bot: update RSS feed
This commit is contained in:
github-actions[bot]
460
feed.xml
460
feed.xml
@@ -7,349 +7,279 @@
|
|||||||
<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>Wed, 27 May 2026 00:21:36 +0000</lastBuildDate>
|
<lastBuildDate>Thu, 28 May 2026 00:19:48 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Towards Customized Multimodal Role-Play</title>
|
<title>EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration</title>
|
||||||
<link>https://arxiv.org/abs/2605.08129</link>
|
<link>https://arxiv.org/abs/2605.15042</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.08129.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Tang, Jianzong Wu, Qingyu Shi, Ye Tian, Aixi Zhang, Hao Jiang, Jiangning Zhang, Yunhai Tong</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new task, Customized Multimodal Role-Play (CMRP). We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions. Building on a unified model, we devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-specific group relative policy optimization (Character-GRPO). Given only 10 images plus corresponding interaction examples, the model acquires the target character and exhibits coherent persona, style, and visual identity in both generated text and images. This process takes about 100 GPU hours. Experiments on the RoleScape-20 dataset show that the proposed method substantially outperforms prior approaches. Ablation studies further validate the effectiveness of our cross-modal consistency design and few-shot customization strategy. We argue that CMRP, coupled with unified modeling, provides a basis for next-generation characterful and immersive interactive agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.15042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wuyang Li, Yang Gao, Mariam Hassan, Lan Feng, Wentao Pan, Po-Chien Luan, Alexandre Alahi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remains challenging because highly dynamic human motion must be synthesized against relatively static environments, making chunk-based generation prone to accumulated drift: (i) low-level quality drift, such as progressive degradation of static backgrounds, and (ii) high-level semantic drift, such as inconsistent character identity and view-dependent attributes. To address this issue, EverAnimate restores drifted flow trajectories by anchoring generation to a persistent latent context memory, consisting of two complementary mechanisms. (i) Persistent Latent Propagation maintains a context memory across chunks to propagate identity and motion in latent space while mitigating temporal forgetting. (ii) Restorative Flow Matching introduces an implicit restoration objective during sampling through velocity adjustment, improving within-chunk fidelity. With only lightweight LoRA tuning, EverAnimate outperforms state-of-the-art long-animation methods in both short- and long-horizon settings: at 10 seconds, it improves PSNR/SSIM by 8%/7% and reduces LPIPS/FID by 22%/11%; at 90 seconds, the gains increase to 15%/15% and 32%/27%, respectively.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.08129</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.15042</guid>
|
||||||
<pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation</title>
|
<title>Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration</title>
|
||||||
<link>https://arxiv.org/abs/2605.10988</link>
|
<link>https://arxiv.org/abs/2605.17423</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.10988.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutszyuk Wong, Wentai Wu, Yuen-Ying Yeung, Weiwei Lin</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instance-level annotations are prohibitively expensive, posing great difficulties to fine-grained anomaly localization. To address this challenge, we propose LogMILP (Log anomaly localization based on Multi-Instance Learning enhanced by prototypes and Perturbation), a weakly supervised framework that enables both bag-level anomaly detection and instance-level anomaly localization using only bag-level labels. Our method guides the model to pinpoint the critical log entries using prototype-guided structural modeling with counterfactual perturbation consistency regularization, thereby improving localization reliability and interpretability under coarse-grained supervision. Experimental results on three public datasets demonstrate that LogMILP achieves competitive detection performance while yielding significantly more reliable instance-level localization. Our code is open-sourced at https://github.com/YUK1207/LogMILP.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.17423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiren Song, Huilin Zhong, Kevin Qinghong Lin, Haofan Wang, Mike Zheng Shou</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We study series-level cinematic remaking, a long-horizon video-to-video generation problem that localizes full episodes or films via stylization or actor replacement while strictly preserving narrative structure, motion choreography, and character identity across hundreds of shots. Existing video generation and editing pipelines often break down in this regime due to compounding identity drift, background mutation, and semantic erosion under large camera motions and viewpoint changes. We propose Soap2Soap, a multi-agent framework that enforces long-term language-visual consistency through a Dual-Bridge Consistency mechanism: a scene-aware JSON screenplay serving as a persistent semantic backbone, and dynamically allocated visual reference anchors at both scene and shot levels. To suppress drift before video synthesis, we introduce batch keyframe consistency, jointly generating multiple keyframes in a shared latent context via a grid-based formulation. A closed-loop verification agent further audits identity, stability, and alignment to trigger selective regeneration. Experiments on SoapBench demonstrate strong improvements over commercial video generation APIs in long-term consistency and narrative fidelity.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.10988</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.17423</guid>
|
||||||
<pubDate>Sat, 09 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing</title>
|
<title>ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2605.23986</link>
|
<link>https://arxiv.org/abs/2605.18879</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23986.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Chen, Zining Zhang, Wenqi Pei, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich, Wei Wu, Hongbao Zhang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.18879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Lin, Chengyi Yang, Zhishang Xiang, Yiping Song, Jinsong Su</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods primarily rely on retraining or aggressive fine-tuning, which are either computationally expensive or prone to degrading related knowledge and overall model utility. In this work, we reformulate machine unlearning as a precise knowledge re-mapping problem via model editing. We propose ZeroUnlearn, a few-shot unlearning framework. It overwrites sensitive inputs by mapping them to a neutral target state and removing their original representations. ZeroUnlearn enforces representational orthogonality through a multiplicative parameter update with a closed-form solution, enabling efficient and targeted unlearning. We further extend ZeroUnlearn to a gradient-based variant for multi-sample unlearning. Experiments demonstrate that our approach outperforms existing baselines while preserving general model utility. Our code is available at the github: https://github.com/XMUDeepLIT/ZeroUnlearn.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23986</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.18879</guid>
|
||||||
<pubDate>Sat, 16 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.20342</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zuhao Yang, Kaichen Zhang, Sudong Wang, Keming Wu, Zhongyu Yang, Bo Li, Xiaojuan Qi, Shijian Lu, Xingxuan Li, Lidong Bing</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video understanding. However, existing native-RL methods dispatch tool calls sequentially (i.e., one per turn): a single wrong crop propagates errors without peer correction, multi-turn tool calls corrupt context, and inference cost scales linearly with the number of turns. We introduce ParaVT, the first multi-agent end-to-end RL-trained framework for Parallel Video Tool calling, dispatching multiple time-window crops in a single turn for cleaner context and better fault tolerance. Yet applying standard RL to ParaVT reveals an obstacle we term the Tool Prior Paradox: the pretrained tool priors that enable tool exploration also destabilize cold-started structural format and expose the skip-tool reward shortcut under temperature sampling. A cross-model contrast on a weaker-prior LMM supports this claim: format stays stable but RL elicits zero tool calls, indicating that prior strength is the shared driver of both format collapse and tool exploration. We propose PARA-GRPO (Parseability-Anchored and Ratio-gAted GRPO), which augments standard RL with two complementary mechanisms: (i) a targeted format reward applied only at the structural-token positions most prone to collapse, and (ii) a per-prompt frame-budget randomization that creates training prompts where calling the tool yields a measurable reward signal over skipping it. Across six long-video understanding benchmarks, ParaVT improves over the Qwen3-VL baseline by +7.9% on average, with PARA-GRPO lifting training-time format compliance from 0.13 to 0.64. As tool capabilities become increasingly internalized in modern LMMs, RL must cooperate with the resulting priors, and ParaVT offers a general recipe for agentic RL. Code, data, and model weights are publicly available.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.20342</guid>
|
|
||||||
<pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.21085</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21085.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexi Canesse, Benoît Goupil, Jesse Read, Sonia Vanier</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still expose a coupled bottleneck in which a shared latent representation is used for both policy execution and inter-agent communication. Consequently, reducing message size directly limits the policy's latent space, often leading to significant performance degradation. We address this with two contributions. First, we introduce β, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint. Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation, allowing us to isolate the effect of bandwidth from the effect of policy capacity while benefiting from in-step communication. We evaluate our method on several partially-observable MARL benchmarks, where communication is essential. Our approach achieves state-of-the-art performance and exhibits scalability and robustness under limited communication, with only marginal degradation as bandwidth is reduced.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.21085</guid>
|
|
||||||
<pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries</title>
|
<title>Understanding Data Temporality Impact on Large Language Models Pre-training</title>
|
||||||
<link>https://arxiv.org/abs/2605.21712</link>
|
<link>https://arxiv.org/abs/2605.22769</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahdi Azhdari, Eric J. Gonzales</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remains uneven across agencies and community stakeholders. Technical prerequisites create a gap between analytical tools central to safety planning and the practitioners able to use them. Local agencies, school committees, and residents may have safety concerns but limited capacity to retrieve, filter, map, and analyze relevant data. Generative AI offers a way to narrow this divide, but its public-sector use raises questions about reliability, reproducibility, and governance. This paper presents a schema-grounded natural language interface for transportation safety analysis, using a large language model (LLM) to interpret user intent while preserving deterministic, reviewable execution against an authoritative database. User queries are translated into structured semantic frames, validated by a rule-based layer, compiled into a typed directed acyclic graph of spatial operations, and executed against a PostGIS database. This bounded design separates language interpretation from deterministic execution, keeping results reproducible and schema-grounded while removing access barriers. The framework is evaluated using a statewide Massachusetts transportation safety database integrating crash records, roadway attributes, and geospatial layers including schools, bus stops, crosswalks, and municipal boundaries. All queries executed successfully; the validation layer corrects errors in 29% of evaluation queries, reflecting the gap between flexible natural language and strict schema-grounded requirements. The results suggest that combining natural language accessibility with deterministic execution is a practical direction for broadening access to transportation safety data, with implications for trustworthy AI in public-sector planning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pilchen Hippolyte, Fabre Romain, Signe Talla Franck, Perez Patrick, Grave Edouard</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training dynamics on the acquisition of time-sensitive factual knowledge, focusing specifically on data ordering. Our main contributions are twofold. First, we introduce a comprehensive benchmark of over 7,000 temporally grounded questions and an evaluation protocol that enables analysis of whether models correctly associate facts with their corresponding time periods. Second, we pretrain 6B-parameter models on temporally ordered Common Crawl snapshots and compare them against standard shuffled pre-training. Our results show that sequentially trained models match shuffled baselines on general language understanding and common knowledge while consistently exhibiting more up-to-date and temporally precise knowledge. Temporally ordered pre-training yields improved factual freshness, while shuffled pre-training peaks on older data, possibly due to increased factual repetition. These findings, along with the release of our code at https://github.com/kyutai-labs/kairos , checkpoints, and datasets at https://huggingface.co/collections/kyutai/kairos provide a foundation for future research on continual learning for LLMs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.21712</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.22769</guid>
|
||||||
<pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.21748</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.21748.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenwei Tang, Zhaoyan Liu, Rasa Hosseinzadeh, Tongzi Wu, Keyvan Golestan, Jesse C. Cresswell</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like conversational chatbots, the amount of generated text can overwhelm human annotation resources. Model developers have begun to rely heavily on auto-evaluation, where LLMs are also used to judge generation quality. However, existing LLM-as-a-judge benchmarks largely focus on simple Q\&A tasks that do not match the complexity of multi-turn conversations. We introduce RankJudge, a benchmark generator for evaluating LLM-as-a-judge on multi-turn conversations grounded in reference documents. RankJudge creates pairs of conversations where one conversation has a single flaw injected into one turn. This construction allows paired conversations to be labeled unambiguously as better or worse, and precisely isolates failure categories to individual turns, enabling a strict joint correctness criterion for judging. We implement RankJudge across the domains of machine learning, biomedicine, and finance, evaluate 21 frontier LLM judges, and rank those judges via the Bradley-Terry model. Our formulation also allows ranking each conversation pair with difficulty ratings, which we use to dynamically curate the evaluation slice to reduce label noise, as confirmed via human annotation. We find that judge rankings are stable under partial observability, coarser correctness criteria, and an alternative random-walk rating algorithm.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.21748</guid>
|
|
||||||
<pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>How Far Will They Go? Red-Teaming Online Influence with Large Language Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.22880</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel C. Ruiz, Anna Serbina, Ashwin Rao, Emilio Ferrara, Luca Luceri</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally deployed open-source LLMs, as opposed to frontier API-only models, given their superior alignment with the operational constraints of privacy-conscious malicious actors deployed in social media environments. We introduce an empirical red-teaming framework for measuring LLM Overton Windows (OWs), defined as the range of political opinions a model can reliably express on controversial topics, and for quantifying how simple natural-language jailbreaks expand that range. We evaluate more than 30 LLMs spanning 10 model families and five countries of origin. We find systematic asymmetries in political expressivity: open-source LLMs are typically more willing to generate left-leaning social media content, OWs tend to contract inversely to model size, and regional differences are substantial despite uneven representation in the open-source ecosystem. Jailbreak potency also varies sharply across model families, motivating a workflow for identifying effective combinations of jailbreak techniques. Taken together, our results establish a practical framework for auditing the political steerability of open-source LLMs and for helping future researchers design stronger countermeasures against LLM-enabled influence campaigns.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.22880</guid>
|
|
||||||
<pubDate>Wed, 20 May 2026 19:25:26 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>MotiMotion: Motion-Controlled Video Generation with Visual Reasoning</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.22818</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22818.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei, Jing Shi, Ming-Hsuan Yang, Zhixin Shu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by missing secondary causal consequences. To address this, we introduce MotiMotion, a novel framework that reformulates motion control as a reasoning-then-generation problem. To encourage causally grounded and commonsense-consistent interactions, we leverage a training-free vision-language reasoner to refine image-space coordinates of primary trajectories and to hallucinate plausible secondary motions. To further improve motion naturalness, we propose a confidence-aware control scheme that modulates guidance strength, enabling the model to closely follow high-confidence plans while correcting artifacts under low-confidence inputs with its internal generative priors. To support systematic evaluation, we curate a new image-to-video benchmark, MotiBench, consisting of interaction-centric scenes where new events are triggered by motion. Both VLM-based evaluation and a human study on MotiBench demonstrate that MotiMotion produces videos with more plausible object behaviors and interaction, and is preferred over existing approaches.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.22818</guid>
|
|
||||||
<pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO</title>
|
<title>Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents</title>
|
||||||
<link>https://arxiv.org/abs/2604.13517</link>
|
<link>https://arxiv.org/abs/2605.22608</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.13517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jing Sun</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system in neurobiology, recent research has sought to introduce multiple discount factors into Actor-Critic architectures, such as Proximal Policy Optimization (PPO), to balance short-term responses with long-term planning. However, this paper reveals that blindly fusing multi-timescale signals in complex delayed-reward tasks can lead to severe algorithmic pathologies. We systematically demonstrate that exposing a temporal attention routing mechanism to policy gradients results in surrogate objective hacking, while adopting gradient-free uncertainty weighting triggers irreversible myopic degeneration, a phenomenon we term the Paradox of Temporal Uncertainty. To address these issues, we propose a Target Decoupling architecture: on the Critic side, we retain multi-timescale predictions to enforce auxiliary representation learning, while on the Actor side, we strictly isolate short-term signals and update the policy based solely on long-term advantages. Rigorous empirical evaluations across multiple independent random seeds in the LunarLander-v2 environment demonstrate that our proposed architecture achieves statistically significant performance improvements. Without relying on hyperparameter hacking, it consistently surpasses the ''Environment Solved'' threshold with minimal variance, completely eliminates policy collapse, and escapes the hovering local optima that trap single-timescale baselines. The source code to reproduce our experiments is publicly available at https://github.com/ben-dlwlrma/Representation-Over-Routing.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.22608.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Asaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework. It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node. Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI that makes agent evaluation highly accessible. In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback. Our analysis shows strong alignment with human-annotated errors and the ability to predict task success rate.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2604.13517</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.22608</guid>
|
||||||
<pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention</title>
|
<title>FastKernels: Benchmarking GPU Kernel Generation in Production</title>
|
||||||
<link>https://arxiv.org/abs/2605.23081</link>
|
<link>https://arxiv.org/abs/2605.23215</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23081.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joe Sharratt</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Blackwell GPUs to move attention computation to 4-bit precision to accelerate inference. However, these techniques result in significant quality degradation in long-context settings. We show that the output impact of quantisation error is highly non-uniform and increases with the importance of each query-key interaction, concentrating functionally relevant error in a small number of attention blocks that contain the most important tokens. We propose ThriftAttention, a low-bit attention variant that delivers near-FP16 long-context quality at FP4 inference efficiency. This approach proceeds in two stages. First, a heuristic rapidly selects a small number of important query-key block pairs for FP16 precision. Second, the selected blocks are computed in FP16 and the remaining blocks in FP4, with both paths merged via online softmax into a single output. We demonstrate across long-context benchmarks and model families that by computing only 5% of query-key blocks in FP16, ThriftAttention recovers on average 89.1% of the FP4-to-FP16 performance gap. We show ThriftAttention's advantage grows with sequence length, mitigating the systematic FP4 quality degradation observed at longer contexts. The code is available at https://github.com/joesharratt1229/ThriftAttention.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23215.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriele Oliaro, Yichao Fu, May Jiang, Owen Lu, Junli Wang, Zhihao Jia, Hao Zhang, Samyam Rajbhandari</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize against. Existing benchmarks are poorly aligned with production inference frameworks: they evaluate kernels on a single GPU with synthetic inputs, ignore the surrounding compilation stack, and reward replicating known optimizations rather than discovering new ones. The resulting reward signals are misleading: agents learn to generate kernels that score well in sandboxes but introduce interface incompatibilities, compilation-stack conflicts, and silent correctness degradation when integrated into real systems. We introduce FastKernels, a kernel benchmark built around a minimal set of 46 representative architectures spanning 8 categories, whose kernels collectively subsume those of 96.2% (409/425) of HuggingFace Transformers architectures. FastKernels doubles as a minimalistic, production-grade inference framework that runs at parity with hardened systems such as vLLM and SGLang on mainstream LLM serving and substantially exceeds upstream references on under-served architectures; each task's interface mirrors the corresponding module in the state-of-the-art library for its architecture family, enabling direct deployment of optimized kernels into production codebases. Evaluating state-of-the-art kernel agents on FastKernels, we find that even the strongest agent achieves only 0.94times aggregate speedup over production baselines, with weaker agents at 0.78times and 0.53times -- confirming that benchmark-production misalignment is a critical bottleneck for the field. We release FastKernels as a stepping stone toward kernel agents whose benchmark gains translate directly into production throughput improvements. Code is available at https://github.com/Snowflake-AI-Research/fastkernels</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23081</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.23215</guid>
|
||||||
<pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Decoding the Critique Mechanism in Large Reasoning Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2603.16331</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16331.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hoang Phan, Quang H. Nguyen, Hung T. Q. Le, Xiusi Chen, Heng Ji, Khoa D. Doan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that such behaviors are beneficial only when the model has sufficiently strong ``critique'' ability to detect its own mistakes. This work systematically investigates how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps. Notably, we discover a peculiar yet important phenomenon: despite the error propagating throughout the entire chain-of-thought (CoT) without any verbalized correction, the model still reaches the correct final answer after the thinking process finishes. This recovery implies the existence of an internal mechanism helping the model to detect errors and trigger self-correction, which we refer to as the hidden critique ability. Building on feature space analysis, we identify a highly interpretable critique vector representing this behavior. Extensive experiments across multiple model scales and families demonstrate that steering latent representations with this vector improves the model's error detection capability and enhances the performance of test-time scaling at no extra training cost. Our findings provide a valuable understanding of LRMs' critique behavior, suggesting a promising direction to control and improve their self-verification mechanism. Our code is available at: https://github.com/mail-research/lrm-critique-vectors.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16331</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction</title>
|
<title>EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation</title>
|
||||||
<link>https://arxiv.org/abs/2605.23889</link>
|
<link>https://arxiv.org/abs/2605.23271</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23889.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding, Xianda Chen, Yuansen Du, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Zhengqing Chen, Hao Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a fundamental mismatch. Streaming geometry is inherently temporally heterogeneous, with evidence ranging from short-lived correspondences to persistent global scale. However, current architectures impose uniform and pathological influence patterns. For example, sliding windows enforce hard cutoffs, while ungated recurrence and causal attention cause cache saturation and spike-like attention sinks. To resolve this, we formalize geometric propagation as an evidence influence kernel and propose HorizonStream, a long-horizon Transformer that explicitly factorizes this kernel. For the long-range temporal factor, Geometric Linear Attention learns channel-wise decay rates to enable bounded, multi-timescale propagation of geometric evidence. For the short-range spatial factor, Geometric Local Attention with Spatiotemporal RoPE performs reliable 3D matching while suppressing attention sinks. Finally, Metric Readout Tokens recover stable scale and rigid pose directly from the persistent geometric state. Extensive experiments show that HorizonStream, trained on only 48-frame clips, generalizes stably to sequences exceeding 10,000\ frames with constant memory and linear time, achieving state-of-the-art streaming 3D reconstruction performance. Project Page: https://3dagentworld.github.io/horizonstream/</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23271.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songlin Yang, Haobin Zhong, Ruilin Zhang, Xiaotong Zhao, Shuai Li, Kai Zheng, Xuyi Yang, Zhe Wang, Zhenchen Tang, Yang Li, Bohai Gu, Zhengwei Peng, Yidan Huang, Mengzhou Luo, Yihang Bo, Dalu Feng, Yujia Zhang, Juntao Ma, Ruiqi Wang, Lvmin Zhang, Yuwei Guo, Frank Guan, Maneesh Agrawala, Hongbo Fu, Alan Zhao, Anyi Rao</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a critical bottleneck. Existing benchmarks predominantly evaluate ''whether it is right'' (basic prompt-following) while fundamentally neglecting ''whether it is good'' (cinematic quality, acting, and aesthetics). Furthermore, current automated metrics lack the domain-specific rigor required to provide trustworthy signals, creating a severe credibility gap between human aesthetic perception and machine scoring. To bridge this gap, we introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework. We treat video generation assessment not merely as an engineering task, but as a core scientific problem: the systematic digitization of subjective cinematic expertise. First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow (pre-production, production, and post-production). Second, we distill human expert judgments into a curated dataset with large-scale human annotations. Third, we inject this knowledge into Vision-Language Models (VLMs) through an expert-calibrated fine-tuning strategy, enabling the VLM to perform explicit Chain-of-Thought reasoning. Compared to previous works, EvalVerse not only retains compatibility with foundational ''rightness'' metrics, but also significantly expands the criteria to ''goodness'' and broaden the task coverage to complex multi-shot sequencing and audio-visual integration. Consequently, by providing granular diagnostic signals, EvalVerse transcends a static leaderboard and establishes a fundamental infrastructure for future work, such as reward models and evaluator agent.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23889</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.23271</guid>
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild</title>
|
<title>SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent</title>
|
||||||
<link>https://arxiv.org/abs/2605.24213</link>
|
<link>https://arxiv.org/abs/2605.24468</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24213.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhimin Zhao, Zehao Wang, Abdul Ali Bangash, Bram Adams, Ahmed E. Hassan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24468.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyang Hu, Hongjin Qian, Shuting Wang, Jiongnan Liu, Ziliang Zhao, Jiejun Tan, Zheng Liu, Zhicheng Dou</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but that information needed for the current decision may be scattered across distant steps and only become relevant later. Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse, but they do not explicitly model how access to past interaction should adapt to the agent's evolving state. We instead cast long-horizon reasoning as a problem of state-adaptive memory. To this end, we propose State-Adaptive Memory~(SAM), a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall. These cues are not treated as replacements for history; rather, they serve as lightweight handles that allow the agent to reconstruct temporally distant information according to its current needs, without retraining the underlying backbone. We further optimize the memory module through expert-guided supervision and reinforcement learning, aligning it with trajectory-level utility. Across BrowseComp, BrowseComp-ZH, WideSearch, and HLE, SAM consistently outperforms strong baselines over diverse agent backbones. Our results suggest that explicit memory modeling provides a simple and effective foundation for long-horizon agentic reasoning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24213</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.24468</guid>
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.23491</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangyi Hu, Chenhui Liu, Tian Huang, Jindong Li, Yang Yang, Jiemin Wu, Zining Zhong, Menglin Yang, Yutao Yue</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23491</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.23264</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongbo Wang, Huaibo Huang, Pin Wang, Jinhua Hao, Chao Zhou, Ran He</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image manifold. While Direct Preference Optimization offers a path to alignment, its reliance on spectrally flat Gaussian noise fails to distinguish authentic high-frequency details from hallucinations. To bridge this geometric gap, we propose ASASR, a theoretically grounded framework that recasts the generative flow into a Sobolev-induced Riemannian geometry by explicitly coloring the noise transition kernel to mirror natural spectral decay. Driving this geometric alignment, we integrate a parametric adversary grounded in the Riesz Representation Theorem, which synthesizes targeted negative samples equivalent to worst-case Sobolev gradients to direct optimization along the tangent space of plausible structural failures. Extensive evaluations demonstrate that ASASR outperforms leading generative baselines, particularly in preserving spectral consistency and structural fidelity, offering a robust solution that effectively mitigates artifacts.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23264</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.23699</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> León Begiristain, Olaf Dünkel, Adam Kortylewski</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causal structure or merely exploit superficial visual correlations for future prediction. We introduce CRONOS, an intervention-based benchmark designed to evaluate counterfactual physical consistency: whether a model's predictions of physical events respond appropriately to controlled changes in the visual input, such as variations of scene context, viewpoint, object appearance, and object category. Built in a photorealistic Unreal Engine environment, CRONOS enables controlled, high-fidelity generation of videos across diverse scenes and dynamics. In contrast to previous benchmarks, CRONOS systematically intervenes on four key factors - viewpoint, scene, object category, and object appearance - while keeping the underlying physical event type, such as a collision, occlusion, or fall, fixed. Our evaluation of recent open-source video generators reveals substantial failures in counterfactual physical consistency: prediction quality for the same physical event type is affected by appearance, environment, and, particularly by viewpoint changes. CRONOS provides a controlled and reproducible testbed for diagnosing how the quality of generated videos changes for different interventions, establishing a concrete target for developing models that perform consistently across changes of multiple conditions. The dataset and code are available at our project page.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23699</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.24117</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yingtie Lei, Zhongwei Wan, Jiankun Zhang, Samiul Alam, Zixuan Zhong, Peizhou Huang, Xin Wang, Jingxuan Zhang, Donghao Zhou, Yunta Hsieh, Zhihao Dou, Hui Shen, Yan Xu, Dimitrios Dimitriadis, Tuo Zhang, Mi Zhang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation. It contains 180 tasks across six real-world agent environments, organized into role-conditioned task families with shared latent procedures. Agents learn from acquisition tasks, update an external skill library using compacted trajectories and verifier feedback, and then face frozen deployment tasks testing context shift, adversarial shortcuts, and composition. By comparing self-generated and curated-start skill evolution against no-skill and raw-trajectory controls, SkillEvolBench separates procedural abstraction from base capability, curated prior knowledge, and direct reuse of episodic traces. Across ten model configurations and three agent harnesses, we find that current agents often adapt locally but rarely form robust reusable skills. Skill-based conditions can improve acquisition or replay, and individual models sometimes gain on specific deployment axes, but these gains are unstable under frozen deployment. Raw-trajectory reuse frequently outperforms distilled skills, suggesting that current abstraction procedures discard contextual and procedural cues that remain useful for future tasks. Capacity and cost analyses further show that writing more skills or larger Tier-3 resource libraries is not sufficient: additional updates can improve coverage while introducing episode-specific drift and procedural clutter. These findings position SkillEvolBench as a testbed for measuring when one-off experience becomes durable procedural knowledge rather than task-local memory.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24117</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.23204</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guiyao Tie, Jiawen Shi, Dingjie Song, Yixiao Huang, Ziji Sheng, Xueyang Zhou, Daizong Liu, Pan Zhou, Yongchao Chen, Ran Xu, Lifang He, Qingsong Wen, Manling Li, Cong Lu, Shuai Li, Pengtao Xie, Yixuan Yuan, Rui Meng, Lei Xing, Lichao Sun, Caiming Xiong, Philip S. Yu, Jianfeng Gao</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift marks a transition from task-level AI for science to workflow-level research automation. Yet current systems remain fragmented, differing in autonomy, domain scope, execution environment, validation mechanism, and human oversight, while still struggling with evidence preservation, reproducibility, weak-direction rejection, provenance tracking, cross-domain robustness, and accountable scientific closure. This survey examines these developments through AutoResearch, defined as the developmental spectrum of AI-powered scientific workflow automation. Within it, Vibe Research denotes the human-steered region of prompt-based assistance and human-verified execution, whereas emerging AI-led systems coordinate larger portions of the discovery loop without achieving robust autonomy. We analyze how research systems redistribute control, evidence, execution, validation, and accountability across workflows and organize the field around five workflow conditions: literature and research grounding; hypothesis formation and planning; experimentation and tool use; feedback, validation, and review; and reporting and knowledge communication. We further synthesize AI scientist systems, mixed-initiative co-research frameworks, benchmarks, domain deployments, and open-source infrastructures. Finally, we propose five evaluation dimensions--novelty, validity, impact, reliability, and provenance--and show that AutoResearch autonomy is domain-conditioned, being more credible in structured, executable, and rapidly verifiable settings but limited in embodied, delayed, heterogeneous, ethical, or institutionally accountable contexts.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23204</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.24218</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Xie, Tianhe Lin, Zilu Wang, Yuting Ning, Yuekun Yao, Tianci Xue, Zhehao Zhang, Zhongyang Li, Kai Zhang, Yufan Wu, Shijie Chen, Boyu Gou, Mingzhe Han, Yifei Wang, Vint Lee, Xinpeng Wei, Xiangjun Wang, Yu Su, Huan Sun</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24218</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Foundation Protocol: A Coordination Layer for Agentic Society</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.23218</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.23218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bang Liu, Yongfeng Gu, Jiayi Zhang, Zhaoyang Yu, Sirui Hong, Maojia Song, Xiaoqiang Wang, Mingyi Deng, Zijie Zhuang, Ronghao Wang, Mingzhe Cao, Yutong Zhu, Xingjian Li, Yifan Wu, Jianhao Ruan, Yiran Peng, Shuangrui Chen, Jinlin Wang, Yizhang Lin, Dongjie Zhang, Dekun Wu, Chen Ma, Lizi Liao, Han Yu, Jian Pei, Heng Ji, Qiang Yang, Yuyu Luo, Chenglin Wu</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form reliable relationships, organize multi-agent work, exchange value, support an AI economy, and stay safe and accountable under real-world oversight. This paper introduces the Foundation Protocol (FP), a graph-first coordination layer for an emerging human-AI society. FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations, and supports native multi-party organization and event-based collaboration. It also provides economic primitives for metering, receipts, and settlement, and treats policy, provenance, and audit as first-class concerns. FP is designed to wrap and bridge existing protocols rather than replace them, enabling incremental adoption while reducing integration and governance overhead. The aim is to keep autonomous agency composable while keeping accountability non-negotiable, so that coordination itself can become shared infrastructure for a human-AI society that is open, pluralistic, and governable.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.23218</guid>
|
|
||||||
<pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>ECHO: Terminal Agents Learn World Models for Free</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.24517</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vaishnavi Shrivastava, Piero Kauffmann, Ahmed Awadallah, Dimitris Papailiopoulos</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream -- stdout, errors, files, logs, and traces -- records the consequences. We argue that this stream is a supervision signal, but standard agent RL discards it: GRPO-style training updates action tokens with sparse outcome-level rewards while ignoring environment responses already in the rollout. Failed rollouts provide little policy-gradient signal despite containing rich evidence about how the environment responds. We introduce ECHO (Environment Cross-entropy Hybrid Objective), a hybrid objective that combines the standard policy-gradient loss on action tokens with an auxiliary loss that trains the policy to predict environment observation tokens resulting from its own actions. ECHO reuses the same forward pass as GRPO, requires no additional rollouts, and turns terminal feedback into dense supervision for all rollouts. ECHO doubles GRPO pass@1 on TerminalBench-2.0: Qwen3-8B improves from 2.70% to 5.17%, and Qwen3-14B from 5.17% to 10.79%. ECHO also produces policies that better predict terminal dynamics, even on trajectories they did not generate: across held-out rollouts, it sharply reduces environment-token cross-entropy while GRPO alone barely changes it. From base Qwen3-8B, ECHO matches expert-SFT-then-GRPO performance on held-out terminal tasks without expert demonstrations, and recovers roughly half of the expert-SFT initialization benefit on TerminalBench-2.0. In some settings, the environment prediction loss alone enables verifier-free self-improvement, allowing policies to improve on unseen OOD tasks by learning only from environment interactions. Together, these results suggest that environment observations are not merely context for future actions, but a dense, on-policy supervision signal already present in every rollout.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24517</guid>
|
|
||||||
<pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SEAL: Synergistic Co-Evolution of Agents and Learning Environments</title>
|
<title>STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media</title>
|
||||||
<link>https://arxiv.org/abs/2605.24426</link>
|
<link>https://arxiv.org/abs/2605.25162</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihao Hu, Zhihao Wen, Xiujin Liu, Pan Wang, Xin Zhang, Wei Wu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as Agent-Environment Misalignment: the agent's capability frontier changes during training, while the environment that provides supervision remains static or only weakly coupled to the agent's revealed failures. We propose SEAL, a closed-loop co-evolution framework for interactive tool-use agents. SEAL collects on-policy trajectories under executable verification, diagnoses failed rollouts into turn-level failure labels, and uses these diagnoses as a shared signal for both environment-side adaptation and model-side policy optimization. The environment evolves its training-time learning interface by exposing clearer tool affordance cues, constraint information, and recovery-oriented feedback, while the policy is updated with diagnosis-guided advantage reweighting. Extensive experiments across in-distribution and out-of-distribution multi-turn tool-use evaluations show that SEAL improves low-resource agent learning: with only 400 training samples, it yields +8.25 to +26.25 average-point gains across three backbones and exhibits positive out-of-distribution transfer. These results demonstrate the value of jointly adapting the learner and its training-time learning substrate for robust self-improving LLM agents.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Xue, Haoyu Liu, Cheng Wang, Pengyu Chen, Haozhuo Zheng, Yang Liu</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persistent trilemma: expert annotation is expensive, real-world service conversations are constrained by privacy and commercial restrictions, and static corpora quickly become temporally stale. We propose Stream, a data-centric framework that leverages publicly available streaming media (live streams and short videos) to synthesize high-value service dialogues at scale. Stream mines authentic interaction signals from noisy streams and synthesizes conversations by integrating role-grounded persona construction with Conversational Blueprint construction; it further adopts retrieval-augmented generation (RAG) to support knowledge-aware responses. Based on Stream, we release StreamDial, a large-scale multi-domain dataset covering Automotive, Restaurant, and Hotel. StreamDial contains 87,498 dialogue sessions and 1,497,320 turns in total, with an average of 17.11 turns per session and a comparable scale across domains. Each session is organized as a structured quadruplet langle P_u, P_a, B, H rangle that pairs dialogue history with explicit user/agent personas and a Conversational Blueprint, capturing realistic service behaviors such as requirement mining, constraint conflicts, negotiation, and recovery. Evaluations with automatic judges and downstream tasks show that StreamDial improves intrinsic dialogue quality over strong baselines, and models trained with StreamDial improve Dialogue State Tracking across backbones; we further report a completed human-evaluation set and encouraging multilingual transfer on Qwen3-8B under a controlled training budget. The data is released in https://github.com/hitxueliang/DialogDataSetBySTREAM.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24426</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25162</guid>
|
||||||
<pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.20278</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.20278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Li, Xuyang Shen, Yan Ma, Rongxin Guo, Shaoxiang Chen, Jiacheng Chen, Haochen Wang, Hongyang Tang, Yucong Zhou, Yu Cheng</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and informative, avoiding hallucination without omitting salient details. Yet pairwise preferences, reference-based metrics, and holistic scalar rewards compress these local errors into a single sequence-level signal, obscuring the tradeoff between factuality and coverage. We introduce ClaimDiff-RL, a framework that uses reference-conditioned atomic claim differences as the reward unit for caption RL. Given an image, an actor caption, and a reference caption, a multimodal judge enumerates visually grounded differences, verifies each difference against the image, assigns open-vocabulary error types and severity levels, and produces per-difference statistics for reward composition. This makes hallucinated claims and omitted salient facts separately measurable and tunable. Experiments show that holistic scalar rewards can reduce hallucination by increasing missing facts, while ClaimDiff-RL exposes this faithfulness and coverage tradeoff and enables more balanced operating points. On a 160-image human-labeled diagnostic benchmark, public captioning benchmarks, and VQA benchmarks, ClaimDiff-RL improves the hallucination--missing-fact balance, preserves general capability, and even surpasses Gemini-3-Pro-Preview on several fine-grained Capability dimensions such as object counting, spatial relations, and scene recognition. These results suggest that typed, verifiable claim differences are an effective reward unit for fine-grained and diagnosable caption RL.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.20278</guid>
|
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking</title>
|
<title>Learning High-Frequency Continuous Action Chunks in Latent Space</title>
|
||||||
<link>https://arxiv.org/abs/2605.25160</link>
|
<link>https://arxiv.org/abs/2605.24931</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guohong Liu, Jialei Ye, Pengzhi Gao, Wei Liu, Jian Luan, Yunxin Liu, Yuanchun Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing benchmarks prioritize reproducibility but are often limited to open-source apps or file-operation tasks for the difficulty of constructing rewards on real applications, leaving a gap between benchmark settings and real-world usage. Moreover, most benchmarks focus on basic grounding and navigation, with limited coverage of complex, long-horizon interactions. To address these limitations, we introduce SimuWoB, a fully synthetic benchmark for mobile GUI agents with 120 challenging tasks spanning diverse types and difficulty levels. We build a robust virtual environment generation framework that synthesizes high-fidelity tasks and environments, and automatically provides valid rewards for each task. Each environment is deployed as a backend-free webpage accessible via URL, enabling efficient and reproducible evaluation. We conduct comprehensive experiments on several state-of-the-art mobile GUI agents. The average success rate is only 27.92%, dropping to 17.82% on long-horizon tasks, which reveals substantial weaknesses in current agents under complex scenarios. Evaluation result comparison with real-world sample tasks demonstrate that agent assessments based on our synthetic environment generalize well. We further provide diagnostic insights across key capability dimensions and discuss implications for future mobile GUI agent development.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24931.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kunyun Wang, Yuhang Zheng, Yupeng Zheng, Jieru Zhao, Wenchao Ding</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action frequencies, it becomes insufficient when the action frequency is further increased (e.g., to 60~Hz). At such high frequencies, policies often fail to generate actions that are both temporally smooth and spatially consistent. We address this challenge by shifting high-frequency action learning from the action space to a latent space with variational autoencoder (VAE). This formulation significantly improves both temporal and spatial consistency of high-frequency control. To enable smooth real-time execution, we further introduce Reuse-then-Refine, a chunk-level refine strategy that improves continuity between adjacent action chunks under asynchronous inference. As a result, robots controlled by our policy can execute complex contact-rich tasks continuously, with less pauses and jerky motions. Experiments on three real-world contact-rich robotic tasks show that our approach consistently completes tasks with smooth motions. Our code and data are available at https://github.com/tars-robotics/RTR.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25160</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.24931</guid>
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models</title>
|
<title>DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2605.25189</link>
|
<link>https://arxiv.org/abs/2605.25188</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenlong Deng, Jiaji Huang, Kaan Ozkara, Yushu Li, Christos Thrampoulidis, Xiaoxiao Li, Youngsuk Park</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that hacking emerges when optimization drifts away from a stable low-dimensional learning trajectory. We analyze this drift through dominant singular directions of parameter updates and show that reward-hacking runs exhibit substantially larger directional change than clean runs. Motivated by this observation, we introduce trusted-direction projection, which constrains gradients to remain within a clean reference subspace. Across reward-hacking experiments on mathematical reasoning, the proposed approach delays shortcut exploitation and better preserves task performance.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25188.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Li, Songtao Wei, Dongming Jiang, Zhichun Guo, Qiannan Li, Bingzhe Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7\% on benchmark metrics, and reduces token consumption by up to 6.5times compared with communication-heavy baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25189</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25188</guid>
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference</title>
|
<title>CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations</title>
|
||||||
<link>https://arxiv.org/abs/2605.25191</link>
|
<link>https://arxiv.org/abs/2605.26293</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25191.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Agata Żywot, Iason Skylitsis, Thijmen Nijdam, Zoe Tzifa-Kratira, Derck Prinzhorn, Konrad Szewczyk, Aritra Bhowmik</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally expensive fine-tuning or rely on style transfer techniques that risk semantic misalignment with textual prompts. We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training. VCF enables visual concept injection into Stable Diffusion by aligning CLIP image features with the text embedding space. VCF consists of three components: (1) a lightweight aligner that maps image tokens to the text embedding manifold using InfoNCE and cross-attention reconstruction losses, (2) a fusion strategy that preserves both textual and visual semantics, and (3) an optional Prompt-Noise Optimization (PNO) module for test-time refinement. Our experiments demonstrate that VCF successfully transfers visual attributes including style, composition, and color palette from reference images while maintaining prompt adherence. Quantitative results show a trade-off between text alignment (CLIP score) and visual correspondence (LPIPS), with VCF outperforming baselines in reference fidelity.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26293.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mike Zhang, Ali Basirat, Desmond Elliott</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and evaluate two models across a total of 14 high and low-resource languages on a diverse set of tasks. Our central finding is that cross-lingual contrastive preference tuning on self-generations (CroCo) transfers without language-specific preference annotation. A reward model trained on English preferences (atop a multilingual base) produces useful within-language rankings across most languages, and pairing in either a monolingual or multilingual setting improves over each model on the majority of setups while preventing the catastrophic forgetting of supervised fine-tuning. We observe that the gains require on-policy data. Off-policy responses reduce the benefit and online preference optimization fails to improve over the offline variant. Specifically, on structured tasks, our method matches or exceeds the base in 6/7 languages for EuroLLM-9B and 4/7 settings for Aya-3B. On open-ended generation, both tuned models win against their respective base across 11 evaluated languages. Overall, we show promising directions for multilingual preference tuning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25191</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26293</guid>
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.25052</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoav Gur-Arieh, Ana Marasović, Mor Geva</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions. Several faithfulness metrics have been proposed, but whether they indeed measure faithfulness remains unknown. Answering this requires ground-truth labels, which are hard to obtain since internal computations are not directly observable. Consequently, most works proposing metrics report only absolute scores or comparisons to prior metrics, and the few existing benchmarks rely on proxies like plausibility or importance, properties orthogonal to faithfulness that can mislead about whether a CoT can be trusted. We address this challenge by constructing tasks whose outputs reveal which intermediate computations must have produced them, and developing an automated labeling pipeline that yields ground-truth faithfulness labels at both the step and CoT level. Building on this methodology, we present BonaFide, a benchmark of 3,066 labeled CoTs across 13 tasks and 10 models, and use it to conduct the first systematic evaluation of prominent faithfulness metrics. Our experiments show that most metrics perform near chance, exhibit strong prediction biases and degrade on longer CoTs. The best metric reaches only 0.70 AUROC at the CoT level while another reaches 0.59 at the step level, with neither transferring across settings, while entailing prohibitively high computational cost. Our results expose fundamental gaps in current faithfulness evaluation and call for the development of more reliable and efficient metrics.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25052</guid>
|
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Geometry-Aware Image Flow Matching</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.25294</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25294.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junho Lee, Kwanseok Kim, Joonseok Lee</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the potential of intrinsic geometric structures within the data. In this work, we investigate the geometry of natural images and observe that semantic information is predominantly encoded in directional components, while norm components can be approximated by the global average. This property holds across both RGB and latent spaces, suggesting that natural images can be effectively modeled on a hypersphere. Building on this finding, we introduce Spherical Optimal Transport Flow Matching (SOT-CFM), which utilizes angular distance, and Spherical Flow Matching (SFM), which constrains dynamics directly on the manifold. Our experiments demonstrate that these geometry-aware methods achieve superior performance against Euclidean baselines. Ultimately, this work provides a novel perspective that bridges the gap between Riemannian manifold-based modeling and natural image generation.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25294</guid>
|
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Your Embedding Model is SMARTer Than You Think</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.24938</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24938.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianrui Zhang, Hyun Jung Lee, Sukanta Ganguly, Tae-Eui Kam, Donghyun Kim, Yong Jae Lee</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval tasks. Multi-vector approaches were introduced as a solution, but they strictly require training and many ignore the necessity of a globally summarizing representation. To address this, we introduce SMART, a framework that unlocks the latent multi-vector capabilities of standard single-vector models. We first demonstrate that standard contrastive training on the pooled embedding implicitly shapes the retrieval geometry of preceding hidden states via gradient flow. By applying direct late-interaction over these frozen hidden states during inference, SMART acts as a plug-and-play upgrade that consistently improves performance across diverse modalities, improving even the state-of-the-art models further on MMEB-V2. We also reveal SMART's superior performance, as simple lightweight post-training not only saves time and compute, but also brings forth further improvement on Visual Document retrieval, allowing a single-vector model to outperform SoTA multi-vector counterparts. Ultimately, SMART offers both a highly efficient inference enhancement and a powerful finetuning technique for multimodal retrieval. We open source our code and weights at https://github.com/HanSolo9682/SMART.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24938</guid>
|
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Macaron-A2UI: A Model for Generative UI in Personal Agents</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.24830</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24830.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fancy Kong, Congjie Zheng, Murphy Zhuang, Rio Yang, Sueky Zhang, Hao Fu, Gene Jin, Song Cao, Kaijie Chen, Andrew Chen, Pony Ma</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer, dynamically synthesizing the right controls, options, and state from the interaction context in real time. We present Macaron-A2UI, a model for Generative UI in personal agents. Our goal is to move beyond text-only interaction by enabling agents to generate natural language together with lightweight, executable UI actions for information collection, preference refinement, confirmation, and multi-goal organization. We build a large-scale Generative UI corpus from heterogeneous dialogue sources, introduce A2UI-Bench for controlled evaluation, and train 30B, 235B and 754B models with parameter-efficient LoRA-based supervised fine-tuning followed by reward-driven reinforcement learning. The best Macaron-A2UI model reaches 75.6 overall on A2UI-Bench without explicit schema hints, surpassing the strongest full-schema frontier baseline. We release the models, benchmark, and evaluation protocol to support future work on Generative UI for personal agents.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.24830</guid>
|
|
||||||
<pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
|
|
||||||
</item>
|
|
||||||
<item>
|
|
||||||
<title>Pixel-Level Pavement Distress Assessment Using Instance Segmentation</title>
|
|
||||||
<link>https://arxiv.org/abs/2605.26095</link>
|
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26095.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Logan Dewick, Bibesh Pyakurel, Kong Pheng Yang, Nazim Choudhury, M. G. Sarwar Murshed</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Automated pavement distress assessment requires more than image-level classification or coarse bounding box detection, demanding precise localization of thin, branching, and irregular cracks to achieve the geometric precision necessary for maintenance-relevant quantification. This paper presents a vision-based pavement distress analysis system based on Mask R-CNN instance segmentation and evaluates it on UWGB-StreetCrack, a custom field-collected roadway image dataset acquired with a vehicle-mounted smartphone and manually annotated with polygon labels for longitudinal cracks, transverse cracks, alligator cracks, and potholes. Five Detectron2-based Mask R-CNN backbone variants were considered under a consistent fine-tuning protocol. The best-performing model, Mask R-CNN with a ResNet-101 FPN backbone, achieved 84.23% precision, 90.04% recall, and an F1 score of 87.04% under the project-specific bounding-box matching protocol. The same model produced an aggregate predicted crack-area fraction of 2.164%, closely matching the 2.170% ground-truth crack-area fraction. To contextualize the segmentation system against a detector-oriented alternative, a CSPDarknet53-based YOLO detector was also adapted and retrained on the dataset, reaching 27.5% precision and 20.7% recall on the validation protocol. The results show that instance segmentation is a practical direction for field pavement imagery and aggregate crack-area estimation, while also exposing open challenges in annotation consistency, class imbalance, confounder rejection, and mask-level benchmarking.</p></description>
|
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26095</guid>
|
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges</title>
|
<title>NSF-SciFy: Mining the NSF Awards Database for Scientific Claims</title>
|
||||||
<link>https://arxiv.org/abs/2605.26002</link>
|
<link>https://arxiv.org/abs/2503.08600</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongtae Hong, Youngjoon Jang, Jia-Heui Ju, Hyeonseok Moon, Heuiseok Lim</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this structural limitation, we propose SemBridge, a novel embedding initialization method designed for cross-lingual adaptation in sparse encoders by leveraging multilingual bridge models. SemBridge establishes semantic alignments between source and target vocabularies using multilingual dense embeddings as a bridge. Rather than directly relying on all source tokens, SemBridge selects a small set of semantically related source-language tokens and uses them to initialize each target-language token, effectively filtering out semantic noise and reconstructing target tokens as precise linear combinations of core synonyms. This accelerates convergence during fine-tuning and improves training efficiency. Extensive experiments across five languages and four sparse architectures demonstrate that SemBridge achieves superior zero-shot retrieval performance and consistently improves retrieval performance after fine-tuning compared to existing baselines. These results validate SemBridge as a practical solution for deploying high-performance sparse retrieval systems in diverse linguistic environments.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2503.08600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Delip Rao, Weiqiu You, Eric Wong, Chris Callison-Burch</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce NSF-SciFy, a comprehensive dataset of scientific claims and investigation proposals extracted from National Science Foundation award abstracts. While previous scientific claim verification datasets have been limited in size and scope, NSF-SciFy represents a significant advance with 2.8 million claims from 400,000 abstracts spanning all science and mathematics disciplines. We present two focused subsets: NSF-SciFy-MatSci with 114,000 claims from materials science awards, and NSF-SciFy-20K with 135,000 claims across five NSF directorates. Using zero-shot prompting, we develop a scalable approach for joint extraction of scientific claims and investigation proposals. We demonstrate the dataset's utility through three downstream tasks: non-technical abstract generation, claim extraction, and investigation proposal extraction. Fine-tuning language models on our dataset yields substantial improvements, with relative gains often exceeding 100%, particularly for claim and proposal extraction tasks. Our error analysis reveals that extracted claims exhibit high precision but lower recall, suggesting opportunities for further methodological refinement. NSF-SciFy enables new research directions in large-scale claim verification, scientific discovery tracking, and meta-scientific analysis. Code and data are available at https://github.com/darpa-scify/NSFSciFy.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26002</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2503.08600</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reinforcing Few-step Generators via Reward-Tilted Distribution Matching</title>
|
<title>Can LLMs Introspect? A Reality Check</title>
|
||||||
<link>https://arxiv.org/abs/2605.26108</link>
|
<link>https://arxiv.org/abs/2605.26242</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26108.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yushi Huang, Xiangxin Zhou, Ruoyu Wang, Chi Zhang, Jun Zhang, Tianyu Pang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a two-stage framework that unifies distribution matching distillation with reward-guided reinforcement learning for few-step flow generators. We show that minimizing the KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward maximization term. In the first stage, we introduce Ambient-Consistent Distribution Matching Distillation (AC-DMD), which performs subinterval-wise distribution matching and augments the fake score objective with a consistency regularizer to help the fake score model track the shifting generator distribution under limited updates. In the second stage, we jointly optimize both terms: for the reward maximization term, we derive a hybrid policy gradient that combines a GRPO-style estimator for the stochastic intermediate transitions with direct reward backpropagation through the deterministic final step, and further introduce step-subset GRPO (SubGRPO) to reduce variance. Experiments on SD3, SD3.5, and FLUX.2 demonstrate that RTDMD establishes new state-of-the-art results across preference, aesthetic, and compositional metrics with only 4 inference steps, outperforming previous few-step text-to-image generation methods. Code and models are available at https://github.com/Harahan/RTDMD.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shashwat Singh, Tal Linzen, Shauli Ravfogel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be premature: to be convinced of this conclusion we need to distinguish genuine introspection from pattern matching based on surface-level cues. Furthermore, we argue that behavioral evidence alone is inherently insufficient to establish strong introspective claims. We re-examine two recently introduced evaluation paradigms in light of this consideration. In the first paradigm, models are expected to detect whether their internal states have been tampered with. We find that models cannot reliably distinguish such interventions on their internal states from manipulations of the input, suggesting that their success in the original studies reflects their ability to detect anomalies more generally, as opposed to interventions on their internal states in particular. In the second paradigm we examine, models are tasked with predicting labels derived from their own hidden states. Here, we find that classifiers that only have access to the input achieve equivalent performance to the model's own in-context predictions, indicating that the original results do not conclusively demonstrate that the model has privileged access to its internal representations. We further introduce a relabeled control setting, where models cannot rely on the semantics of the task to solve it, and instead must rely on the internal representation; models perform closer to chance on this better-controlled version of the task. Taken together, these results indicate that current evidence is insufficient to establish that LLMs display metacognitive monitoring.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26108</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26242</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MetaphorVU: Towards Metaphorical Video Understanding</title>
|
<title>Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation</title>
|
||||||
<link>https://arxiv.org/abs/2605.25461</link>
|
<link>https://arxiv.org/abs/2605.26111</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25461.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoqun Li, Boxi Cao, Guiping Jiang, Fangrui Lv, Ruotong Pan, Jianan Wang, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Yong Du, Ruyin Jia, Liyan, Tingting Gao, Han Li, Xianpei Han, Le Sun</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li, Yu-Jhe Li, Igor Gilitschenski</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits cross-modal reasoning abilities and causes copy-paste artifacts. Recent frameworks that connect multimodal models and diffusion models improve instruction following, but largely overlook identity preservation. To address these limitations, we condition diffusion models on Multimodal Large Language Models (MLLMs) that jointly encode text and reference images, and augment it with VAE-based identity conditioning. A novel Dual Layer Aggregation (DLA) module is designed to aggregate multi-level MLLM features for optimal conditioning, and a multi-stage denoising strategy is applied to progressively balance the semantic information from MLLM and fine-detail identity from VAE during inference. Extensive experiments demonstrate that our approach harmonizes multimodal understanding with identity preservation, mitigates copy-paste issues, and achieves superior performance regarding human preference on subject-driven image generation. Our project website is available at https://zsh2000.github.io/squeeze-mllm-subject-gen/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25461</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26111</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Helix4D: Complex 4D Mesh Generation</title>
|
<title>Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals</title>
|
||||||
<link>https://arxiv.org/abs/2605.26109</link>
|
<link>https://arxiv.org/abs/2605.26045</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26109.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiraphon Yenphraphai, Jianqi Chen, Jian Wang, Gordon Qian, Sergey Tulyakov, Rameen Abdal, Raymond A. Yeh, Peter Wonka, Chaoyang Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D generation. Our design arises from two key questions: (a) how to enable Trellis2's frame-local attention to share information across frames while preserving its pretrained quality on rare cases such as transparent objects and inner surfaces, and (b) how to inject temporal information into a purely 3D positional encoding without breaking pretrained capabilities. We address (a) with a sliding-window cross-frame attention and anchor on the first frame. The first frame is generated by the base Trellis2 model and injected into our model, letting it inherit Trellis2's quality in rare cases through cross-frame attention. We address (b) with a 4D temporal encoding that repurposes redundant low-frequency spatial RoPE bands for time, extending the encoding from 3D with no additional parameters. Extensive experiments show the effectiveness of Helix4D for high-quality dynamic mesh generation on ActionBench and our own challenging complex dynamics set.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Federico Torrielli, Peter Schneider-Kamp, Lukas Galke Poech</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty quantification (UQ) for the natural-language outputs of such activation oracles is so far understudied. Here, we investigate 6 different methods for estimating the confidence of activation oracles and evaluate how well-calibrated their confidence scores are. Our experiments on 6,000 samples per oracle (varying verbalizer and context prompts) reveal that bootstrap mode frequency is the best-calibrated method among those tested (ECE 5.7% vs. 25.5% for the answer-word log-probability on Qwen3-8B; 10.3% vs. 13.1% on Qwen3.6-27B), and that the log-prob baseline can serve as a fast triage signal at a fraction of the cost. Code and the patched trainer are available at https://github.com/federicotorrielli/probabilistic_activation_oracles.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26109</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26045</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Language Models Need Sleep</title>
|
<title>Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2605.26099</link>
|
<link>https://arxiv.org/abs/2605.25437</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangyun Lee, Sean McLeish, Tom Goldstein, Giulia Fanti</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model periodically converts recent context into persistent fast weights before clearing its key-value cache. During sleep, the model performs N offline recurrent passes over the accumulated context and updates the fast weights in its state-space model (SSM) blocks through a learned local rule. During inference, this shifts extra computation to sleep while preserving the latency of wake-time prediction. We test our method on controlled synthetic tasks, including cellular automata and multi-hop graph retrieval, as well as a realistic math reasoning task, on which a regular transformer as well as SSM-attention hybrid models fail. We then show that increasing sleep duration N for our models improves performance, with the largest gains on examples that require deeper reasoning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanhu Zeng, Zhicong Luo, Zefan Wang, You Li, Chi Chen, Maosong Sun</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Visual reasoning through reinforcement learning with verifiable rewards (RLVR) has achieved remarkable progress. However, when dealing with multi-source inputs, existing approaches tend to treat them as a mere accumulation of information, lacking explicit mechanisms to distinguish whether integrating additional sources yields information gain or introduces interference. Therefore, they struggle to effectively model dynamic interaction when integrating multiple sources, particularly when they differ significantly in physical properties and semantics, e.g., infrared and depth, leading to inferior performance to mono-source reasoning when a certain source holds the dominant signal. To address this issue, we propose MARS, a novel mono-anchored multi-source reasoning framework that models each visual modality as an independent information source. Specifically, by treating mono-source rewards as dynamic anchors, our method explicitly incorporates the information gain introduced by multi-source fusion into advantage normalization and adaptively emphasizes mutual promotion between sources while suppressing potential noise or conflicts during RLVR. From theoretical analysis, our method effectively quantifies information gain introduced by multi-source integration in gradient estimation, enabling consistent modality regulation. Empirical results also show impressive 3.2% and 4.9% performance gains on GRPO and DAPO across diverse datasets, confirming effectiveness of our method.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26099</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25437</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>InstructSAM: Segment Any Instance with Any Instructions</title>
|
<title>Rethinking VLM Representation for VLA Initialization</title>
|
||||||
<link>https://arxiv.org/abs/2605.26102</link>
|
<link>https://arxiv.org/abs/2605.25802</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqian Yuan, Wentong Li, Zhaocheng Li, Yutong Lin, Juncheng Li, Siliang Tang, Jun Xiao, Yueting Zhuang, Wenqiao Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query interface that elegantly bridges a vision-language model (VLM) and SAM3. Specifically, a bank of learnable instance queries is injected into the VLM and contextualized with instruction and visual information, enabling each query to serve as an instance-aware slot. A hybrid-attention mechanism further promotes interaction among these queries, visual tokens, and instruction tokens, improving instance enumeration and reducing duplicate predictions. The resulting LLM-conditioned queries are projected into SAM3's detector query space to drive accurate multi-instance segmentation in a single forward pass. This design equips SAM3 with high-level instruction understanding, compositional reasoning, and instance-level set prediction without modifying its core architecture. To support training and evaluation, we further construct Inst2Seg, a high-quality and large-scale instruction-based instance segmentation dataset and benchmark that couples free-form instructions with instance-level masks. Extensive experiments show that only 2B-scale InstructSAM achieves strong results across complex instruction-driven and phrase-level referring segmentation benchmarks, outperforming prior end-to-end methods and SAM3's agentic pipeline while enabling efficient single-pass multi-instance prediction.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25802.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weifeng Lin, Siyuan Huang, Hao Li, Tingwei Chen, Ruichuan An, Xinyu Wei, Jianbo Liu, Hongsheng Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is useful as a VLA initialization. In this paper, we study VLA initialization as a controlled representation-design problem along three axes: capability-level embodied VQA supervision, parameter-update strategy, and robot-data pretraining. Our experiments show that the original pretrained VLM representation is a key source of action performance. However, embodied VQA adaptation does not yield uniform gains: its benefit depends on downstream bottlenecks, and gains from different capability domains are not simply additive. For update strategy, LoRA provides a more reliable initialization than Full Finetune, indicating that overly reshaping the pretrained representation can weaken VLA initialization. Robot-data pretraining further improves VLA initialization, with the strongest variant obtained by staged LoRA-based training. Together, these findings suggest that effective VLM-to-VLA adaptation should inject action-relevant embodied and robot-trajectory signals while preserving the pretrained VLM representation that remains useful for action learning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26102</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25802</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Channel-wise Vector Quantization</title>
|
<title>LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence</title>
|
||||||
<link>https://arxiv.org/abs/2605.26089</link>
|
<link>https://arxiv.org/abs/2605.25979</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Song, Tianhang Wang, Yitong Chen, Tong Zhang, Zuxuan Wu, Ming Li, Jiaqi Wang, Kaicheng Yu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This formulation represents an image as discrete levels of visual details, rather than as a grid of spatial patches. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ achieves 100% codebook utilization with a 16K+ codebook size without any bells and whistles, and substantially improves reconstruction quality over conventional VQ; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiang An, Yin Xie, Feilong Tang, Yunyao Yan, Huajie Tan, Didi Zhu, Changrui Chen, Xiuwei Zhao, Bin Qin, Kaicheng Yang, Yifei Shen, Yuanhan Zhang, Kaichen Zhang, Wenkang Zhang, Zheng Cheng, Nansen Zhang, Chunsheng Wu, Chunjiang Ge, Zimin Ran, Dehua Song, Chunyuan Li, Shikun Feng, Ming Hu, Zhangquan Chen, Junbo Niu, Bo Li, Ziyong Feng, Ziwei Liu, Zongyuan Ge, Jiankang Deng</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of multimodal benchmarks. The model builds on a native OneVision-Encoder and incorporates Windowed Attention for efficient local computation while maintaining native resolution. Its key advance is codec-stream tokenization: it treats compressed video as a continuous bit-cost stream, where bit-cost dynamics determine adaptive temporal groups, and motion-residual cues select salient spatial evidence into compact visual canvases. This allocation concentrates a limited token budget on event-bearing content, enabling more stable long-video token compression than fixed groups of pictures. A shared 3D RoPE further places codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system. Furthermore, we build the LLaVA-OV-2 data and training stack around large-scale open supervision: approximately 8M re-captioned video samples for pretraining, a 4M-sample spatial corpus for fine-tuning. We also introduce JumpScore, a temporal-localization benchmark targeting fine-grained grounding in high-frequency, densely repeated motion, a regime underrepresented by existing video evaluations. A standout capability of LLaVA-OV-2 is its unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. On JumpScore, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B (30.1) by +44.8 points; under matched visual-token budgets on the same benchmark, codec-stream inputs improve temporal grounding over frame sampling by +9.7 points. Across standard benchmarks, LLaVA-OneVision-2-8B further outperforms Qwen3-VL-8B by +4.3 average points on video tasks, +5.3 on spatial tasks, and +15.6 average J&F on tracking tasks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26089</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25979</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World</title>
|
<title>D^2-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing</title>
|
||||||
<link>https://arxiv.org/abs/2605.26086</link>
|
<link>https://arxiv.org/abs/2605.25893</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusong Lin, Xinyuan Liang, Haiyang Wang, Qipeng Gu, Siqi Cheng, Jiangui Chen, Shuzhe Wu, Feiyang Pan, Lue Fan, Sanyuan Zhao, Dandan Tu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks similarly provide only partial user state and therefore fail to capture performance in such a broad, always-on setting. To address this gap, we introduce Claw-Anything, a benchmark that expands agent context along three dimensions: long-horizon activity histories, interdependent backend services, and integrated GUI and CLI interaction across multiple devices. To instantiate this setting, we simulate months of user activity through multi-round event injection, producing complex world states and realistic noise, including irrelevant events and conflicting signals. Agents must reason over rich contextual environments while remaining robust to such noise. This expanded scope also enables the evaluation of proactive assistance, requiring agents to anticipate user needs and deliver timely recommendations. Experiments show that GPT-5.5 achieves only 34.5% pass@1, substantially below prior benchmarks, underscoring a gap between current agent capabilities and the demands of always-on personal assistance. Alongside the benchmark, we release an automated data-generation pipeline that yields 2,000 training environments and improves the base model by 23.7%, demonstrating its utility of scalable data infrastructure.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25893.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aoxi Liu, Yupeng Chen, James Oldfield, Guanzhe Hong, Junchi Yu, Baoyuan Wu, Philip Torr, Adel Bibi</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely unexplored. Unlike AR-LLMs, D-LLMs generate text through a multi-step denoising process, exposing intermediate hidden representations that may contain safety-relevant information unavailable in standard single-step monitoring setups. Motivated by the suitability of lightweight probes for always-on monitoring, we analyze which trajectory-level signals best indicate when such probes are likely to struggle. We find that the most informative signal is safety hesitation: intermediate hidden states repeatedly falling within a small margin of the probe's decision boundary. The number of such hesitation steps in D-LLM's trajectory predicts probe failure effectively, providing a proxy of sample difficulty. Building on this analysis, we propose D^2-Monitor, a bi-level safety monitor for D-LLMs. D^2-Monitor adopts a lightweight probe as an always-on monitor to jointly estimate hesitation and perform base classification. When the hesitation level exceeds a threshold, a more expressive but computationally heavier probe is activated. This dynamic routing mechanism allocates monitoring resources efficiently at test time. Evaluated on 3 datasets (WildguardMix, ToxicChat, OpenAI-Moderation) across 4 D-LLMs, D^2-Monitor achieves state-of-the-art performance with a compact parameter footprint (leq 0.85M parameters), and exhibits the best trade-off between effectiveness and efficiency relative to 8 baselines.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26086</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.25893</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>On-Policy Adversarial Flow Distillation for Autoregressive Video Generation</title>
|
<title>LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV</title>
|
||||||
<link>https://arxiv.org/abs/2605.26105</link>
|
<link>https://arxiv.org/abs/2605.26244</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26105.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Luo, Shengju Qian, Xiaohang Tang, Zirui Zhu, Yong Liu, Xin Wang, Yang You</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout distribution, whereas practical teachers may expose only prompt-conditioned completed videos and may differ in architecture, capacity, temporal design, and sampling schedule. This interface makes supervised fine-tuning off-policy, score-based distillation inapplicable, and direct adversarial imitation too sparse for denoising-time credit assignment. We propose Adversarial Flow Distillation (AFD), an on-policy framework for heterogeneous black-box video distillation. AFD queries the teacher and rolls out the current student on the same prompts, trains a prompt-paired Bradley-Terry discriminator to estimate clean-sample teacher-student discrepancy, and converts the resulting on-policy advantage into forward-process flow-matching updates on the student's own noised states. Thus, AFD provides dense velocity-field supervision while requiring no teacher scores, latents, denoising trajectories, step alignment, or reverse-chain reinforcement learning. Experiments across two causal AR student families show that AFD consistently improves motion- and physics-sensitive generation while preserving general video quality, and ablations validate the importance of adaptive on-policy feedback and forward-process credit assignment. The method requires only clean teacher videos and student rollouts, providing a practical route for distilling proprietary or heterogeneous video generators into efficient autoregressive students.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tengfei Liu, Yang Shi, Xuanyu Zhu, Jiafu Tang, Liu Yang, Qixun Wang, Zhuoran Zhang, Yuqi Tang, Fengxiang Wang, Yuhao Dong, Xinlong Chen, Bozhou Li, Bohan Zeng, Yue Ding, Xiaohan Zhang, Jialu Chen, Haotian Wang, Yuanxing Zhang, Pengfei Wan, Leye Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned generation and rarely support unified evaluation across text, image, and video conditioning modalities. Moreover, they provide limited insight into how identity consistency, narrative coherence, and audio-visual alignment degrade over extended temporal horizons. To bridge this gap, we introduce LongAV-Compass, a systematic benchmark for minute-long audio-visual generation. LongAV-Compass contains 284 curated test cases spanning text-to-audio-video (T2AV), image-to-audio-video (I2AV), and video-to-audio-video (V2AV), organized by application scenario and generation complexity. The benchmark combines taxonomy-guided benchmark construction with a unified evaluation framework that integrates MLLM-assisted assessment with complementary perceptual and multimodal metrics, including DINO-v2, ArcFace, CLIP, and ImageBind. The framework evaluates more than 20 fine-grained dimensions covering within-segment quality, cross-segment consistency, global narrative coherence, semantic alignment, and audio-visual synchronization. Through experiments on 11 representative models together with human-alignment validation, LongAV-Compass provides a diagnostic testbed for analyzing the limitations of current systems in sustaining coherent, semantically aligned, and temporally consistent minute-scale audio-visual generation across diverse input modalities.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26105</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26244</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents</title>
|
<title>Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction</title>
|
||||||
<link>https://arxiv.org/abs/2605.25971</link>
|
<link>https://arxiv.org/abs/2605.26230</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25971.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyi Hu, Qirong Lyu, Xianghan Kong, Weiwen Liu, Jianghao Lin, Zixuan Guo, Yan Xu, Yasheng Wang, Weinan Zhang, Yong Yu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between interactions is largely wasted, leaving agents unable to prepare for future user needs. To bridge this gap, we introduce ProAct, a proactive agent architecture that leverages idle-time compute to anticipate and fulfill likely upcoming user needs. By analyzing evolving dialogue history together with persistent memory, ProAct predicts upcoming needs and iteratively acquires information, allowing the agent to resolve knowledge gaps and prepare evidence before the user initiates a query.To rigorously evaluate proactive capabilities, we also introduce ProActEval, a comprehensive benchmark comprising 200 scenarios across 40 domains, featuring predictable need chains and diverse user cognitive profiles. Empirical results demonstrate significant advantages over reactive baselines. ProAct accelerates task completion by reducing required turns by 14.8%, decreases user effort by 11.7%, and cuts hallucination rates by 28.1% on ProActEval. Furthermore, MemBench evaluations confirm that ProAct achieves state-of-the-art reflective accuracy, underscoring its sustained and robust performance.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26230.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jin Hyeon Kim, Jaeeun Lee, Claire Kim, Kyoungjin Oh, Paul Hyunbin Cho, Jaewon Min, Yeji Choi, Jihye Park, Hyunhee Park, Minkyu Park, Seungryong Kim</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas real-world observations often contain degradations that differ significantly from such settings. Improving robustness for multi-view 3D reconstruction under degraded conditions therefore remains an important challenge. We present Geometry-Aware Representation Denoising (GARD), a novel framework that performs diffusion-based multi-view restoration directly in the feature space of a feed-forward 3D reconstruction model. This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry. Furthermore, by employing an additional RGB image decoder, the refined representations can also be used to restore high-quality RGB images, thereby enabling the simultaneous recovery of 3D scene geometry and high-quality imagery. Comprehensive experiments on the Depth Anything 3 (DA3) benchmark demonstrate the effectiveness of the proposed GARD framework.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25971</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26230</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents</title>
|
<title>MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research</title>
|
||||||
<link>https://arxiv.org/abs/2605.25624</link>
|
<link>https://arxiv.org/abs/2605.26114</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Wang, Dunjie Lu, Junli Wang, Tianyi Bai, Shixuan Liu, Zhipeng Zhang, Haiquan Wang, Hao Hu, Tianbao Xie, Shuai Bai, Dayiheng Liu, Que Shen, Junyang Lin, Tao Yu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable environment, and verifiable reward. However, hand-curated benchmarks achieve high reward fidelity but cover few applications and LLM-as-judge-based datasets scale broadly but lack reliable verification. We present CUA-Gym, a scalable pipeline that co-generates task instructions, environment states, and reward functions. Concretely, a Generator agent constructs the initial and golden environment states, and a separate Discriminator agent writes the reward function from the task specification. An orchestrator agent drives the two through iterative rounds upon execution. Generated tuples then pass a final filter combining LLM majority voting and agent rollouts, ensuring quality beyond the per-task adversarial loop. To address the scarcity of training environments, we further synthesize CUA-Gym-Hub, a broad suite of high-fidelity mock web applications grounded in real-world software-use distributions, expanding the scale of CUA RLVR data by magnitude. Using this pipeline, we construct CUA-Gym, a dataset of 32,112 verified RLVR training tuples grounded in 110 environments. Trained with GSPO on CUA-Gym, our CUA-Gym-A3B and CUA-Gym-A17B achieve 62.1% and 72.6% on OSWorld-Verified, outperforming prior open-source CUAs at comparable scales, with performance scaling smoothly in both data volume and environment diversity. The same checkpoints also improve on the held-out WebArena benchmark, indicating transfer beyond the training environments. We will open-source the full synthesis pipeline, dataset, CUA-Gym-Hub environments, and models.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26114.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dingbang Wu, Rui Hao, Haiyang Wang, Shuzhe Wu, Han Xiao, Zhenghong Li, Bojiang Zhou, Zheng Ju, Zichen Liu, Lue Fan, Zhaoxiang Zhang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for everyday apps: verifiable outcome signals through deterministic state-based judging over structured JSON state, and scalable online RL through low-cost parallel rollouts. The full environment state is captured, configured, forked, and compared as structured JSON, and a single server can host hundreds of parallel instances, with about 400 MB memory per instance and about 3 s cold start. A layered state model and a declarative task-definition framework keep state programmability and task creation practical at scale, and a single programmatic judging mechanism delivers both deterministic evaluation verdicts and dense RL rewards. The accompanying MobileGym-Bench provides 416 parameterized task templates, including 256 test and 160 train templates, over 28 apps, with deterministic judges and a structured AnswerSheet protocol that avoids free-text matching failures. In a Sim-to-Real case study, GRPO on Qwen3-VL-4B-Instruct gains +12.8 percentage points on the 256-task test set, and on a 59-task real-device signal subset, real-device execution retains 95.1% of the simulation-side training gain. Project page: https://mobilegym.github.io.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25624</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26114</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement</title>
|
<title>RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models</title>
|
||||||
<link>https://arxiv.org/abs/2605.25569</link>
|
<link>https://arxiv.org/abs/2605.26632</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufeng Yang, Jianzhuang Liu, Jisheng Chu, Yuqi Peng, Xianfang Zeng, Jiancheng Huang, Shifeng Chen</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weighted flow matching loss that preserves image structure across continuous enhancement strengths. ControlLight allows users to edit real-world degraded low-light images toward satisfactory enhancement results by flexibly controlling the strength while preserving visual consistency and realism. Extensive experiments show that ControlLight achieves state-of-the-art performance against existing low-light enhancement approaches while demonstrating strong continuous controllability and generalization to real-world scenarios.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26632.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xing Cong, Hanlin Tang, Kan Liu, Lan Tao, Lin Qu, Chenhao Xie</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve FLOPs, remains underexplored. A key reason is that most existing approaches focus on weight sparsification, and pruning 50% of the weights can remove critical model capacity and degrade generation quality. Our study, however, shows that DiT activations are intrinsically sparse and significantly more robust to N:M semi-structured sparsification than weights. Motivated by this observation, we advocate a paradigm shift from weight sparsification to activation sparsification. We propose RT-Lynx, which applies N:M sparsification to activations and incorporates error-compensation techniques to mitigate accuracy loss. We further implement highly optimized CUDA kernels tailored to this setting, achieving up to a 1.55x speedup on average in linear layers. Extensive experiments across multiple diffusion models demonstrate that our method preserves the generation quality of the original models while substantially accelerating inference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25569</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26632</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion</title>
|
<title>MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale</title>
|
||||||
<link>https://arxiv.org/abs/2605.25449</link>
|
<link>https://arxiv.org/abs/2605.27235</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25449.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, David Paz, Xinyu Huang, Yuliang Guo, Yu-Lun Liu, Yue Wang, Liu Ren</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying cross-view inconsistency and temporal drift. We argue that 360° video generation offers a natural solution: panoramic coverage simplifies trajectory design and provides a strong global context for maintaining coherence. We introduce Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion, a controllable 360° video generation framework that synthesizes high-fidelity videos from sparse 360° inputs. The key idea is an explicit 3D Cache, reconstructed from the input, which serves as a geometric scaffold for any user-defined camera path. This allows the diffusion model to focus on photorealistic texture refinement while the 3D Cache enforces global geometric consistency. Experiments show that Pantheon360 achieves superior visual quality and unmatched geometric coherence, enabling reliable and flexible 360° scene generation for downstream simulation and digital-twin applications.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27235.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhicong Tang, Zhao Zhang, Jingye Chen, Mohan Zhou, Yifan Pu, Yuchi Liu, Yalong Bai, Ethan Smith, Yuhui Yuan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains an underexplored area at scale. To address this gap, we present MRT, a 20B-parameter masked region diffusion model tailored for multi-layer transparent image generation and editing, trained on over 10M multilingual design samples spanning diverse aspect ratios and textual prompts. To fully leverage this scale, we make two key technical contributions. First, we unify three complementary tasks including text-to-layers, image-to-layers, and layers-to-layers within a shared masked region diffusion framework, where selective token masking enables flexible layer-wise generation and editing. Second, to enable overflow layer generation, we introduce an overflow-aware canvas layer that handles boundary inconsistencies and supports semi-transparent background synthesis, enabling complete editable layers extending beyond visible canvas boundaries. Additionally, we apply diffusion distillation to achieve 8-step, real-time multi-layer generation with minimal quality degradation. Extensive experiments demonstrate that our framework substantially outperforms prior state-of-the-art approaches, including various commercial systems, across all three tasks, establishing a new benchmark for multi-layer transparent image generation. Notably, our model significantly outperforms the concurrent Qwen-Image-Layered model in image-to-layers quality according to user-study results, while achieving 10-100\times faster inference and reducing activation GPU memory consumption by 50-90\% during image-to-layer inference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25449</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27235</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Toward Native Multimodal Modeling: A Roadmap</title>
|
<title>Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments</title>
|
||||||
<link>https://arxiv.org/abs/2605.25343</link>
|
<link>https://arxiv.org/abs/2605.27209</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyu An, Junru Lu, Junnan Dong, Qiufeng Wang, Yinghui Li, Weizhi Fei, Zichao Yu, Zheng Yuan, Biao Liu, Haopeng Wang, Renzhao Liang, Yixuan Yang, Yunhang Shen, Bo Ke, Keyu Chen, Linhao Luo, Difan Zou, Xiao Huang, Di Yin, Ruizhi Qiao, Xing Sun</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite its potential, the design space of native architectures remains insufficiently defined. In this paper, we present the community with a formalized roadmap for this transition. Specifically, we formally define the architectural nativity, distinguishing mid-fusion and early-fusion from non-native paradigms. We further organize the existing native models through the lens of input-output duality into three categories: (i) Multi-to-Text for cross-modal comprehension with text-only output; (ii) Multi-to-Target for scenario-oriented generation, e.g., image, audio and video generation, and (iii) Multi-to-Multi for unified modeling with symmetric input-output. We deliver a comprehensive and industrial-grade investigation into the transition toward the definitive NMM framework, where understanding and generation seamlessly coexist within a unified transformer paradigm. We systematically unpack the end-to-end pipeline from industrial perspectives from architectural coordination, massive data curation, to full-stack training recipes, inference & deployment, and the comprehensive evaluation for truly native modeling.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxin Chen, Xiaodong Cai, Junfeng Fang, Zhuowen Han, Yu Wang, Yaorui Shi, Yi Zhang, Qi Gu, Xunliang Cai, Xiang Wang, An Zhang, Tat-Seng Chua</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often exhibit notable degradation when deployed in real-world settings, where environments are inherently stochastic and imperfect. We argue that this discrepancy arises from a fundamental mismatch between idealized training settings and real-world interaction dynamics, where current paradigms rely on carefully curated task instructions and stable, well-controlled environments. To address this gap, we propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process. We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution. We introduce such perturbations into the training pipeline by modifying user interaction patterns and simulating tool execution results within the training environment. To stabilize training while encouraging agents to handle increasingly challenging imperfections, noise is applied to only a subset of rollouts and progressively increased in difficulty as the model adapts to the current noise level. Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments. Our analysis reveals that training under noise conditions also yields performance gains on idealized benchmarks, suggesting that controlled exposure to environmental noise promotes more generalizable reasoning and decision-making behaviors. Our findings highlight the importance of modeling interaction imperfections for bridging the gap between agent training and real-world deployment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25343</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27209</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction</title>
|
<title>MobileMoE: Scaling On-Device Mixture of Experts</title>
|
||||||
<link>https://arxiv.org/abs/2605.26115</link>
|
<link>https://arxiv.org/abs/2605.27358</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26115.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weijie Wang, Zimu Li, Jinchuan Shi, Zeyu Zhang, Botao Ye, Marc Pollefeys, Donny Y. Chen, Bohan Zhuang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain centered on Gaussian primitives and expose surfaces only indirectly: extracting a usable mesh for downstream simulation, physics reasoning, or embodied interaction still requires expensive post-hoc steps that break the feed-forward promise. This limitation is especially pronounced in pose-free settings, where scene structure and camera parameters must be estimated jointly from sparse observations. We present TriSplat, a feed-forward reconstruction network that represents scenes with oriented triangle primitives and directly exports simulation-ready mesh scenes from a single forward pass. Given input images, the network predicts local 3D point maps, triangle attributes, camera poses, and optional intrinsics. Rather than regressing triangle orientation as an unconstrained latent variable, our approach constructs geometry normals from the predicted point maps, refines them with an image-conditioned normal head, and converts them into stable local frames for triangle parameterization. A mono-normal bootstrap schedule further stabilizes early training, while opacity and blur scheduling progressively sharpens the learned surface representation for direct mesh extraction. Experiments on RealEstate10K and DL3DV show that this representation produces more geometry-faithful reconstructions than Gaussian feed-forward baselines while maintaining competitive novel-view rendering quality. Because the rendering primitives are themselves surface triangles, the output can be directly ingested by physics engines, collision detectors, and standard rendering pipelines without any conversion, making it a practical simulation-ready solution for feed-forward 3D scene reconstruction.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27358.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanbei Chen, Hanxian Huang, Ernie Chang, Jacob Szwejbka, Digant Desai, Zechun Liu, Vikas Chandra, Raghuraman Krishnamoorthi</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present MobileMoE, a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier for on-device LLMs. We first formulate an on-device MoE scaling law that jointly optimizes MoE architecture under mobile memory and compute constraints, identifying an on-device sweet spot - moderate sparsity with fine-grained and shared experts - that is simultaneously memory and compute-optimal. Building on the derived architectures, we train MobileMoE with a four-stage recipe covering pre-training, mid-training, instruction fine-tuning, and quantization-aware training, all on open-source datasets. Across 14 benchmarks, MobileMoE matches or exceeds leading on-device dense LLMs with 2-4times fewer inference FLOPs, and matches or surpasses the state-of-the-art MoE OLMoE-1B-7B with up to 60% fewer parameters. To bridge the last mile to mobile deployment, we provide the first efficient MoE inference on commodity smartphones with comprehensive on-device profiling. At comparable INT4 weight memory, MobileMoE-S delivers 1.8-3.8times faster prefill and 2.2-3.4times faster decode than the dense baseline MobileLLM-Pro.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.26115</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27358</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation</title>
|
<title>Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini</title>
|
||||||
<link>https://arxiv.org/abs/2605.25874</link>
|
<link>https://arxiv.org/abs/2605.27295</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25874.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaining Ying, Hengrui Hu, Siyu Ren, Jiamu Li, Fengjiao Chen, Ziwen Wang, Xuezhi Cao, Xunliang Cai, Henghui Ding</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Interactive world models are advancing rapidly, yet existing benchmarks cover only part of the required competencies, leaving no unified standard for systematic evaluation. To fill this gap, we introduce WBench, a comprehensive multi-turn benchmark for interactive world model evaluation along five dimensions, namely video quality, setting adherence, interaction adherence, consistency, and physics compliance. WBench contains 289 test cases and 1,058 interaction turns, where each case specifies a world setting and a multi-turn interaction sequence, covering diverse scenes, styles, subjects, and both first- and third-person perspectives, together with four interaction types, including navigation, subject action, event editing, and perspective switching. For navigation, WBench unifies text, 6-DoF pose, and discrete-action control, enabling evaluation of models with different native input interfaces. Evaluation uses 22 automatic sub-metrics that combine specialist vision models with large multimodal models, and all metrics are validated against human judgments. Across 20 state-of-the-art models, we find that no single model performs strongly across all dimensions. We provide detailed diagnostic insights into the characteristic strengths, weaknesses, and open challenges of each model. Code and data are available at https://github.com/meituan-longcat/WBench.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang, Gustavo Hernández Ábrego, Shih-Cheng Huang, Aashi Jain, Daniel Salz, Sonam Goenka, Chaitra Hegde, Ji Ma, Feiyang Chen, Jiaxing Wu, Tanmaya Dabral, Babak Samari, Kevin Poulet, Daniel Cer, Kaifeng Chen, Paul Suganathan, Hui Hui, Jovan Andonov, Philippe Schlattner, Jay Han, Iftekhar Naim, Wing Lowe, Vladimir Pchelin, Albert Yang, Yi-Ting Chen, Zhongli Ding, Grace Zhang, Georg Heigold, Yichang Chen, Antoine Reveillon, Brendan Mccloskey, Wenlei Zhou, Dahun Kim, Rui Meng, Emma Wang, Jack Zheng, Halley Fede, Zhen Yang, Keegan Mosley, Brian Potetz, Sahil Dua, Henrique Schechter Vera, Shen Gao, Hesen Zhang, Andreas Hess, Hengxuan Ying, Alberto Montes, Karan Gill, Min Choi, Sebastian Russo, Anja Hauth, Jinhyuk Lee, Michael Boratko, Megan Barnes, Vikram Rao, Claudiu Musat, Cyril Allauzen, Ehsan Variani, Shankar Kumar, Tom Bagby, Junyi Jiao, Yang Gu, Tengxin Li, Ayush Agrawal, Roberto Santana, Dev Nath, Stephen Karukas, Shuoxuan Han, Lucia Loher, Alice Twu, Nidhi Vyas, Siddharth Bhai, Frank Palma Gomez, Wangyuan Zhang, Chaoren Liu, Jizheng Yang, Steve Qiu, Shijie Zhang, Sujay Kulkarni, Sascha Rothe, Sean Nakamoto, Raphael Hoffmann, Zach Gleicher, Yunhsuan Sung, Qin Yin, Tom Duerig, Mojtaba Seyedhosseini</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25874</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27295</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning</title>
|
<title>Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows</title>
|
||||||
<link>https://arxiv.org/abs/2605.25604</link>
|
<link>https://arxiv.org/abs/2605.24219</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.25604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guochao Jiang, Jingyi Song, Guofeng Quan, Chuzhan Hao, Guohua Liu, Yuewei Zhang</p><p><b>Upvotes:</b> 116</p><p><b>Summary:</b> Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to training instability, while Advantage Combination relies on static hyperparameters and ignores cross-objective correlations. To address these limitations, we propose Dynamic Variance-adaptive Advantage Optimization (DVAO), which dynamically adjusts combination weights based on the empirical reward variance of each objective within a rollout group, effectively up-weighting objectives with a stronger learning signal while suppressing noisy ones. We mathematically prove that DVAO maintains bounded advantage magnitudes for stable training and introduces a self-adaptive cross-objective regularization mechanism. Extensive experiments on mathematical reasoning and tool-use benchmarks using Qwen3 and Qwen2.5 models demonstrate that DVAO significantly outperforms baseline methods, achieving a superior multi-objective Pareto frontier and robust training stability.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.24219.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harshada Badave, Santosh Borse, Andrea Gomez, Harshitha Narahari, Sara Carter, Vishwa Bhatt, Aishani Rachakonda, Shuxin Lin, Dhaval Patel</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination benchmarks still evaluate only the final output, missing failures that originate in intermediate Thought-Action-Observation steps. We present Trajel, a dataset and evaluation framework for auditing trajectory-level hallucinations in multi-agent industrial workflows. Trajel introduces a five-type hallucination taxonomy (factual, referential, logical, procedural, and scope-based) over expert-annotated agent traces from AssetOpsBench. We benchmark supervised detection models at the subtask, trajectory, and long-context levels. Our results show that the most common failure modes are missed by existing benchmarks, that nearly half of hallucinated trajectories involve multiple types at once, and that automated detectors with high binary accuracy still misclassify the subtlest types. Trajectory-aware detection significantly outperforms standard post-hoc verification, making taxonomy-grounded evaluation necessary for safer agentic deployment.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2605.25604</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.24219</guid>
|
||||||
<pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate>
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27141</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxin Chen, Yi Zhang, Zhengzhou Cai, Yaorui Shi, Zhiyuan Yao, Chenhang Cui, Jingnan Zheng, Yaqi Huo, Xi Su, Qi Gu, Xunliang Cai, Xiang Wang, An Zhang, Tat-Seng Chua</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on understanding the user beyond what is explicitly stated, as user intent is often reflected in fragmented daily interactions and requires both personalized modeling and proactive interaction. However, existing agent benchmarks primarily evaluate reasoning and tool use, largely overlooking the challenges of inferring and leveraging user preferences in realistic scenarios. To address this gap, we introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions. In VitaBench 2.0, tasks are organized as temporally ordered sequences for individual users, where preferences are embedded in fragmented and heterogeneous interactions. Successful completion of tasks requires the agent to continuously extract, utilize, and update user preferences from these interactions. We further evaluate proactiveness through tasks that require agents to recognize missing information and actively acquire it from users or environments before making decisions. To support systematic analysis, we provide an extensible memory interface that enables controlled comparison across different memory architectures. We benchmark a diverse set of frontier proprietary and open-source LLMs. Results show that real-world personalization remains highly challenging even for state-of-the-art models, revealing a substantial gap between current capabilities and practical requirements. Extensive analysis further reveals the failure modes and capability bottlenecks of current agents in real-world personalized decision-making, providing insights for future model improvements.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27141</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27068</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ye Yuan, Rui Song, Weien Li, Zeyu Li, Haochen Liu, Xiangyu Kong, Changjiang Han, Yonghan Yang, Zichen Zhao, Zixuan Dong, Fuyuan Lyu, Bowei He, Haolun Wu, Jikun Kang, Xue Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environments are scored only by game outcomes such as win rates and largely remain to text-only interaction, making it difficult to tell whether an agent's language is actually grounded in what it perceived and did, or to identify the failure modes underlying its behavior. To address this gap, we introduce QUACK, an open-source environment and evaluation framework for auditing the grounding of agent language in multimodal social reasoning. QUACK evaluates agents at three levels: game outcomes, behavioral trajectories, and utterance-level consistency. Its core Statement Verification Pipeline reconstructs each agent's ground-truth trajectory from engine logs and checks every discussion claim against it, automatically flagging spatial hallucination, unsupported accusation, deception collapse, and language-action inconsistency. Evaluating three frontier VLMs in both homogeneous and cross-model adversarial settings, we find that even the strongest agent hallucinates 15.1% of its verifiable spatial claims and makes over half of its accusations without grounded evidence. We release the full engine, evaluation framework, toolkit, and logs at https://github.com/AAAAA-Academia-Attractions/QUACK.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27068</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27366</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huawei Lin, Peng Li, Jie Song, Fuxin Jiang, Tieying Zhang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent (Memory-Utilizing Skill Evolution), a skill-centric agent framework that lets agents continuously improve their task-solving capability by creating, reusing, and refining skills under a unified lifecycle (creation, memory, management, evaluation, and refinement). Our framework enables agents to create skills on demand, store and reuse them across tasks, organize and select them efficiently, and evaluate them through unit tests and runtime feedback for continuous refinement. We further introduce skill-level memory that accumulates experience for each skill across tasks, enabling more effective reuse and adaptation over time. Experiments on SkillsBench provide initial evidence that lifecycle-managed skills can improve task success, efficiency, reuse, and cross-agent transfer, highlighting the importance of treating skills as long-lived, experience-aware, and testable assets.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27366</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.26952</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26952.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dingwei Chen, Zefang Zong, Zhipeng Ma, Leo Luo, Yang Li, Chengming Li, Peng Chen, Jie Jiang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces increasing redundant tool calls and blurs the model's intrinsic knowledge boundary, where the model fails to distinguish when tools are needed versus when parametric knowledge suffices. Existing solutions based on reward shaping create coarse-grained optimization targets that tend to incentivize indiscriminate tool-call suppression, leading to reward hacking. In this paper, we propose AKBE (Agentic Knowledge Boundary Enhancement), an on-policy method that dynamically probes the model's intrinsic knowledge boundary through dual-path (with-tool and no-tool) rollouts during training. We define the knowledge boundary as the per-instance determination of whether tools are required and the minimum tool calls necessary. By comparing correctness across paths, AKBE categorizes trajectories and constructs targeted supervisory signals that guide efficient tool-use patterns for each question. These signals are integrated seamlessly into the agentic RL training loop. Experiments on seven QA benchmarks demonstrate that AKBE improves task accuracy by +1.85 on average and reduces tool calls by 18% over standard agentic RL, yielding 25% higher tool productivity without any accuracy-efficiency trade-off. Further analysis suggests its plug-and-play compatibility across different RL algorithms and the mechanism of each signal category. Our code is available at https://github.com/CuSO4-Chen/AKBE.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26952</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>JLT: Clean-Latent Prediction in Latent Diffusion Transformers</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27102</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27102.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Funing Fu, Tenghui Wang, Junyong Cen, Qichao Zhu, Guanyu Zhou</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images are mapped into a learned latent space, where compression has already removed much of the raw pixel variability. We introduce JLT, a 130M latent diffusion Transformer over frozen FLUX.2 VAE codes, and compare clean-latent prediction with a matched velocity-prediction DiT under the same representation, backbone, and training settings. Although the three variables x, epsilon, and v are linearly convertible for a fixed corruption time, a local Gaussian analysis shows that velocity regression inherits an isotropic target-covariance floor and amplifies low-variance latent directions, while clean prediction damps them. On ImageNet 256 x 256, JLT-B/1 obtains FID-50K 2.50 with classifier-free guidance, with a large matched-target gap over velocity prediction. These results suggest that prediction targets in latent diffusion are representation-dependent geometric choices, rather than interchangeable algebraic parameterizations.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27102</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.26895</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26895.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingze Wang, Shuchen Zhu, Yuxin Fang, Binghui Li, Kai Shen, Shu Zhong</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has been extensively studied, the scale vector remains poorly understood despite its ubiquitous use. In this work, we present a systematic study of scale vectors in LLMs from the perspectives of expressivity, optimization, and architectural structure. First, we show empirically that although scale vectors constitute only a negligible fraction of model parameters, removing them substantially degrades LLM pre-training. Our theory further shows that, in Pre-Norm architectures, scale vectors do not increase expressivity; instead, they improve optimization through a self-amplifying preconditioning effect on subsequent linear mappings. Second, we investigate the role of weight decay for scale vectors. By distinguishing Input-Norm and Output-Norm layers, we theoretically show that weight decay is beneficial for the former but harmful for the latter, due to their distinct roles in optimization and expressivity. Third, motivated by this understanding, we propose three lightweight and complementary improvements to scale vectors: branch-specific heterogeneity, improved placement around linear mappings, and magnitude-direction reparameterization. Both theory and experiments show that each improvement yields consistent gains. Finally, we combine these improvements into a unified scale-vector strategy and evaluate it through extensive LLM pre-training experiments on dense and mixture-of-experts models ranging from 0.12B to 2B parameters, across multiple optimizers and learning rate schedules, under industrial-scale token budgets. The unified strategy consistently achieves lower terminal loss than well-tuned baselines and exhibits more favorable scaling behavior, while adding negligible parameter and computational overhead.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26895</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27030</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinglin Wang, Hao Lin, Shaoxiong Feng, Peiwen Yuan, Yiwei Li, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Ji Zhang, Boyuan Pan, Yao Hu, Kan Li</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during search: intermediate discoveries remain branch-private and cannot guide other branches in time. This information isolation causes substantial redundant exploration, as branches repeatedly rediscover information already found elsewhere and require more search steps to collect complete decision information needed to reach correct answers. To bridge this gap, we propose Collaborative Parallel Thinking (CPT), a training-free inference framework that enables search-time information sharing across parallel branches. CPT extracts compact intermediate information from ongoing branches, maintains a deduplicated query-level information pool, and broadcasts pool entries through the input context, allowing each branch in subsequent search steps to reuse discoveries made by other branches rather than rediscover the same information. Empirically, experiments on HMMT and AIME benchmarks show that CPT establishes a stronger accuracy--latency Pareto frontier than strong baselines across rollout budgets and model scales, highlighting search-time collaboration as an effective direction for efficient parallel TTS.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27030</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.26494</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.26494.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MiniMax, Aili Chen, Aonian Li, Baichuan Zhou, Bangwei Gong, Binyang Jiang, Boji Dan, Changqing Yu, Chao Wang, Cheng Ma, Cheng Zhong, Cheng Zhu, Chengjun Xiao, Chengyi Yang, Chengyu Du, Chenyang Zhang, Chi Zhang, Chuangyi Huang, Chunhao Zhang, Chunhui Du, Chunyu Zhao, Congchao Guo, Da Chen, Deming Ding, Dianjun Sun, Dongyu Zhang, Enhui Yang, Fei Yu, Guang Zheng, Guodong Zheng, Guohong Li, Haichao Zhu, Haigang Zhou, Haimo Zhang, Han Ding, Hao Zhang, Haohai Sun, Haolin Lyu, Haonan Lu, Haoyu Wang, Huajie Shi, Huiyang Li, Jiacheng Chen, Jian Zhang, Jiaqi Zhuang, Jiaren Cai, Jiaxin Pan, Jiayao Li, Jiayuan Song, Jichuan Zhang, Jie Wang, Jihao Gu, Jin Zhu, Jingwei Dong, Jingyang Li, Jingyu Zhang, Jingze Zhuang, Jinhao Tian, Jinli Liu, Jinyi Hu, Jun Tao, Jun Zhang, Junbin Ruan, Junhao Xu, Junjie Yan, Junteng Liu, Junxian He, Kang Xu, Ke Ji, Ke Yang, Kecheng Xiao, Keyu Duan, Keyu Li, Le Han, Letian Ruan, Li Yuan, Lianfei Yu, Liheng Feng, Lijie Mo, Lin Li, Lingye Bao, Lingyu Yang, Lingyuan Zhou, Loki, Lu Chen, Lunbin Ceng, Ming Li, Ming Zhong, Mingliang Tao, Mingyuan Chi, Mujie Lin, Nan Hu, Ningxin Chen, Peiyin Zhu, Peng Gao, Pengcheng Gao, Pengfei Li, Penglin Li, Pengyu Zhao, Qibin Ren, Qidi Xu, Qihan Ren, Qile Li, Qin Wang, Quanliang Chen, Qunhong Ceng, Rong Tian, Rui Dong, Ruitao Leng, Ruize Zhang, Shanqi Liu, Shaoyu Chen, Sheng Jia, Shun Yao, Shuoran Zhao, Shuqi Yu, Sichen Li, Sicheng Pan, Songquan Zhu, Tengfei Li, Tian Xie, Tiancheng Qin, Tianrun Liang, Wei Liu, Weiqi Xu, Weitao Li, Weixiang Chen, Weiyu Cheng, Weiyu Zhang, Wenhu Chen, Wenqian Zhao, Xiancai Chen, Xiangjun Song, Xiangyuan Wang, Xiao Luo, Xiao Su, Xiaobo Li, Xiaodong Han, Xiaojie Wu, Xihao Song, Xingyi Han, Xinyu Guan, Xuan Lu, Xun Zou, Xunhao Lai, Xutong Li, Yan Gong, Yang Wang, Yang Xu, Yangsen Wang, Ye Tang, Yicheng Chen, Yinran Qiu, Yiqi Shi, Yiting Guo, Yiwen Huang, Yixuan Wang, Yongyi Hu, Yu Gao, Yu Zhang, Yuanxiang Ying, Yuanzhen Zhang, Yubo Wang, Yuchen Song, Yufeng Yang, Yuhang Meng, Yuhang Miao, Yuhao Li, Yujie Liu, Yulin Hu, Yunan Huang, Yunji Li, Yunyi Huang, Yusen Zhang, Yusu Hong, Yutao Xie, Yutong Zhang, Yuwen Liao, Yuxuan Shi, Yuze Wenren, Zebin Li, Zehan Li, Zejian Luo, Zeyu Jin, Zeyuan Sun, Zhanpeng Zhou, Zhaochen Su, Zhendong Li, Zhengmao Zhu, Zhengyuan Peng, Zhenhua Fan, Zhi Zhang, Zhichao Xu, Zhiheng Lv, Zhikang Xu, Zhitao He, Zhiwei He, Zhongyuan Li, Zibo Gao, Zijia Wu, Zijian Song, Zijian Zhou, Zijun Sun, Zishan Huang, Ziying Chen, Ziyue Ge</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.26494</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SpatialBench: Is Your Spatial Foundation Model an All-Round Player?</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27367</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27367.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haosong Peng, Hao Li, Jiaqi Chen, Yuhao Pan, Runmao Yao, Yalun Dai, Fushuo Huo, Fangzhou Hong, Zhaoxi Chen, Haozhao Wang, Dingwen Zhang, Ziwei Liu, Wenchao Xu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27367</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding</title>
|
||||||
|
<link>https://arxiv.org/abs/2605.27365</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2605.27365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihao Wang, Shilong Liu, Yuanguo Kuang, Xinyu Wei, Yangzhou Liu, Zhiqi Li, Yunze Man, Guo Chen, Andrew Tao, Guilin Liu, Jan Kautz, Lei Zhang, Zhiding Yu</p><p><b>Upvotes:</b> 91</p><p><b>Summary:</b> Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single step, LocateAnything preserves intra-box geometric coherence and unlocks substantial parallelism. We show that PBD improves both decoding throughput and localization accuracy. We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples, substantially increasing data diversity for high-precision localization. Extensive evaluations show that LocateAnything advances the speed-accuracy frontier, achieving significantly higher decoding throughput while improving high-IoU localization quality across diverse benchmarks. The results highlight the complementary benefits of Parallel Box Decoding and large-scale training data in enabling efficient and precise unified visual grounding and detection.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2605.27365</guid>
|
||||||
|
<pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user