinforcement learning consistently exhibit narrow and repetitive behaviors that impede downstream performance. To address this limitation, we develop a training strategy that interleaves task-execution rollouts and exploration rollouts, with each type of rollout optimized by its corresponding verifiable reward. Building on this training strategy, we propose the Explore-then-Act paradigm, which decouples information-gathering from task execution: agents first utilize an interaction budget to acquire grounded environmental knowledge, then leverage it for task resolution. Our results demonstrate that learning to systematically explore is imperative for building generalizable and real-world-ready agents.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15167</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.16143</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO</title>
|
<title>Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design</title>
|
||||||
<link>https://arxiv.org/abs/2605.15190</link>
|
<link>https://arxiv.org/abs/2605.15871</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanzuo Lu, Ronglai Zuo, Jiankang Deng</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content. Distilling such generators from high-fidelity bidirectional teachers yields competitive few-step models, yet a persistent gap between the history distributions encountered during training and those arising at inference constrains generation quality over long horizons. We introduce the Real-time Autoregressive Video Extrapolation Network (RAVEN), a training-time test framework that repacks each self rollout into an interleaved sequence of clean historical endpoints and noisy denoising states. This formulation aligns training attention with inference-time extrapolation and allows downstream chunk losses to supervise the history representations on which future predictions depend. We further propose Consistency-model Group Relative Policy Optimization (CM-GRPO), which reformulates a consistency sampling step as a conditional Gaussian transition and applies online Reinforcement Learning (RL) directly to this kernel, avoiding the Euler-Maruyama auxiliary process adopted in prior flow-model RL formulations. Experiments demonstrate that RAVEN surpasses recent causal video distillation baselines across quality, semantic, and dynamic degree evaluations, and that CM-GRPO provides further gains when combined with RAVEN.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alberto Pepe, Chien-Yu Lin, Despoina Magka, Bilge Acun, Yannan Nellie Wu, Anton Protopopov, Carole-Jean Wu, Yoram Bachrach</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Compose for high-level architecture search, and AIRA-Design for low-level mechanistic implementation. AIRA-Compose uses 11 agents to explore fundamental computational primitives under a 24-hour budget. Agents evaluate million-parameter candidates, extrapolating top designs to 350M, 1B, and 3B scales. This yields 14 architectures across two families: AIRAformers (Transformer-based) and AIRAhybrids (Transformer-Mamba). Pre-trained at 1B scale, these consistently outperform Llama 3.2 and Composer-found baselines. On downstream tasks, AIRAformer-D and AIRAhybrid-D improve accuracy by 2.4% and 3.8% over Llama 3.2. Furthermore, AIRA-Compose finds models with highly efficient scaling frontiers: AIRAformer-C scales 54% and 71% faster than Llama 3.2 and Composer's best Transformer, while AIRAhybrid-C outscales Nemotron-2 by 23% and Composer's best hybrid by 37%. AIRA-Design tasks 20 agents with writing novel attention mechanisms for long-range dependencies and high-performing training scripts. On the Long Range Arena benchmark, agent-designed architectures reach within 2.3% and 2.6% of human state-of-the-art on document matching and text classification. On the Autoresearch benchmark, Greedy Opus 4.5 achieves 0.968 validation bits-per-byte under a fixed time budget, surpassing the published minimum. Together, these frameworks show AI agents can autonomously discover architectures and algorithmic optimizations matching or surpassing hand-designed baselines. This establishes a powerful paradigm for discovering next-generation foundation models, marking a clear step toward recursive self-improvement.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15190</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15871</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ViMU: Benchmarking Video Metaphorical Understanding</title>
|
<title>WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes</title>
|
||||||
<link>https://arxiv.org/abs/2605.14607</link>
|
<link>https://arxiv.org/abs/2605.15843</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Li, Xinchao Wang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content directly presented, while the other is the subtext beneath it-the implicit ideas and intentions the creator seeks to convey through the medium. Likewise, since video technologies became widely adopted, video has served not only as a powerful tool for recording and communicating visual information, but also as a vehicle for emotions, attitudes, and social meanings that are often difficult to articulate explicitly. Thus, the true meaning of many videos does not reside solely in what is shown on screen; it is often embedded in context, style of expression, and the viewer's social experience. Some forms of such video subtext are humorous, while others carry irony, mockery, or criticism. These implicit meanings can also be interpreted very differently across cultural backgrounds and social groups. However, most existing video understanding models still focus primarily on literal visual comprehension, such as recognizing objects, actions, or temporal relations, and lack a systematic ability to understand the metaphorical, ironic, and social meanings embedded in videos. To bridge this gap, we introduce ViMU, the first benchmark designed to systematically evaluate the subtext understanding capabilities of frontier models in videos. ViMU assesses whether video understanding models can go beyond literal perception to infer implicit meaning while grounding their interpretations in multimodal evidence and answering both open-ended and multiple-choice questions. Importantly, all questions are designed to be hint-free, ensuring that no key evidence is disclosed to models before answering.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15843.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jichen Hu, Jiawei Guo, Jiazhong Cen, Chen Yang, Sikuang Li, Wei Shen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent 3D world modeling systems based on generative scene synthesis, such as Marble, can create coherent and explorable 3D environments, yet their outputs are typically static monolithic assets with limited editability and physical interaction. This restricts their use in immersive content creation and embodied simulation, where generated worlds must be actively modified and manipulated. To tackle this challenge, we present WorldAct, a framework that converts static generated 3D worlds into editable and interaction-ready scenes. WorldAct uses a multimodal agent to guide scene decomposition, identify actionable objects, reconstruct geometrically aligned object-level meshes for interaction, and restore the residual background via 3D inpainting. The resulting scenes support object-level editing, collision-aware manipulation, and embodied task execution while preserving global scene coherence. Experiments show that WorldAct enables richer interaction scenarios than the original generated scenes, suggesting a practical path toward editable and interactive 3D world models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14607</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15843</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation</title>
|
<title>Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models</title>
|
||||||
<link>https://arxiv.org/abs/2605.14712</link>
|
<link>https://arxiv.org/abs/2605.15961</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijie Lian, Bin Yu, Xiaopeng Lin, Zhaolong Shen, Laurence Tianruo Yang, Yurun Jin, Haishan Liu, Changti Wu, Hang Yuan, Cong Huang, Kai Chen</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15961.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabian Morelli, Arnas Uselis, Ankit Sonthalia, Seong Joon Oh</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution shifts. Recent approaches have attempted to mitigate this trade-off, but often rely on computationally expensive text-guidance. We propose a novel method for robust fine-tuning, SAE-FT, which operates only on the model's visual representations. SAE-FT regularizes changes to these representations by penalizing the addition and removal of semantically meaningful features identified by a Sparse Autoencoder trained on the pre-trained model. This constraint prevents catastrophic forgetting and makes the fine-tuning process interpretable, enabling direct analysis of semantic changes. SAE-FT is both mechanistically transparent and computationally efficient, matching or exceeding state-of-the-art performance on ImageNet and its associated distribution shift benchmarks. Code is publicly available at: https://github.com/Fabian-Mor/sae-ft.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14712</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15961</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Orchard: An Open-Source Agentic Modeling Framework</title>
|
<title>Efficient Image Synthesis with Sphere Latent Encoder</title>
|
||||||
<link>https://arxiv.org/abs/2605.15040</link>
|
<link>https://arxiv.org/abs/2605.15592</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, Xiao Yu, Rui Yang, Tao Ge, Alessandrio Sordoni, Xingdi Yuan, Yelong Shen, Pengcheng He, Tong Zhang, Zhou Yu, Jianfeng Gao</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning, reasoning, tool use, and multi-turn interaction with environments. Despite major investment, open research remains constrained by infrastructure and training gaps. Many high-performing systems rely on proprietary codebases, models, or services, while most open-source frameworks focus on orchestration and evaluation rather than scalable agent training. We present Orchard, an open-source framework for scalable agentic modeling. At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management across task domains, agent harnesses, and pipeline stages. On top of Orchard Env, we build three agentic modeling recipes. Orchard-SWE targets coding agents. We distill 107K trajectories from MiniMax-M2.5 and Qwen3.5-397B, introduce credit-assignment SFT to learn from productive segments of unresolved trajectories, and apply Balanced Adaptive Rollout for RL. Starting from Qwen3-30B-A3B-Thinking, Orchard-SWE achieves 64.3% on SWE-bench Verified after SFT and 67.5% after SFT+RL, setting a new state of the art among open-source models of comparable size. Orchard-GUI trains a 4B vision-language computer-use agent using only 0.4K distilled trajectories and 2.2K open-ended tasks. It achieves 74.1%, 67.0%, and 64.0% success rates on WebVoyager, Online-Mind2Web, and DeepShop, respectively, making it the strongest open-source model while remaining competitive with proprietary systems. Orchard-Claw targets personal assistant agents. Trained with only 0.2K synthetic tasks, it achieves 59.6% pass@3 on Claw-Eval and 73.9% when paired with a stronger ZeroClaw harness. Collectively, these results show that a lightweight, open, harness-agnostic environment layer enables reusable agentic data, training recipes, and evaluations across domains.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tung Do, Thuan Hoang Nguyen, Hao Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15040</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15592</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models</title>
|
<title>Unlocking Dense Metric Depth Estimation in VLMs</title>
|
||||||
<link>https://arxiv.org/abs/2605.15055</link>
|
<link>https://arxiv.org/abs/2605.15876</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15055.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quanhao Li, Junqiu Yu, Kaixun Jiang, Yujie Wei, Zhen Xing, Pandeng Li, Ruihang Chu, Shiwei Zhang, Yu Liu, Zuxuan Wu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15876.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanxun Yu, Xuan Qu, Yuxin Wang, Jianke Zhu, Lei ke</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability. By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm with a two-stage schedule, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass. We further introduce a unified indoor-outdoor metric depth benchmark in a VLM-compatible format. Experiments show that DepthVLM significantly outperforms existing VLMs with higher inference efficiency, surpasses leading pure vision models, and improves complex 3D spatial reasoning, moving toward a truly unified foundation model. All code and checkpoints will be publicly released.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15055</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15876</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale</title>
|
<title>PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control</title>
|
||||||
<link>https://arxiv.org/abs/2605.14445</link>
|
<link>https://arxiv.org/abs/2605.15963</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runyuan He, Qiuyang Mang, Shang Zhou, Kaiyuan Liu, Hanchen Li, Huanzhi Mao, Qizheng Zhang, Zerui Li, Bo Peng, Lufeng Cheng, Tianfu Fu, Yichuan Wang, Wenhao Chai, Jingbo Shang, Alex Dimakis, Joseph E. Gonzalez, Alvin Cheung</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming. Open-ended coding remains a weak spot for LLMs, largely because open-ended training problems are scarce and expensive to construct. Our goal is to synthesize open-ended coding problems at scale to train stronger LLM coders. We introduce FrontierSmith, an automated system for iteratively evolving open-ended problems from existing closed-ended coding tasks. Starting from competitive programming problems, FrontierSmith generates candidate open-ended variants by changing the problems'goals, restricting outputs, and generalizing inputs. It then uses a quantitative idea divergence metric to select problems that elicit genuinely diverse approaches from different solvers. Agents then generate test cases and verifiers for the surviving candidates. On two open-ended coding benchmarks, training on our synthesized data yields substantial gains over the base models: Qwen3.5-9B improves by +8.82 score on FrontierCS and +306.36 (Elo-rating-based performance) on ALE-bench; Qwen3.5-27B improves by +12.12 and +309.12, respectively. The synthesized problems also make agents take more turns and use more tokens, similar to human-curated ones, suggesting that closed-ended seeds can be a practical starting point for long-horizon coding data.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15963.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Wei, Xi Bai, Shan Liu, Caijun Jia, Zheng Sun, Xinglong Xu, Siyuan Li, Linzhuang Sun, Bihui Yu, Conghui He, Cheng Tan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a forgiving region-tolerant paradigm, where many nearby pixels inside the same component remain valid. Precise geometric construction breaks this assumption: actions must land on points in continuous canvas space rather than tolerant regions. Because geometric primitives carry ontological dependencies, a local coordinate error can induce cascading topological failures that distort downstream objects and invalidate the final construction. We identify this regime as precision-sensitive GUI tasks, requiring point-level accuracy, geometry-aware verification, and robustness to dependency-driven error propagation. To benchmark it, we introduce PAGE Bench, with 4,906 problems and over 224K process-supervised, pixel-level GUI actions. We further propose PAGER, a topology-aware agent that decomposes construction into dependency-structured planning and pixel-level execution. Pixel-grounded supervised tuning establishes executable action grammar, while precision-aligned reinforcement learning mitigates rollout-induced exposure bias through state-conditioned geometric feedback. Experiments reveal a pronounced Semantic-Execution Gap: general multimodal models can exceed 88% action type accuracy yet remain below 6% task success. PAGER closes this gap, delivering 4.1x higher task success than the strongest evaluated general baseline and raising step success rate from below 9% for GUI-specialized agents to over 62%, establishing a new state of the art for point-precise GUI control.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14445</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15963</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both</title>
|
<title>CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage</title>
|
||||||
<link>https://arxiv.org/abs/2605.15198</link>
|
<link>https://arxiv.org/abs/2605.15597</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15198.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Guo, Rain Liu, Xinyan Chen, Pheng-Ann Heng</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is computationally expensive and architecturally non-trivial. Recent alternatives include agentic reasoning through code or tool calls, and latent reasoning with learnable hidden embeddings. However, agentic methods incur context-switching latency from external execution, while latent methods lack task generalization and are difficult to train with autoregressive parallelization. To combine their strengths while mitigating their limitations, we propose ATLAS, a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit. Each functional token is associated with an internalized visual operation, yet requires no visual supervision and remains a standard token in the tokenizer vocabulary, which can be generated via next-token prediction. This design avoids verbose intermediate visual content generation, while preserving compatibility with the vanilla scalable SFT and RL training, without architectural or methodological modifications. To further address the sparsity of functional tokens during RL, we introduce Latent-Anchored GRPO (LA-GRPO), which stabilizes the training by anchoring functional tokens with a statically weighted auxiliary objective, providing stronger gradient updates. Extensive experiments and analyses demonstrate that ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability. We hope ATLAS offers a new paradigm inspiring future visual reasoning research.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15597.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Liu, Jungang Li, Jieming Yu, Xinglin Yu, Zihao Dongfang, Zongjian Ding, Kaifeng Ding, Yi Yang, Lidong Chen, Yang Zou, Shunwen Bai, Jiahuan Zhang, Haoran Huang, Shan Huang, Yudong Gao, Mingjun Cheng</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, source-specific rendering policies yield heterogeneous annotations, and sparse heuristics may miss important regions or introduce depth-inconsistent observations. We study how to convert 3D assets into sparse panoramic RGB-D-pose data that preserves complete scene coverage with low redundancy and auditable provenance. We propose COVER (Coverage-Oriented Viewpoint curation with ERP Range-depth warping), a training-free ERP viewpoint curator that projects geometry observed from selected views into candidate ERP probes, scores incremental coverage, and penalizes depth conflicts. Under bounded proxy error, its greedy coverage proxy preserves the standard coverage-style approximation behavior up to an additive error term. Using COVER, we build CM-EVS (Coverage-curated Metric ERP View Set), a panoramic RGB-D-pose dataset with 36,373 curated ERP frames from 1,275 indoor scenes across Blender indoor, HM3D, and ScanNet++, complemented by outdoor panoramas from TartanGround and OB3D re-encoded into the same schema. Each frame provides full-sphere RGB, metric range depth, calibrated pose; COVER-produced indoor frames include per-step provenance logs. With a median of only 25 frames per indoor scene, CM-EVS covers all 13 unified room types while maintaining compact scene-level coverage. Experiments show that COVER improves the coverage-conflict trade-off, making CM-EVS a sparse, compact, and auditable RGB-D-pose resource for geometry-consistent panoramic 3D learning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15198</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15597</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction</title>
|
<title>Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR</title>
|
||||||
<link>https://arxiv.org/abs/2605.15186</link>
|
<link>https://arxiv.org/abs/2605.15726</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaixin Zhu, Yiwen Tang, Yifan Yang, Renrui Zhang, Bohan Zeng, Ziyu Guo, Ruichuan An, Zhou Liu, Qizhi Chen, Delin Qu, Jaehong Yoon, Wentao Zhang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong performance in static scene perception, these models remain limited in responding to dynamic human instructions, which restricts their use in interactive applications. Existing editing methods typically rely on a 2D-lifting strategy, where individual views are edited independently and then lifted back into 3D space. This indirect pipeline often leads to blurry textures and inconsistent geometry, as 2D editors lack the spatial awareness required to preserve structure across viewpoints. To address these limitations, we propose VGGT-Edit, a feed-forward framework for text-conditioned native 3D scene editing. VGGT-Edit introduces depth-synchronized text injection to align semantic guidance with the backbone's spatial poses, ensuring stable instruction grounding. This semantic signal is then processed by a residual transformation head, which directly predicts 3D geometric displacements to deform the scene while preserving background stability. To ensure high-fidelity results, we supervise the framework with a multi-term objective function that enforces geometric accuracy and cross-view consistency. We also construct the DeltaScene Dataset, a large-scale dataset generated through an automated pipeline with 3D agreement filtering to ensure ground-truth quality. Experiments show that VGGT-Edit substantially outperforms 2D-lifting baselines, producing sharper object details, stronger multi-view consistency, and near-instant inference speed.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chanuk Lee, Sangwoo Park, Minki Kang, Sung Ju Hwang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally expensive, and existing approaches that modify the optimization objective provide limited control over what is explored. In this work, we propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR. Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts to induce diverse reasoning trajectories without relying on expensive oracle supervision. To effectively learn from such structured exploration, we further propose a unified objective, which decomposes the reward signal into inter- and intra-context components and incorporates a distillation objective to transfer discovered behaviors back to the base policy. Empirically, NudgeRL outperforms standard GRPO with up to 8 times larger rollout budgets, while outperforming oracle-guided RL baseline on average across five challenging math benchmarks. These results demonstrate that structured, context-driven exploration can serve as an efficient and scalable alternative to both brute-force rollout scaling and feasibility-oriented methods based on privileged information. Our code is available at https://github.com/tally0818/NudgeRL.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15186</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15726</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video</title>
|
<title>Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization</title>
|
||||||
<link>https://arxiv.org/abs/2605.15182</link>
|
<link>https://arxiv.org/abs/2605.15980</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15182.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Wang, Tong He</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn camera-specific conditioning through camera encoders, control branches, or attention and positional-encoding modifications, which often require post-training on large-scale camera-annotated videos. Training-free alternatives avoid such post-training, but often shift the cost to test-time optimization or extra denoising-time guidance. We propose Warp-as-History, a simple interface that turns camera-induced warps into camera-warped pseudo-history with target-frame positional alignment and visible-token selection. Given a target camera trajectory, we construct camera-warped pseudo-history from past observations and feed it through the model's visual-history pathway. Crucially, we align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations. Without any training, architectural modification, or test-time optimization, this interface reveals a non-trivial zero-shot capability of a frozen video generation model to follow camera trajectories. Moreover, lightweight offline LoRA finetuning on only one camera-annotated video further improves this capability and generalizes to unseen videos, improving camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation. Extensive experiments on diverse datasets confirm the effectiveness of our method.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxuan He, Siming Fu, Zeyue Xue, Weijie Wang, Ruizhe He, Yuming Li, Dacheng Yin, Shuai Dong, Haoyang Huang, Hongfa Wang, Nan Duan, Bohan Zhuang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15182</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15980</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems</title>
|
<title>DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo</title>
|
||||||
<link>https://arxiv.org/abs/2605.14892</link>
|
<link>https://arxiv.org/abs/2605.16257</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14892.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihao Qi, Jie Ma, Rui Xing, Wei Guo, Xiao Huang, Zhitao Gao, Jianhao Deng, Jun Liu, Lingling Zhang, Bifan Wei, Boqian Yang, Pinghui Wang, Jianwen Sun, Jing Tao, Yaqiang Wu, Hui Liu, Yu Yao, Tongliang Liu</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination also amplifies a less explored risk: errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structural self-improvement. Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined. This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement. For each stage, we provide systematic taxonomies and formally characterize the dependencies between adjacent stages, revealing how each stage both depends on and constrains the next. Beyond synthesizing existing work, we identify open challenges at stage boundaries and propose a cross-stage research agenda for closed-loop multi-agent systems capable of continuously diagnosing failures, reorganizing structures, and refining agent behaviors, extending current coordination frameworks toward more self-organizing forms of collective intelligence. By bridging these previously fragmented research threads, this survey aims to offer both a systematic reference and a conceptual roadmap toward autonomous, self-improving multi-agent intelligence.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.16257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanwen Wang, Weizhi Zhao, Xiangyu Wang, Siyuan Huang, He Lin, Boyuan Zheng, Rongtao Xu, Gang Wang, Yao Mu, He Wang, Lue Fan, Hongsheng Li, Zhaoxiang Zhang, Tieniu Tan</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, existing dexterous benchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14892</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.16257</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning</title>
|
<title>FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization</title>
|
||||||
<link>https://arxiv.org/abs/2605.14386</link>
|
<link>https://arxiv.org/abs/2605.15824</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14386.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Junghoon Shin, Minseo Kim</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust parameter; and (iii) an Architecture Mapper that enables cross-architecture breeding between heterogeneous model families. Empirically, the flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training. Across scales from 4B to 35B parameters, Darwin models consistently improve over their parents, support recursive multi-generation evolution, and enable a training-free evolutionary merge that combines Transformer- and Mamba-based components. Together, the Darwin Family demonstrates that diagnostic-guided evolutionary merging is a practical and reproducible alternative to costly post-training pipelines for reasoning-centric language models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15824.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quanjian Song, Yefeng Shen, Mengting Chen, Hao Sun, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Liujuan Cao</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference-garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and consistent long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180times faster than existing baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14386</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15824</guid>
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.15128</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15128.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghao Guo, Qingyue Jiao, Zeru Shi, Yihao Quan, Boxuan Zhang, Danrui Li, Liwei Che, Wujiang Xu, Shilong Liu, Zirui Liu, Mubbasir Kapadia, Vladimir Pavlovic, Jiang Liu, Mengdi Wang, Yiyu Shi, Dimitris N. Metaxas, Ruixiang Tang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only captions or textual traces, allowing answers to be inferred without preserving the fine-grained visual evidence. Meanwhile, harder cases that require reasoning over changing visual states are largely absent. Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures how retrieved evidence must be used (from single evidence to evolutionary synthesis). Under this framework, we construct a new benchmark across 8 life-scenario tasks, with ablation-driven validation gates for assessing answerability, shortcut resistance, visual necessity, and reasoning structure. By evaluating 13 memory methods across 4 VLM backbones, we show that current architectures still struggle to preserve fine-grained visual details and reason about state changes over time. Our findings show that long-term multimodal memory depends on evidence routing, temporal tracking, and detail extraction.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15128</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.15178</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyi Zhu, Haozhe Liu, Yuyang Zhao, Tian Ye, Junsong Chen, Jincheng Yu, Tong He, Song Han, Enze Xie</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise 6-DoF trajectory adherence. (3) Two-Stage Generation Pipeline applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. (4) Robust Annotation Pipeline extracts accurate metric-scale 6-DoF camera poses from public videos to yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only sim213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at 36times higher throughput for scalable world modeling.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15178</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.14906</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.14906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiyu Ren, Zhaowei Wang, Yiming Du, Zhongwei Xie, Chi Liu, Xinlin Yang, Haoyue Feng, Wenjun Pan, Tianshi Zheng, Baixuan Xu, Zhengnan Li, Yangqiu Song, Ginny Wong, Simon See</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and memory-augmented agents. However, no existing benchmark conducts a systematic comparison of the two on questions that genuinely require multimodal evidence. To close this gap, we introduce MEMLENS, a comprehensive benchmark for memory in multimodal multi-session conversations, comprising 789 questions across five memory abilities (information extraction, multi-session reasoning, temporal reasoning, knowledge update, and answer refusal) at four standard context lengths (32K-256K tokens) under a cross-modal token-counting scheme. An image-ablation study confirms that solving MEMLENS requires visual evidence: removing evidence images drops two frontier LVLMs below 2% accuracy on the 80.4% of questions whose evidence includes images. Evaluating 27 LVLMs and 7 memory-augmented agents, we find that long-context LVLMs achieve high short-context accuracy through direct visual grounding but degrade as conversations grow, whereas memory agents are length-stable but lose visual fidelity under storage-time compression. Multi-session reasoning caps most systems below 30%, and neither approach alone solves the task. These results motivate hybrid architectures that combine long-context attention with structured multimodal retrieval. Our code is available at https://github.com/xrenaf/MEMLENS.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.14906</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Self-Distilled Agentic Reinforcement Learning</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.15155</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15155.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang, Jinyang Wu, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfect skills retrieval or utilization. We introduce SDAR (Self-Distilled Agentic Reinforcement Learning), which treats OPSD as a gated auxiliary objective while keeping RL as the primary optimization backbone. SDAR maps detached token-level signals into a sigmoid gate, strengthening distillation on teacher-endorsed positive-gap tokens and softly attenuating negative teacher rejections. Across the Qwen2.5 and Qwen3 families on ALFWorld, WebShop, and Search-QA, SDAR substantially improves over GRPO (+9.4% on ALFWorld, +7.0% on Search-QA, +10.2% on WebShop-Acc), avoids the instability of naive GRPO+OPSD, and consistently outperforms hybrid RL--OPSD baselines across model scales.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15155</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.15141</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Min Zhao, Hongzhou Zhu, Kaiwen Zheng, Zihan Zhou, Bokai Yan, Xinyuan Li, Xiao Yang, Chongxuan Li, Jun Zhu</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies are either target-misaligned, incapable of few-step generation, or too costly to scale. We propose Causal Forcing++, a principled and scalable pipeline that uses causal consistency distillation (causal CD) for few-step AR initialization. The core idea is that causal CD learns the same AR-conditional flow map as causal ODE distillation, but obtains supervision from a single online teacher ODE step between adjacent timesteps, avoiding the need to precompute and store full PF-ODE trajectories. This makes the initialization both more efficient and easier to optimize. The resulting pipeline, \ours, surpasses the SOTA 4-step chunk-wise Causal Forcing under the \textbf{frame-wise 2-step setting} by 0.1 in VBench Total, 0.3 in VBench Quality, and 0.335 in VisionReward, while reducing first-frame latency by 50\% and Stage 2 training cost by sim4times. We further extend the pipeline to action-conditioned world model generation in the spirit of Genie3. Project Page: https://github.com/thu-ml/Causal-Forcing and https://github.com/shengshu-ai/minWM .</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.15141</guid>
|
|
||||||
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user