bot: update RSS feed
This commit is contained in:
github-actions[bot]
258
feed.xml
258
feed.xml
@@ -7,202 +7,146 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Mon, 02 Mar 2026 00:03:10 +0000</lastBuildDate>
|
||||
<lastBuildDate>Tue, 03 Mar 2026 00:04:52 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games</title>
|
||||
<link>https://arxiv.org/abs/2602.17594</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Ivy Zhao, Nathan Cloos, Kelsey R. Allen, Thomas L. Griffiths, Katherine M. Collins, José Hernández-Orallo, Phillip Isola, Samuel J. Gershman, Joshua B. Tenenbaum</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this era of rapid technological advance. Conventional AI benchmarks typically assess only narrow capabilities in a limited range of human activity. Most are also static, quickly saturating as developers explicitly or implicitly optimize for them. We propose that a more promising way to evaluate human-like general intelligence in AI systems is through a particularly strong form of general game playing: studying how and how well they play and learn to play all conceivable human games, in comparison to human players with the same level of experience, time, or other resources. We define a "human game" to be a game designed by humans for humans, and argue for the evaluative suitability of this space of all such games people can imagine and enjoy -- the "Multiverse of Human Games". Taking a first step towards this vision, we introduce the AI GameStore, a scalable and open-ended platform that uses LLMs with humans-in-the-loop to synthesize new representative human games, by automatically sourcing and adapting standardized and containerized variants of game environments from popular human digital gaming platforms. As a proof of concept, we generated 100 such games based on the top charts of Apple App Store and Steam, and evaluated seven frontier vision-language models (VLMs) on short episodes of play. The best models achieved less than 10\% of the human average score on the majority of the games, and especially struggled with games that challenge world-model learning, memory and planning. We conclude with a set of next steps for building out the AI GameStore as a practical way to measure and drive progress toward human-like general intelligence in machines.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17594</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 18:17:25 +0000</pubDate>
|
||||
<title>DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference</title>
|
||||
<link>https://arxiv.org/abs/2602.18846</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual tokens or drop them progressively in language backbone, often trading accuracy for speed. In this work, we propose DUET-VLM, a versatile plug-and-play dual compression framework that consists of (a) vision-only redundancy aware compression of vision encoder's output into information-preserving tokens, followed by (b) layer-wise, salient text-guided dropping of visual tokens within the language backbone to progressively prune less informative tokens. This coordinated token management enables aggressive compression while retaining critical semantics. On LLaVA-1.5-7B, our approach maintains over 99% of baseline accuracy with 67% fewer tokens, and still retains >97% even at 89% reduction. With this dual-stage compression during training, it achieves 99.7% accuracy at 67% and 97.6% at 89%, surpassing prior SoTA visual token reduction methods across multiple benchmarks. When integrated into Video-LLaVA-7B, it even surpasses the baseline -- achieving >100% accuracy with a substantial 53.1% token reduction and retaining 97.6% accuracy under an extreme 93.4% setting. These results highlight end-to-end training with DUET-VLM, enabling robust adaptation to reduced visual (image/video) input without sacrificing accuracy, producing compact yet semantically rich representations within the same computational budget. Our code is available at https://github.com/AMD-AGI/DUET-VLM.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.18846</guid>
|
||||
<pubDate>Sat, 21 Feb 2026 14:22:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data</title>
|
||||
<link>https://arxiv.org/abs/2602.18253</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.18253.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xabier de Zuazo, Vincenzo Verbeni, Eva Navas, Ibon Saratxaga, Mathieu Bourguignon, Nicola Molinaro</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We pre-train a Conformer-based model on 50 hours of single-subject listening data and fine-tune on just 5 minutes per subject across 18 participants. Transfer learning yields consistent improvements, with in-task accuracy gains of 1-4% and larger cross-task gains of up to 5-6%. Not only does pre-training improve performance within each task, but it also enables reliable cross-task decoding between perception and production. Critically, models trained on speech production decode passive listening above chance, confirming that learned representations reflect shared neural processes rather than task-specific motor activity.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.18253</guid>
|
||||
<pubDate>Fri, 20 Feb 2026 14:39:50 +0000</pubDate>
|
||||
<title>LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding</title>
|
||||
<link>https://arxiv.org/abs/2602.20913</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20913.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jihao Qiu, Lingxi Xie, Xinyue Huo, Qi Tian, Qixiang Ye</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for efficient video context navigation, avoiding the redundancy of exhaustive search. At the core of LongVideo-R1 lies a reasoning module that leverages high-level visual cues to infer the most informative video clip for subsequent processing. During inference, the agent initiates traversal from top-level visual summaries and iteratively refines its focus, immediately halting the exploration process upon acquiring sufficient knowledge to answer the query. To facilitate training, we first extract hierarchical video captions from CGBench, a video corpus with grounding annotations, and guide GPT-5 to generate 33K high-quality chain-of-thought-with-tool trajectories. The LongVideo-R1 agent is fine-tuned upon the Qwen-3-8B model through a two-stage paradigm: supervised fine-tuning (SFT) followed by reinforcement learning (RL), where RL employs a specifically designed reward function to maximize selective and efficient clip navigation. Experiments on multiple long video benchmarks validate the effectiveness of name, which enjoys superior tradeoff between QA accuracy and efficiency. All curated data and source code are provided in the supplementary material and will be made publicly available. Code and data are available at: https://github.com/qiujihao19/LongVideo-R1</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.20913</guid>
|
||||
<pubDate>Tue, 24 Feb 2026 13:49:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance</title>
|
||||
<link>https://arxiv.org/abs/2602.20300</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> William Watson, Nicole Cho, Sumitra Ganesh, Manuela Veloso</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Model (LLM) hallucinations are usually treated as defects of the model or its decoding strategy. Drawing on classical linguistics, we argue that a query's form can also shape a listener's (and model's) response. We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension. Using 369,837 real-world queries, we ask: Are there certain types of queries that make hallucination more likely? A large-scale analysis reveals a consistent "risk landscape": certain features such as deep clause nesting and underspecification align with higher hallucination propensity. In contrast, clear intention grounding and answerability align with lower hallucination rates. Others, including domain specificity, show mixed, dataset- and model-dependent effects. Thus, these findings establish an empirically observable query-feature representation correlated with hallucination risk, paving the way for guided query rewriting and future intervention studies.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.20300</guid>
|
||||
<pubDate>Mon, 23 Feb 2026 19:30:08 +0000</pubDate>
|
||||
<title>Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling</title>
|
||||
<link>https://arxiv.org/abs/2602.21317</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guancheng Tu, Shiyang Zhang, Tianyu Zhang, Yi Zhang, Diji Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) are converging towards a singular Artificial Hivemind, where shared Nature (pre-training priors) result in a profound collapse of distributional diversity, limiting the distinct perspectives necessary for creative exploration and scientific discovery. To address this, we propose to equip models with inference-time Nurture (individualized epistemic trajectories) using Epistemic Evolution paradigm, progressing through explore, internalize, and express. We instantiate this via PRISM (Pluralistic Reasoning via In-context Structure Modeling), a model-agnostic system that augments LLM with dynamic On-the-fly Epistemic Graphs. On three creativity benchmarks, PRISM achieves state-of-the-art novelty and significantly expands distributional diversity. Moreover, we evaluate the real-world utility via a challenging rare-disease diagnosis benchmark. Results demonstrate that PRISM successfully uncovers correct long-tail diagnoses that standard LLM miss, confirming that its divergence stems from meaningful exploration rather than incoherent noise. Overall, this work establishes a new paradigm for Pluralistic AI, moving beyond monolithic consensus toward a diverse ecosystem of unique cognitive individuals capable of collective, multi-perspective discovery.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.21317</guid>
|
||||
<pubDate>Tue, 24 Feb 2026 19:38:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>No One Size Fits All: QueryBandits for Hallucination Mitigation</title>
|
||||
<link>https://arxiv.org/abs/2602.20332</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing. The dearth of studies focusing on hallucinations in closed-source models is especially concerning, as they constitute the vast majority of models in institutional deployments. We introduce QueryBandits, a model-agnostic contextual bandit framework that adaptively learns online to select the optimal query-rewrite strategy by leveraging an empirically validated and calibrated reward function. Across 16 QA scenarios, our top QueryBandit (Thompson Sampling) achieves an 87.5% win rate over a No-Rewrite baseline and outperforms zero-shot static policies (e.g., Paraphrase or Expand) by 42.6% and 60.3%, respectively. Moreover, all contextual bandits outperform vanilla bandits across all datasets, with higher feature variance coinciding with greater variance in arm selection. This substantiates our finding that there is no single rewrite policy optimal for all queries. We also discover that certain static policies incur higher cumulative regret than No-Rewrite, indicating that an inflexible query-rewriting policy can worsen hallucinations. Thus, learning an online policy over semantic features with QueryBandits can shift model behavior purely through forward-pass mechanisms, enabling its use with closed-source models and bypassing the need for retraining or gradient-based adaptation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.20332</guid>
|
||||
<pubDate>Mon, 23 Feb 2026 20:28:48 +0000</pubDate>
|
||||
<title>How to Take a Memorable Picture? Empowering Users with Actionable Feedback</title>
|
||||
<link>https://arxiv.org/abs/2602.21877</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21877.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of Memorability Feedback (MemFeed), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present MemCoach, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce MemBench, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.21877</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 13:02:35 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation</title>
|
||||
<link>https://arxiv.org/abs/2602.20423</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao, Hassan Rivaz</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation remains underexplored. We present MedCLIPSeg, a novel framework that adapts CLIP for robust, data-efficient, and uncertainty-aware medical image segmentation. Our approach leverages patch-level CLIP embeddings through probabilistic cross-modal attention, enabling bidirectional interaction between image and text tokens and explicit modeling of predictive uncertainty. Together with a soft patch-level contrastive loss that encourages more nuanced semantic learning across diverse textual prompts, MedCLIPSeg effectively improves data efficiency and domain generalizability. Extensive experiments across 16 datasets spanning five imaging modalities and six organs demonstrate that MedCLIPSeg outperforms prior methods in accuracy, efficiency, and robustness, while providing interpretable uncertainty maps that highlight local reliability of segmentation results. This work demonstrates the potential of probabilistic vision-language modeling for text-driven medical image segmentation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.20423</guid>
|
||||
<pubDate>Mon, 23 Feb 2026 23:46:05 +0000</pubDate>
|
||||
<title>Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets</title>
|
||||
<link>https://arxiv.org/abs/2602.22207</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanna Yukhymenko, Anton Alexandrov, Martin Vechev</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a fully automated framework designed to address these challenges by enabling scalable, high-quality translation of datasets and benchmarks. We demonstrate that adapting test-time compute scaling strategies, specifically Universal Self-Improvement (USI) and our proposed multi-round ranking method, T-RANK, allows for significantly higher quality outputs compared to traditional pipelines. Our framework ensures that benchmarks preserve their original task structure and linguistic nuances during localization. We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages (Ukrainian, Bulgarian, Slovak, Romanian, Lithuanian, Estonian, Turkish, Greek). Evaluations using both reference-based metrics and LLM-as-a-judge show that our translations surpass existing resources, resulting in more accurate downstream model assessment. We release both the framework and the improved benchmarks to facilitate robust and reproducible multilingual AI development.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22207</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 18:58:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models</title>
|
||||
<link>https://arxiv.org/abs/2602.20981</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.20981.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Christian Simon, Masato Ishii, Wei-Yao Wang, Koichi Saito, Akio Hayakawa, Dongseok Shim, Zhi Zhong, Shuyang Cui, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work, we tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on short instances can generalize to longer ones during testing. To tackle this challenge, we present multimodal hierarchical networks so-called MMHNet, an enhanced extension of state-of-the-art video-to-audio models. Our approach integrates a hierarchical method and non-causal Mamba to support long-form audio generation. Our proposed method significantly improves long audio generation up to more than 5 minutes. We also prove that training short and testing long is possible in the video-to-audio generation tasks without training on the longer durations. We show in our experiments that our proposed method could achieve remarkable results on long-video to audio benchmarks, beating prior works in video-to-audio tasks. Moreover, we showcase our model capability in generating more than 5 minutes, while prior video-to-audio methods fall short in generating with long durations.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.20981</guid>
|
||||
<pubDate>Tue, 24 Feb 2026 15:01:39 +0000</pubDate>
|
||||
<title>Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators</title>
|
||||
<link>https://arxiv.org/abs/2602.22647</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt, Raghunandan Keshavan, Shao-Chuan Wang, Xinyang Yi, Mingyan Gao, Onkar Dalal, Lichan Hong, Ed Chi, Ningren Han</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on business logic (e.g. enforcing content freshness or product category), which standard autoregressive decoding cannot natively support. Moreover, existing constrained decoding methods that make use of prefix trees (Tries) incur severe latency penalties on hardware accelerators (TPUs/GPUs). In this work, we introduce STATIC (Sparse Transition Matrix-Accelerated Trie Index for Constrained Decoding), an efficient and scalable constrained decoding technique designed specifically for high-throughput LLM-based generative retrieval on TPUs/GPUs. By flattening the prefix tree into a static Compressed Sparse Row (CSR) matrix, we transform irregular tree traversals into fully vectorized sparse matrix operations, unlocking massive efficiency gains on hardware accelerators. We deploy STATIC on a large-scale industrial video recommendation platform serving billions of users. STATIC produces significant product metric impact with minimal latency overhead (0.033 ms per step and 0.25% of inference time), achieving a 948x speedup over a CPU trie implementation and a 47-1033x speedup over a hardware-accelerated binary-search baseline. Furthermore, the runtime overhead of STATIC remains extremely low across a wide range of practical configurations. To the best of our knowledge, STATIC enables the first production-scale deployment of strictly constrained generative retrieval. In addition, evaluation on academic benchmarks demonstrates that STATIC can considerably improve cold-start performance for generative retrieval. Our code is available at https://github.com/youtube/static-constraint-decoding.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22647</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 06:00:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2602.21420</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21420.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened sampling, they simultaneously narrow the model's reasoning boundary and reduce generation diversity. We identify a root cause that existing methods overlook: the uniform penalization of errors. Current approaches -- whether data-filtering methods that select prompts by difficulty, or advantage normalization schemes -- treat all incorrect rollouts within a group identically. We show that this uniformity allows overconfident errors (incorrect reasoning paths that the RL process has spuriously reinforced) to persist and monopolize probability mass, ultimately suppressing valid exploratory trajectories. To address this, we propose the Asymmetric Confidence-aware Error Penalty (ACE). ACE introduces a per-rollout confidence shift metric, c_i = log(pi_theta(y_i|x) / pi_ref(y_i|x)), to dynamically modulate negative advantages. Theoretically, we demonstrate that ACE's gradient can be decomposed into the gradient of a selective regularizer restricted to overconfident errors, plus a well-characterized residual that partially moderates the regularizer's strength. We conduct extensive experiments fine-tuning Qwen2.5-Math-7B, Qwen3-8B-Base, and Llama-3.1-8B-Instruct on the DAPO-Math-17K dataset using GRPO and DAPO within the VERL framework. Evaluated on MATH-500 and AIME 2025, ACE composes seamlessly with existing methods and consistently improves the full Pass@k spectrum across all three model families and benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.21420</guid>
|
||||
<pubDate>Tue, 24 Feb 2026 22:46:43 +0000</pubDate>
|
||||
<title>dLLM: Simple Diffusion Language Modeling</title>
|
||||
<link>https://arxiv.org/abs/2602.22661</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22661.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanhui Zhou, Lingjie Chen, Hanghang Tong, Dawn Song</p><p><b>Upvotes:</b> 65</p><p><b>Summary:</b> Although diffusion language models (DLMs) are evolving quickly, many recent models converge on a set of shared components. These components, however, are distributed across ad-hoc research codebases or lack transparent implementations, making them difficult to reproduce or extend. As the field accelerates, there is a clear need for a unified framework that standardizes these common components while remaining flexible enough to support new methods and architectures. To address this gap, we introduce dLLM, an open-source framework that unifies the core components of diffusion language modeling -- training, inference, and evaluation -- and makes them easy to customize for new designs. With dLLM, users can reproduce, finetune, deploy, and evaluate open-source large DLMs such as LLaDA and Dream through a standardized pipeline. The framework also provides minimal, reproducible recipes for building small DLMs from scratch with accessible compute, including converting any BERT-style encoder or autoregressive LM into a DLM. We also release the checkpoints of these small DLMs to make DLMs more accessible and accelerate future research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22661</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 06:26:02 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling</title>
|
||||
<link>https://arxiv.org/abs/2602.21760</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.21760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Euisoo Jung, Byunghyun Kim, Hyunjin Kim, Seonghye Cho, Jae-Gil Lee</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism suffer from noticeable generation artifacts and fail to achieve substantial acceleration proportional to the number of GPUs. Therefore, we propose a hybrid parallelism framework that combines a novel data parallel strategy, condition-based partitioning, with an optimal pipeline scheduling method, adaptive parallelism switching, to reduce generation latency and achieve high generation quality in conditional diffusion models. The key ideas are to (i) leverage the conditional and unconditional denoising paths as a new data-partitioning perspective and (ii) adaptively enable optimal pipeline parallelism according to the denoising discrepancy between these two paths. Our framework achieves 2.31times and 2.07times latency reductions on SDXL and SD3, respectively, using two NVIDIA RTX~3090 GPUs, while preserving image quality. This result confirms the generality of our approach across U-Net-based diffusion models and DiT-based flow-matching architectures. Our approach also outperforms existing methods in acceleration under high-resolution synthesis settings. Code is available at https://github.com/kaist-dmlab/Hybridiff.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.21760</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 10:23:07 +0000</pubDate>
|
||||
<title>CL4SE: A Context Learning Benchmark For Software Engineering Tasks</title>
|
||||
<link>https://arxiv.org/abs/2602.23047</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23047.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haichuan Hu, Ye Shang, Guoqing Xie, Congqing He, Quanjun Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at test time without model fine-tuning. Despite its success, existing research lacks a systematic taxonomy of SE-specific context types and a dedicated benchmark to quantify the heterogeneous effects of different contexts across core SE workflows. To address this gap, we propose CL4SE (Context Learning for Software Engineering), a comprehensive benchmark featuring a fine-grained taxonomy of four SE-oriented context types (interpretable examples, project-specific context, procedural decision-making context, and positive & negative context), each mapped to a representative task (code generation, code summarization, code review, and patch correctness assessment). We construct high-quality datasets comprising over 13,000 samples from more than 30 open-source projects and evaluate five mainstream LLMs across nine metrics. Extensive experiments demonstrate that context learning yields an average performance improvement of 24.7% across all tasks. Specifically, procedural context boosts code review performance by up to 33% (Qwen3-Max), mixed positive-negative context improves patch assessment by 30% (DeepSeek-V3), project-specific context increases code summarization BLEU by 14.78% (GPT-Oss-120B), and interpretable examples enhance code generation PASS@1 by 5.72% (DeepSeek-V3). CL4SE establishes the first standardized evaluation framework for SE context learning, provides actionable empirical insights into task-specific context design, and releases a large-scale dataset to facilitate reproducible research in this domain.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23047</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 14:28:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain</title>
|
||||
<link>https://arxiv.org/abs/2602.22045</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Walter Hernandez Cruz, Peter Devine, Nikhil Vadgama, Paolo Tasca, Jiahua Xu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We introduce DLT-Corpus, the largest domain-specific text collection for Distributed Ledger Technology (DLT) research to date: 2.98 billion tokens from 22.12 million documents spanning scientific literature (37,440 publications), United States Patent and Trademark Office (USPTO) patents (49,023 filings), and social media (22 million posts). Existing Natural Language Processing (NLP) resources for DLT focus narrowly on cryptocurrencies price prediction and smart contracts, leaving domain-specific language under explored despite the sector's ~$3 trillion market capitalization and rapid technological evolution. We demonstrate DLT-Corpus' utility by analyzing technology emergence patterns and market-innovation correlations. Findings reveal that technologies originate in scientific literature before reaching patents and social media, following traditional technology transfer patterns. While social media sentiment remains overwhelmingly bullish even during crypto winters, scientific and patent activity grow independently of market fluctuations, tracking overall market expansion in a virtuous cycle where research precedes and enables economic growth that funds further innovation. We publicly release the full DLT-Corpus; LedgerBERT, a domain-adapted model achieving 23% improvement over BERT-base on a DLT-specific Named Entity Recognition (NER) task; and all associated tools and code.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22045</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 15:53:41 +0000</pubDate>
|
||||
<title>CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era</title>
|
||||
<link>https://arxiv.org/abs/2602.23452</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23452.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengqing Yuan, Kaiwen Shi, Zheyuan Zhang, Lichao Sun, Nitesh V. Chawla, Yanfang Ye</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Scientific research relies on accurate citation for attribution and integrity, yet large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications. Such hallucinated citations have already been observed in submissions and accepted papers at major machine learning venues, exposing vulnerabilities in peer review. Meanwhile, rapidly growing reference lists make manual verification impractical, and existing automated tools remain fragile to noisy and heterogeneous citation formats and lack standardized evaluation. We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing. Our multi-agent verification pipeline decomposes citation checking into claim extraction, evidence retrieval, passage matching, reasoning, and calibrated judgment to assess whether a cited source truly supports its claim. We construct a large-scale human-validated dataset across domains and define unified metrics for citation faithfulness and evidence alignment. Experiments with state-of-the-art LLMs reveal substantial citation errors and show that our framework significantly outperforms prior methods in both accuracy and interpretability. This work provides the first scalable infrastructure for auditing citations in the LLM era and practical tools to improve the trustworthiness of scientific references.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23452</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 19:17:39 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>veScale-FSDP: Flexible and High-Performance FSDP at Scale</title>
|
||||
<link>https://arxiv.org/abs/2602.22437</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Fully Sharded Data Parallel (FSDP), also known as ZeRO, is widely used for training large-scale models, featuring its flexibility and minimal intrusion on model code. However, current FSDP systems struggle with structure-aware training methods (e.g., block-wise quantized training) and with non-element-wise optimizers (e.g., Shampoo and Muon) used in cutting-edge models (e.g., Gemini, Kimi K2). FSDP's fixed element- or row-wise sharding formats conflict with the block-structured computations. In addition, today's implementations fall short in communication and memory efficiency, limiting scaling to tens of thousands of GPUs. We introduce veScale-FSDP, a redesigned FSDP system that couples a flexible sharding format, RaggedShard, with a structure-aware planning algorithm to deliver both flexibility and performance at scale. veScale-FSDP natively supports efficient data placement required by FSDP, empowering block-wise quantization and non-element-wise optimizers. As a result, veScale-FSDP achieves 5~66% higher throughput and 16~30% lower memory usage than existing FSDP systems, while scaling efficiently to tens of thousands of GPUs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22437</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 21:55:43 +0000</pubDate>
|
||||
<title>DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model</title>
|
||||
<link>https://arxiv.org/abs/2602.23622</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shibo Hong, Boxian Ai, Jun Kuang, Wei Wang, FengJiao Chen, Zhongyuan Peng, Chenhao Huang, Yixin Cao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate plausible adherence to instructions and strong reasoning ability on current benchmarks, their ability to edit small objects remains underexplored, despite its importance for precise local editing and refining details in both real and generated images. In this paper, we introduce DeepLookEditBench (DLEBench), the first benchmark dedicated to assessing the abilities of IIEMs in editing small-scale objects. Specifically, we construct a challenging testbed comprising 1889 samples across seven instruction types. In these samples, target objects occupy only 1%-10% of the image area, covering complex scenarios such as partial occlusion and multi-object editing. To ensure robust evaluation on this benchmark, we propose an evaluation protocol with refined score rubrics to minimize subjectivity and ambiguity in two criteria: Instruction Following and Visual Consistency. This protocol also introduces a dual-mode evaluation framework (Tool-driven and Oracle-guided Modes) addressing the misalignment between LMM-as-a-Judge and human judgements on DLEBench. Empirical results on 10 IIEMs reveal significant performance gaps in small-scale object editing, highlighting the need for specialized benchmarks to advance this ability.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23622</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 02:59:34 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns</title>
|
||||
<link>https://arxiv.org/abs/2602.22479</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22479.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Afshin Khadangi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Continual learning is a core requirement for deployed language models, yet standard training and fine-tuning pipelines remain brittle under non-stationary data. Online updates often induce catastrophic forgetting, while methods that improve stability frequently increase latency, memory footprint, or dense computation in ways that do not scale well to long contexts. We introduce TRC^{2} (Thalamically Routed Cortical Columns), a decoder-only backbone that addresses continual learning at the architectural level. TRC^{2} combines sparse thalamic routing over cortical columns with mechanisms for modulation, prediction, memory, and feedback, together with a fast corrective pathway that supports rapid adaptation without destabilizing slower parameters. The resulting block is sparse and chunk-parallel, enabling efficient training and inference while preserving clean ablations of each subsystem. We instantiate a reproducible training and evaluation stack and a continual-learning harness that measures proxy forgetting under streaming domain shifts. Across language modeling and continual learning benchmarks, TRC^{2} improves the stability-plasticity tradeoff at comparable compute, enabling rapid on-stream adaptation while preserving previously acquired behavior.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22479</guid>
|
||||
<pubDate>Wed, 25 Feb 2026 23:38:16 +0000</pubDate>
|
||||
<title>LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding</title>
|
||||
<link>https://arxiv.org/abs/2602.23881</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23881.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Samarin, Sergei Krutikov, Anton Shevtsov, Sergei Skvortsov, Filipp Fisin, Alexander Golubev</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly determined by the acceptance rate, yet standard training minimizes Kullback-Leibler (KL) divergence as a proxy objective. While KL divergence and acceptance rate share the same global optimum, small draft models, having limited capacity, typically converge to suboptimal solutions where minimizing KL does not guarantee maximizing acceptance rate. To address this issue, we propose LK losses, special training objectives that directly target acceptance rate. Comprehensive experiments across four draft architectures and six target models, ranging from 8B to 685B parameters, demonstrate consistent improvements in acceptance metrics across all configurations compared to the standard KL-based training. We evaluate our approach on general, coding and math domains and report gains of up to 8-10% in average acceptance length. LK losses are easy to implement, introduce no computational overhead and can be directly integrated into any existing speculator training framework, making them a compelling alternative to the existing draft training objectives.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23881</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 10:20:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Causal Motion Diffusion Models for Autoregressive Motion Generation</title>
|
||||
<link>https://arxiv.org/abs/2602.22594</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qing Yu, Akihisa Watanabe, Kent Fujiwara</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal causality and real-time applicability, or autoregressive models that suffer from instability and cumulative errors. In this work, we present Causal Motion Diffusion Models (CMDM), a unified framework for autoregressive motion generation based on a causal diffusion transformer that operates in a semantically aligned latent space. CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations. On top of this latent representation, an autoregressive diffusion transformer is trained using causal diffusion forcing to perform temporally ordered denoising across motion frames. To achieve fast inference, we introduce a frame-wise sampling schedule with causal uncertainty, where each subsequent frame is predicted from partially denoised previous frames. The resulting framework supports high-quality text-to-motion generation, streaming synthesis, and long-horizon motion generation at interactive rates. Experiments on HumanML3D and SnapMoGen demonstrate that CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness, while substantially reducing inference latency.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22594</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 03:58:25 +0000</pubDate>
|
||||
<title>Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks</title>
|
||||
<link>https://arxiv.org/abs/2602.23898</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23898.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihua Dong, Kuo Yang, Lin Ju, Handong Zhao, Yitian Zhang, Yizhou Wang, Huimin Zeng, Jianglin Lu, Yun Fu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Referring Expression Comprehension (REC) links language to region level visual perception. Standard benchmarks (RefCOCO, RefCOCO+, RefCOCOg) have progressed rapidly with multimodal LLMs but remain weak tests of visual reasoning and grounding: (i) many expressions are very short, leaving little reasoning demand; (ii) images often contain few distractors, making the target easy to find; and (iii) redundant descriptors enable shortcut solutions that bypass genuine text understanding and visual reasoning. We introduce Ref-Adv, a modern REC benchmark that suppresses shortcuts by pairing linguistically nontrivial expressions with only the information necessary to uniquely identify the target. The dataset contains referring expressions on real images, curated with hard distractors and annotated with reasoning facets including negation. We conduct comprehensive ablations (word order perturbations and descriptor deletion sufficiency) to show that solving Ref-Adv requires reasoning beyond simple cues, and we evaluate a broad suite of contemporary multimodal LLMs on Ref-Adv. Despite strong results on RefCOCO, RefCOCO+, and RefCOCOg, models drop markedly on Ref-Adv, revealing reliance on shortcuts and gaps in visual reasoning and grounding. We provide an in depth failure analysis and aim for Ref-Adv to guide future work on visual reasoning and grounding in MLLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23898</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 10:47:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios</title>
|
||||
<link>https://arxiv.org/abs/2602.22638</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiheng Song, Jingshuai Zhang, Chuan Qin, Chao Wang, Chao Chen, Longfei Xu, Kaikui Liu, Xiangxiang Chu, Hengshu Zhu</p><p><b>Upvotes:</b> 99</p><p><b>Summary:</b> Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries collected from Amap and covers a broad spectrum of route-planning intents across multiple cities worldwide. To enable reproducible, end-to-end evaluation, we design a deterministic API-replay sandbox that eliminates environmental variance from live services. We further propose a multi-dimensional evaluation protocol centered on outcome validity, complemented by assessments of instruction understanding, planning, tool use, and efficiency. Using MobilityBench, we evaluate multiple LLM-based route-planning agents across diverse real-world mobility scenarios and provide an in-depth analysis of their behaviors and performance. Our findings reveal that current models perform competently on Basic information retrieval and Route Planning tasks, yet struggle considerably with Preference-Constrained Route Planning, underscoring significant room for improvement in personalized mobility applications. We publicly release the benchmark data, evaluation toolkit, and documentation at https://github.com/AMAP-ML/MobilityBench .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22638</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 05:39:38 +0000</pubDate>
|
||||
<title>Accelerating Masked Image Generation by Learning Latent Controlled Dynamics</title>
|
||||
<link>https://arxiv.org/abs/2602.23996</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiwen Zhu, Quansheng Zeng, Yuandong Pu, Shuo Cao, Xiaohui Li, Yi Xin, Qi Qin, Jiayang Li, Yu Qiao, Jinjin Gu, Yihao Liu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete tokens, the rich semantics contained in the continuous features are lost. Some existing works attempt to cache the features to approximate future features. However, they exhibit considerable approximation error under aggressive acceleration rates. We attribute this to their limited expressivity and the failure to account for sampling information. To fill this gap, we propose to learn a lightweight model that incorporates both previous features and sampled tokens, and regresses the average velocity field of feature evolution. The model has moderate complexity that suffices to capture the subtle dynamics while keeping lightweight compared to the original base model. We apply our method, MIGM-Shortcut, to two representative MIGM architectures and tasks. In particular, on the state-of-the-art Lumina-DiMOO, it achieves over 4x acceleration of text-to-image generation while maintaining quality, significantly pushing the Pareto frontier of masked image generation. The code and model weights are available at https://github.com/Kaiwen-Zhu/MIGM-Shortcut.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23996</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 13:16:58 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization</title>
|
||||
<link>https://arxiv.org/abs/2602.22675</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianben Chen, Tianrui Qin, King Zhu, Qiexiang Wang, Chengjun Yu, Shu Xu, Jiaqi Wu, Jiayu Zhang, Xinpeng Liu, Xin Gui, Jingyi Cao, Piaohong Wang, Dingfeng Shi, He Zhu, Tiannan Wang, Yuqing Wang, Maojia Song, Tianyu Zheng, Ge Zhang, Jian Yang, Jiaheng Liu, Minghao Liu, Yuchen Eleanor Jiang, Wangchunshu Zhou</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains challenging. In this work, we propose Search More, Think Less (SMTL), a framework for long-horizon agentic search that targets both efficiency and generalization. SMTL replaces sequential reasoning with parallel evidence acquisition, enabling efficient context management under constrained context budgets. To support generalization across task types, we further introduce a unified data synthesis pipeline that constructs search tasks spanning both deterministic question answering and open-ended research scenarios with task appropriate evaluation metrics. We train an end-to-end agent using supervised fine-tuning and reinforcement learning, achieving strong and often state of the art performance across benchmarks including BrowseComp (48.6\%), GAIA (75.7\%), Xbench (82.0\%), and DeepResearch Bench (45.9\%). Compared to Mirothinker-v1.0, SMTL with maximum 100 interaction steps reduces the average number of reasoning steps on BrowseComp by 70.7\%, while improving accuracy.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22675</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 06:46:41 +0000</pubDate>
|
||||
<title>InfoNCE Induces Gaussian Distribution</title>
|
||||
<link>https://arxiv.org/abs/2602.24012</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24012.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE and its variants. In this work, we show that the InfoNCE objective induces Gaussian structure in representations that emerge from contrastive training. We establish this result in two complementary regimes. First, we show that under certain alignment and concentration assumptions, projections of the high-dimensional representation asymptotically approach a multivariate Gaussian distribution. Next, under less strict assumptions, we show that adding a small asymptotically vanishing regularization term that promotes low feature norm and high feature entropy leads to similar asymptotic results. We support our analysis with experiments on synthetic and CIFAR-10 datasets across multiple encoder architectures and sizes, demonstrating consistent Gaussian behavior. This perspective provides a principled explanation for commonly observed Gaussianity in contrastive representations. The resulting Gaussian model enables principled analytical treatment of learned representations and is expected to support a wide range of applications in contrastive learning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24012</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 13:35:58 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Imagination Helps Visual Reasoning, But Not Yet in Latent Space</title>
|
||||
<link>https://arxiv.org/abs/2602.22766</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang, Jinan Xu, Maosong Sun</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its effectiveness remain unclear. Motivated to demystify the true source of its efficacy, we investigate the validity of latent reasoning using Causal Mediation Analysis. We model the process as a causal chain: the input as the treatment, the latent tokens as the mediator, and the final answer as the outcome. Our findings uncover two critical disconnections: (a) Input-Latent Disconnect: dramatic perturbations on the input result in negligible changes to the latent tokens, suggesting that latent tokens do not effectively attend to the input sequence. (b) Latent-Answer Disconnect: perturbations on the latent tokens yield minimal impact on the final answer, indicating the limited causal effect latent tokens imposing on the outcome. Furthermore, extensive probing analysis reveals that latent tokens encode limited visual information and exhibit high similarity. Consequently, we challenge the necessity of latent reasoning and propose a straightforward alternative named CapImagine, which teaches the model to explicitly imagine using text. Experiments on vision-centric benchmarks show that CapImagine significantly outperforms complex latent-space baselines, highlighting the superior potential of visual reasoning through explicit imagination.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22766</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 08:56:23 +0000</pubDate>
|
||||
<title>SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching</title>
|
||||
<link>https://arxiv.org/abs/2602.24208</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24208.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yasaman Haghighi, Alexandre Alahi</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduces computation by reusing previously computed model outputs across timesteps. Existing caching methods rely on heuristic criteria to choose cache/reuse timesteps and require extensive tuning. We address this limitation with a principled sensitivity-aware caching framework. Specifically, we formalize the caching error through an analysis of the model output sensitivity to perturbations in the denoising inputs, i.e., the noisy latent and the timestep, and show that this sensitivity is a key predictor of caching error. Based on this analysis, we propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis. Our framework provides a theoretical basis for adaptive caching, explains why prior empirical heuristics can be partially effective, and extends them to a dynamic, sample-specific approach. Experiments on Wan 2.1, CogVideoX, and LTX-Video show that SenCache achieves better visual quality than existing caching methods under similar computational budgets.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24208</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 17:36:09 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models</title>
|
||||
<link>https://arxiv.org/abs/2602.22859</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongrui Jia, Chaoya Jiang, Shikun Zhang, Wei Ye</p><p><b>Upvotes:</b> 147</p><p><b>Summary:</b> As Large Multimodal Models (LMMs) scale up and reinforcement learning (RL) methods mature, LMMs have made notable progress in complex reasoning and decision making. Yet training still relies on static data and fixed recipes, making it difficult to diagnose capability blind spots or provide dynamic, targeted reinforcement. Motivated by findings that test driven error exposure and feedback based correction outperform repetitive practice, we propose Diagnostic-driven Progressive Evolution (DPE), a spiral loop where diagnosis steers data generation and reinforcement, and each iteration re-diagnoses the updated model to drive the next round of targeted improvement. DPE has two key components. First, multiple agents annotate and quality control massive unlabeled multimodal data, using tools such as web search and image editing to produce diverse, realistic samples. Second, DPE attributes failures to specific weaknesses, dynamically adjusts the data mixture, and guides agents to generate weakness focused data for targeted reinforcement. Experiments on Qwen3-VL-8B-Instruct and Qwen2.5-VL-7B-Instruct show stable, continual gains across eleven benchmarks, indicating DPE as a scalable paradigm for continual LMM training under open task distributions. Our code, models, and data are publicly available at https://github.com/hongruijia/DPE.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22859</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 10:53:57 +0000</pubDate>
|
||||
<title>Enhancing Spatial Understanding in Image Generation via Reward Modeling</title>
|
||||
<link>https://arxiv.org/abs/2602.24233</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyu Tang, Chaoran Feng, Yufan Deng, Jie Wu, Xiaojie Li, Rui Wang, Yunpeng Chen, Daquan Zhou</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attempts. To address this challenge, we introduce a novel method that strengthens the spatial understanding of current image generation models. We first construct the SpatialReward-Dataset with over 80k preference pairs. Building on this dataset, we build SpatialScore, a reward model designed to evaluate the accuracy of spatial relationships in text-to-image generation, achieving performance that even surpasses leading proprietary models on spatial evaluation. We further demonstrate that this reward model effectively enables online reinforcement learning for the complex spatial generation. Extensive experiments across multiple benchmarks show that our specialized reward model yields significant and consistent gains in spatial understanding for image generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24233</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 17:59:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>OmniGAIA: Towards Native Omni-Modal AI Agents</title>
|
||||
<link>https://arxiv.org/abs/2602.22897</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong, Jiajie Jin, Hao Wang, Yinuo Wang, Ji-Rong Wen, Yuan Lu, Zhicheng Dou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajectories synthesized via a hindsight-guided tree exploration strategy and OmniDPO for fine-grained error correction, OmniAtlas effectively enhances the tool-use capabilities of existing open-source models. This work marks a step towards next-generation native omni-modal AI assistants for real-world scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22897</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 11:35:04 +0000</pubDate>
|
||||
<title>Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models</title>
|
||||
<link>https://arxiv.org/abs/2602.24264</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arnas Uselis, Andrea Dittadi, Seong Joon Oh</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massive datasets, they still cover only a tiny fraction of the combinatorial space of possible inputs, raising the question of what structure representations must have to support generalization to unseen combinations. We formalize three desiderata for compositional generalization under standard training (divisibility, transferability, stability) and show they impose necessary geometric constraints: representations must decompose linearly into per-concept components, and these components must be orthogonal across concepts. This provides theoretical grounding for the Linear Representation Hypothesis: the linear structure widely observed in neural representations is a necessary consequence of compositional generalization. We further derive dimension bounds linking the number of composable concepts to the embedding geometry. Empirically, we evaluate these predictions across modern vision models (CLIP, SigLIP, DINO) and find that representations exhibit partial linear factorization with low-rank, near-orthogonal per-concept factors, and that the degree of this structure correlates with compositional generalization on unseen combinations. As models continue to scale, these conditions predict the representational geometry they may converge to. Code is available at https://github.com/oshapio/necessary-compositionality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24264</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 18:32:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>General Agent Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2602.22953</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.22953.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Elron Bandel, Asaf Yehudai, Lilach Eden, Yehoshua Sagron, Yotam Perlitz, Elad Venezian, Natalia Razinkov, Natan Ergas, Shlomit Shachor Ifergan, Segev Shlomov, Michal Jacovi, Leshem Choshen, Liat Ein-Dor, Yoav Katz, Michal Shmueli-Scheuer</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The promise of general-purpose agents - systems that perform tasks in unfamiliar environments without domain-specific engineering - remains largely unrealized. Existing agents are predominantly specialized, and while emerging implementations like OpenAI SDK Agent and Claude Code hint at broader capabilities, no systematic evaluation of their general performance has been pursued. Current agentic benchmarks assume domain-specific integration, encoding task information in ways that preclude fair evaluation of general agents. This paper frames general-agent evaluation as a first-class research objective. We propose conceptual principles for such evaluation, a Unified Protocol enabling agent-benchmark integration, and Exgentic - a practical framework for general agent evaluation. We benchmark five prominent agent implementations across six environments as the first Open General Agent Leaderboard. Our experiments show that general agents generalize across diverse environments, achieving performance comparable to domain-specific agents without any environment-specific tuning. We release our evaluation protocol, framework, and leaderboard to establish a foundation for systematic research on general-purpose agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.22953</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 12:48:02 +0000</pubDate>
|
||||
<title>Memory Caching: RNNs with Growing Memory</title>
|
||||
<link>https://arxiv.org/abs/2602.24281</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes quadratic complexity and so has motivated recent studies to explore viable subquadratic recurrent alternatives. Despite showing promising preliminary results in diverse domains, such recurrent architectures underperform Transformers in recall-intensive tasks, often attributed to their fixed-size memory. In this paper, we introduce Memory Caching (MC), a simple yet effective technique that enhances recurrent models by caching checkpoints of their memory states (a.k.a. hidden states). Memory Caching allows the effective memory capacity of RNNs to grow with sequence length, offering a flexible trade-off that interpolates between the fixed memory (i.e., O(L) complexity) of RNNs and the growing memory (i.e., O(L^2) complexity) of Transformers. We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules. Our experimental results on language modeling, and long-context understanding tasks show that MC enhances the performance of recurrent models, supporting its effectiveness. The results of in-context recall tasks indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24281</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 18:53:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2602.23008</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyuan Liu, Jeonghye Kim, Xufang Luo, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose Exploratory Memory-Augmented On- and Off-Policy Optimization (EMPO^2), a hybrid RL framework that leverages memory for exploration and combines on- and off-policy updates to make LLMs perform well with memory while also ensuring robustness without it. On ScienceWorld and WebShop, EMPO^2 achieves 128.6% and 11.3% improvements over GRPO, respectively. Moreover, in out-of-distribution tests, EMPO^2 demonstrates superior adaptability to new tasks, requiring only a few trials with memory and no parameter updates. These results highlight EMPO^2 as a promising framework for building more exploratory and generalizable LLM-based agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23008</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 13:50:57 +0000</pubDate>
|
||||
<title>CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation</title>
|
||||
<link>https://arxiv.org/abs/2602.24286</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24286.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao, Jiahao Li, Chengquan Jiang, Weiqiang Lou, Yufan Song, Hongli Yu, Jiaze Chen, Wei-Ying Ma, Ya-Qin Zhang, Jingjing Liu, Mingxuan Wang, Xin Liu, Hao Zhou</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24286</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 18:58:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GeoWorld: Geometric World Models</title>
|
||||
<link>https://arxiv.org/abs/2602.23058</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23058.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Zhang, Danning Li, Ian Reid, Richard Hartley</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their latent representations are typically learned in Euclidean space, neglecting the underlying geometric and hierarchical structure among states, and (ii) they struggle with long-horizon prediction, which leads to rapid degradation across extended rollouts. To address these challenges, we introduce GeoWorld, a geometric world model that preserves geometric structure and hierarchical relations through a Hyperbolic JEPA, which maps latent representations from Euclidean space onto hyperbolic manifolds. We further introduce Geometric Reinforcement Learning for energy-based optimization, enabling stable multi-step planning in hyperbolic latent space. Extensive experiments on CrossTask and COIN demonstrate around 3% SR improvement in 3-step planning and 2% SR improvement in 4-step planning compared to the state-of-the-art V-JEPA 2. Project website: https://steve-zeyu-zhang.github.io/GeoWorld.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23058</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 14:42:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>The Trinity of Consistency as a Defining Principle for General World Models</title>
|
||||
<link>https://arxiv.org/abs/2602.23152</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Wei, Siyuan Li, Yuhang Xu, Zheng Sun, Junjie Jiang, Hexuan Jin, Caijun Jia, Honghao He, Xinglong Xu, Xi bai, Chang Yu, Yumou Liu, Junnan Zhu, Xuanhe Zhou, Jintao Chen, Xiaobin Hu, Shancheng Pang, Bihui Yu, Ran He, Zhen Lei, Stan Z. Li, Conghui He, Shuicheng Yan, Cheng Tan</p><p><b>Upvotes:</b> 188</p><p><b>Summary:</b> The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23152</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 16:15:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation</title>
|
||||
<link>https://arxiv.org/abs/2602.23165</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichen Peng, Jyun-Ting Song, Siyeol Jung, Ruofan Liu, Haiyang Liu, Xuangeng Chu, Ruicong Liu, Erwin Wu, Hideki Koike, Kris Kitani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between two people engaging in conversation. We present DyaDiT, a multi-modal diffusion transformer that generates contextually appropriate human motion from dyadic audio signals. Trained on Seamless Interaction Dataset, DyaDiT takes dyadic audio with optional social-context tokens to produce context-appropriate motion. It fuses information from both speakers to capture interaction dynamics, uses a motion dictionary to encode motion priors, and can optionally utilize the conversational partner's gestures to produce more responsive motion. We evaluate DyaDiT on standard motion generation metrics and conduct quantitative user studies, demonstrating that it not only surpasses existing methods on objective metrics but is also strongly preferred by users, highlighting its robustness and socially favorable motion generation. Code and models will be released upon acceptance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23165</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 16:30:07 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents</title>
|
||||
<link>https://arxiv.org/abs/2602.23205</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23205.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjia Wang, Liang Pan, Huaijin Pi, Yuke Lou, Xuqian Ren, Yifan Wu, Zhouyingcheng Liao, Lei Yang, Rishabh Dabral, Christian Theobalt, Taku Komura</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly studio setups and wearable devices, limiting the large-scale collection of scene-conditioned human motion data in the wild. To address this, we propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones. Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes within a unified metric world coordinate frame. The proposed method allows metric-scale and scene-consistent capture in everyday environments without static cameras or markers, bridging human motion and scene geometry seamlessly. Compared with optical capture ground truth, we demonstrate that the dual-view setting exhibits a remarkable ability to mitigate depth ambiguity, achieving superior alignment and reconstruction performance over single iphone or monocular models. Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune on feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via sim-to-real RL to replicate human motions depicted in videos. Experimental results validate the effectiveness of our pipeline and its contributions towards advancing embodied AI research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23205</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 16:53:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning</title>
|
||||
<link>https://arxiv.org/abs/2602.23258</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their deployability and adaptability. We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining. Our approach acts as an active firewall, intercepting agent outputs and employing a retrieval-augmented rectifier to iteratively correct errors based on a failure-driven indicator pool. This mechanism allows for the precise identification of potential errors using distilled failure patterns as prior knowledge. Irreparable outputs are subsequently pruned to prevent error propagation, while a fallback strategy preserves system integrity. Empirical results on extensive math benchmarks show that AgentDropoutV2 significantly boosts the MAS's task performance, achieving an average accuracy gain of 6.3 percentage points on math benchmarks. Furthermore, the system exhibits robust generalization and adaptivity, dynamically modulating rectification efforts based on task difficulty while leveraging context-aware indicators to resolve a wide spectrum of error patterns. Our code and dataset are released at https://github.com/TonySY2/AgentDropoutV2.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23258</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 17:31:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving</title>
|
||||
<link>https://arxiv.org/abs/2602.23259</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangxin Sun, Feng Xue, Teng Long, Chang Liu, Jian-Fang Hu, Wei-Shi Zheng, Nicu Sebe</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Currently, IL-based methods have become a mainstream paradigm: models rely on standard driving behaviors given by experts, and learn to minimize the discrepancy between their actions and expert actions. However, this objective of "only driving like the expert" suffers from limited generalization: when encountering rare or unseen long-tail scenarios outside the distribution of expert demonstrations, models tend to produce unsafe decisions in the absence of prior experience. This raises a fundamental question: Can an E2E-AD system make reliable decisions without any expert action supervision? Motivated by this, we propose a unified framework named Risk-aware World Model Predictive Control (RaWMPC) to address this generalization dilemma through robust control, without reliance on expert demonstrations. Practically, RaWMPC leverages a world model to predict the consequences of multiple candidate actions and selects low-risk actions through explicit risk evaluation. To endow the world model with the ability to predict the outcomes of risky driving behaviors, we design a risk-aware interaction strategy that systematically exposes the world model to hazardous behaviors, making catastrophic outcomes predictable and thus avoidable. Furthermore, to generate low-risk candidate actions at test time, we introduce a self-evaluation distillation method to distill riskavoidance capabilities from the well-trained world model into a generative action proposal network without any expert demonstration. Extensive experiments show that RaWMPC outperforms state-of-the-art methods in both in-distribution and out-of-distribution scenarios, while providing superior decision interpretability.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23259</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 17:32:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?</title>
|
||||
<link>https://arxiv.org/abs/2602.23339</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23339.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23339</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 18:45:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale</title>
|
||||
<link>https://arxiv.org/abs/2602.23361</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23361.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sven Elflein, Ruilong Li, Sérgio Agostinho, Zan Gojcic, Laura Leal-Taixé, Qunjie Zhou, Aljosa Osep</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements grow quadratically w.r.t. the number of input images. Our approach is built on the key insight that this bottleneck stems from the varying-length Key-Value (KV) space representation of scene geometry, which we distill into a fixed-size Multi-Layer Perceptron (MLP) via test-time training. VGG-T^3 (Visual Geometry Grounded Test Time Training) scales linearly w.r.t. the number of input views, similar to online models, and reconstructs a 1k image collection in just 54 seconds, achieving a 11.6times speed-up over baselines that rely on softmax attention. Since our method retains global scene aggregation capability, our point map reconstruction error outperforming other linear-time methods by large margins. Finally, we demonstrate visual localization capabilities of our model by querying the scene representation with unseen images.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23361</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 18:59:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MediX-R1: Open Ended Medical Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2602.23363</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.23363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Omair Mohamed, Mohamed Zidan, Fahad Khan, Salman Khan, Rao Anwer, Hisham Cholakkal</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically grounded, free-form answers beyond multiple-choice formats. MediX-R1 fine-tunes a baseline vision-language backbone with Group Based RL and a composite reward tailored for medical reasoning: an LLM-based accuracy reward that judges semantic correctness with a strict YES/NO decision, a medical embedding-based semantic reward to capture paraphrases and terminology variants, and lightweight format and modality rewards that enforce interpretable reasoning and modality recognition. This multi-signal design provides stable, informative feedback for open-ended outputs where traditional verifiable or MCQ-only rewards fall short. To measure progress, we propose a unified evaluation framework for both text-only and image+text tasks that uses a Reference-based LLM-as-judge in place of brittle string-overlap metrics, capturing semantic correctness, reasoning, and contextual alignment. Despite using only sim51K instruction examples, MediX-R1 achieves excellent results across standard medical LLM (text-only) and VLM (image + text) benchmarks, outperforming strong open-source baselines and delivering particularly large gains on open-ended clinical tasks. Our results demonstrate that open-ended RL with comprehensive reward signals and LLM-based evaluation is a practical path toward reliable medical reasoning in multimodal models. Our trained models, curated datasets and source code are available at https://medix.cvmbzuai.com</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.23363</guid>
|
||||
<pubDate>Thu, 26 Feb 2026 18:59:46 +0000</pubDate>
|
||||
<title>Mode Seeking meets Mean Seeking for Fast Long Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2602.24289</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.24289.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer. Our approach utilizes a global Flow Matching head trained via supervised learning on long videos to capture narrative structure, while simultaneously employing a local Distribution Matching head that aligns sliding windows to a frozen short-video teacher via a mode-seeking reverse-KL divergence. This strategy enables the synthesis of minute-scale videos that learns long-range coherence and motions from limited long videos via supervised flow matching, while inheriting local realism by aligning every sliding-window segment of the student to a frozen short-video teacher, resulting in a few-step fast long video generator. Evaluations show that our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency. Project website: https://primecai.github.io/mmm/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.24289</guid>
|
||||
<pubDate>Fri, 27 Feb 2026 18:59:02 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user