bot: update RSS feed
This commit is contained in:
github-actions[bot]
319
feed.xml
319
feed.xml
@@ -7,223 +7,230 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Fri, 20 Mar 2026 00:05:08 +0000</lastBuildDate>
|
||||
<lastBuildDate>Sat, 21 Mar 2026 00:04:24 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA</title>
|
||||
<link>https://arxiv.org/abs/2603.08501</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08501.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd Hawasly, Mohammed Qusay Hashim, Kareem Darwish, Firoj Alam</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especially consequential in Islamic settings where users expect grounding in canonical texts (Qur'an and Hadith) and jurisprudential (fiqh) nuance. Retrieval-augmented generation (RAG) reduces some of these limitations by grounding generation in external evidence. However, a single ``retrieve-then-generate'' pipeline is limited to deal with the diversity of Islamic queries. Users may request verbatim scripture, fatwa-style guidance with citations or rule-constrained computations such as zakat and inheritance that require strict arithmetic and legal invariants. In this work, we present a bilingual (Arabic/English) multi-agent Islamic assistant, called Fanar-Sadiq, which is a core component of the Fanar AI platform. Fanar-Sadiq routes Islamic-related queries to specialized modules within an agentic, tool-using architecture. The system supports intent-aware routing, retrieval-grounded fiqh answers with deterministic citation normalization and verification traces, exact verse lookup with quotation validation, and deterministic calculators for Sunni zakat and inheritance with madhhab-sensitive branching. We evaluate the complete end-to-end system on public Islamic QA benchmarks and demonstrate effectiveness and efficiency. Our system is currently publicly and freely accessible through API and a Web application, and has been accessed approx1.9M times in less than a year.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.08501</guid>
|
||||
<pubDate>Mon, 09 Mar 2026 15:35:12 +0000</pubDate>
|
||||
<title>COT-FM: Cluster-wise Optimal Transport Flow Matching</title>
|
||||
<link>https://arxiv.org/abs/2603.13395</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13395.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chiensheng Chiang, Kuan-Hsun Tu, Jia-Wei Liao, Cheng-Fu Chou, Tsung-Wei Ke</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce COT-FM, a general framework that reshapes the probability path in Flow Matching (FM) to achieve faster and more reliable generation. FM models often produce curved trajectories due to random or batchwise couplings, which increase discretization error and reduce sample quality. COT-FM fixes this by clustering target samples and assigning each cluster a dedicated source distribution obtained by reversing pretrained FM models. This divide-and-conquer strategy yields more accurate local transport and significantly straighter vector fields, all without changing the model architecture. As a plug-and-play approach, COT-FM consistently accelerates sampling and improves generation quality across 2D datasets, image generation benchmarks, and robotic manipulation tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13395</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 13:52:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning</title>
|
||||
<link>https://arxiv.org/abs/2603.10263</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10263.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanyi Sun, Shuran Song</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies. DICE-RL turns a pretrained behavior prior into a high-performing "pro" policy by amplifying high-success behaviors from online feedback. We pretrain a diffusion- or flow-based policy for broad behavioral coverage, then finetune it with a stable, sample-efficient residual off-policy RL framework that combines selective behavior regularization with value-guided action selection. Extensive experiments and analyses show that DICE-RL reliably improves performance with strong stability and sample efficiency. It enables mastery of complex long-horizon manipulation skills directly from high-dimensional pixel inputs, both in simulation and on a real robot. Project website: https://zhanyisun.github.io/dice.rl.2026/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.10263</guid>
|
||||
<pubDate>Tue, 10 Mar 2026 22:49:46 +0000</pubDate>
|
||||
<title>SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation</title>
|
||||
<link>https://arxiv.org/abs/2603.16924</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16924.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirbek Djanibekov, Luisa Bentivogli, Matteo Negri, Sara Papi</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Simultaneous speech-to-speech translation (SimulS2S) is essential for real-time multilingual communication, with increasing integration into meeting and streaming platforms. Despite this, SimulS2S remains underexplored in research, where current solutions often rely on resource-intensive training procedures and operate on short-form, pre-segmented utterances, failing to generalize to continuous speech. To bridge this gap, we propose SimulU, the first training-free policy for long-form SimulS2S. SimulU adopts history management and speech output selection strategies that exploit cross-attention in pre-trained end-to-end models to regulate both input history and output generation. Evaluations on MuST-C across 8 languages show that SimulU achieves a better or comparable quality-latency trade-off against strong cascaded models. By eliminating the need for ad-hoc training, SimulU offers a promising path to end-to-end SimulS2S in realistic, long-form scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16924</guid>
|
||||
<pubDate>Wed, 11 Mar 2026 22:07:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing</title>
|
||||
<link>https://arxiv.org/abs/2603.11535</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11535.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanchi Sun, Yixin Liu, Yonghui Wu, Lichao Sun</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Token-choice Mixture-of-Experts (TC-MoE) routes each token to a fixed number of experts, limiting dynamic computation allocation and requiring auxiliary losses to maintain load balance. We propose Expert Threshold (ET) routing, where each expert maintains an exponential moving average (EMA) threshold estimated from the global token distribution. At both training and inference, each token is independently routed to an expert if its score exceeds the expert's threshold, enabling dynamic computation allocation while achieving load balance without auxiliary losses. This fully causal mechanism eliminates dependence on other tokens in the batch, making it well-suited for autoregressive language modeling. In pretraining experiments scaling to 2.4B parameters on FineWeb-Edu, ET achieves 0.067 lower cross-entropy loss than TC-MoE, equivalent to reaching the same performance with 1.6times fewer tokens.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11535</guid>
|
||||
<pubDate>Thu, 12 Mar 2026 04:45:48 +0000</pubDate>
|
||||
<title>OSM-based Domain Adaptation for Remote Sensing VLMs</title>
|
||||
<link>https://arxiv.org/abs/2603.11804</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.11804.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi, Delyan Boychev, Luc Van Gool, Danda Pani Paudel</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling pipelines address this gap by distilling knowledge from large frontier models, but this dependence on large teachers is costly, limits scalability, and caps achievable performance at the ceiling of the teacher. We propose OSMDA: a self-contained domain adaptation framework that eliminates this dependency. Our key insight is that a capable base VLM can serve as its own annotation engine: by pairing aerial images with rendered OpenStreetMap (OSM) tiles, we leverage optical character recognition and chart comprehension capabilities of the model to generate captions enriched by OSM's vast auxiliary metadata. The model is then fine-tuned on the resulting corpus with satellite imagery alone, yielding OSMDA-VLM, a domain-adapted VLM that requires no manual labeling and no stronger external model. We conduct exhaustive evaluations spanning 10 benchmarks across image-text-to-text tasks and comparing against 9 competitive baselines. When equally mixed with real data, our method achieves state-of-the-art results, while being substantially cheaper to train than teacher-dependent alternatives. These results suggest that, given a strong foundation model, alignment with crowd-sourced geographic data is a practical and scalable path towards remote sensing domain adaptation. Dataset and model weights will be made publicly available.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.11804</guid>
|
||||
<pubDate>Thu, 12 Mar 2026 11:08:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass</title>
|
||||
<link>https://arxiv.org/abs/2603.12789</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangmin Kim, Minhyuk Hwang, Geonho Cha, Dongyoon Wee, Jaesik Park</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and extending them to multi-view settings requires additional overhead modules or preprocessed data. To this end, we present CHROMM, a unified framework that jointly estimates cameras, scene point clouds, and human meshes from multi-person multi-view videos without relying on external modules or preprocessing. We integrate strong geometric and human priors from Pi3X and Multi-HMR into a single trainable neural network architecture, and introduce a scale adjustment module to solve the scale discrepancy between humans and the scene. We also introduce a multi-view fusion strategy to aggregate per-view estimates into a single representation at test-time. Finally, we propose a geometry-based multi-person association method, which is more robust than appearance-based approaches. Experiments on EMDB, RICH, EgoHumans, and EgoExo4D show that CHROMM achieves competitive performance in global human motion and multi-view pose estimation while running over 8x faster than prior optimization-based multi-view approaches. Project page: https://nstar1125.github.io/chromm.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.12789</guid>
|
||||
<pubDate>Fri, 13 Mar 2026 08:48:19 +0000</pubDate>
|
||||
<title>Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation</title>
|
||||
<link>https://arxiv.org/abs/2603.13045</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13045.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifeng Liu, Siqi Ouyang, Yatish Hosmane Revanasiddappa, Lei Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training methods rely heavily on high-quality parallel data, which are often scarce or unavailable for low-resource languages. In this paper, we introduce WALAR, a reinforcement training method using only monolingual text to elevate LLMs' translation capabilities on massive low-resource languages while retaining their performance on high-resource languages. Our key insight is based on the observation of failure modes (or "holes") in existing source-based multilingual quality estimation (QE) models. Reinforcement learning (RL) using these QE models tends to amplify such holes, resulting in poorer multilingual LLMs. We develop techniques including word alignment and language alignment to mitigate such holes in WALAR's reward for RL training. We continually trained an LLM supporting translation of 101 languages using WALAR. The experiments show that our new model outperforms LLaMAX, one of the strongest open-source multilingual LLMs by a large margin on 1400 language directions on Flores-101 dataset.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13045</guid>
|
||||
<pubDate>Fri, 13 Mar 2026 14:52:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.13033</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanpeng Zhao, Wentao Ding, Hongtao Li, Baoxiong Jia, Zilong Zheng</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> A recent trend in vision-language models (VLMs) has been to enhance their spatial cognition for embodied domains. Despite progress, existing evaluations have been limited both in paradigm and in coverage, hindering rapid, iterative model development. To address these limitations, we propose ESPIRE, a diagnostic benchmark for embodied spatial reasoning. ESPIRE offers a simulated world that physically grounds VLMs and evaluates them on spatial-reasoning-centric robotic tasks, thus narrowing the gap between evaluation and real-world deployment. To adapt VLMs to robotic tasks, we decompose each task into localization and execution, and frame both as generative problems, in stark contrast to predominant discriminative evaluations (e.g., via visual-question answering) that rely on distractors and discard execution. This decomposition further enables a fine-grained analysis beyond passive spatial reasoning toward reasoning to act. We systematically design ESPIRE both at the instruction level and at the environment level, ensuring broad coverage of spatial reasoning scenarios. We use ESPIRE to diagnose a range of frontier VLMs and provide in-depth analysis of their spatial reasoning behaviors.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13033</guid>
|
||||
<pubDate>Fri, 13 Mar 2026 14:43:00 +0000</pubDate>
|
||||
<title>MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2603.16929</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongjun Wang, Wei Liu, Weibo Gu, Xing Sun, Kai Han</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable boundaries and vanishing gradient regions, failing to maintain gradient fidelity. Furthermore, these methods lack a hazard-aware mechanism to adaptively suppress extreme deviations, leaving the optimization process vulnerable to abrupt policy shifts. To address these challenges, we propose Modulated Hazard-aware Policy Optimization (MHPO), a novel framework designed for robust and stable reinforcement learning. The proposed MHPO introduces a Log-Fidelity Modulator (LFM) to map unbounded importance ratios into a bounded, differentiable domain. This mechanism effectively prevents high-variance outlier tokens from destabilizing the loss landscape while ensuring global gradient stability. Complementarily, a Decoupled Hazard Penalty (DHP) integrates cumulative hazard functions from survival analysis to independently regulate positive and negative policy shifts. By shaping the optimization landscape with hazard-aware penalties, the proposed MHPO achieves fine-grained regulation of asymmetric policy shifts simultaneously mitigating mode collapse from over-expansion and preventing policy erosion from catastrophic contraction within a stabilized trust region. Extensive evaluations on diverse reasoning benchmarks across both text-based and vision-language tasks demonstrate that MHPO consistently outperforms existing methods, achieving superior performance while significantly enhancing training stability.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16929</guid>
|
||||
<pubDate>Sat, 14 Mar 2026 00:45:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning</title>
|
||||
<link>https://arxiv.org/abs/2603.14482</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14482.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.14482</guid>
|
||||
<pubDate>Sun, 15 Mar 2026 17:02:40 +0000</pubDate>
|
||||
<title>VID-AD: A Dataset for Image-Level Logical Anomaly Detection under Vision-Induced Distraction</title>
|
||||
<link>https://arxiv.org/abs/2603.13964</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13964.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hiroto Nakata, Yawen Zou, Shunsuke Sakai, Shun Maeda, Chunzhi Gu, Yijin Wei, Shangce Gao, Chao Zhang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Logical anomaly detection in industrial inspection remains challenging due to variations in visual appearance (e.g., background clutter, illumination shift, and blur), which often distract vision-centric detectors from identifying rule-level violations. However, existing benchmarks rarely provide controlled settings where logical states are fixed while such nuisance factors vary. To address this gap, we introduce VID-AD, a dataset for logical anomaly detection under vision-induced distraction. It comprises 10 manufacturing scenarios and five capture conditions, totaling 50 one-class tasks and 10,395 images. Each scenario is defined by two logical constraints selected from quantity, length, type, placement, and relation, with anomalies including both single-constraint and combined violations. We further propose a language-based anomaly detection framework that relies solely on text descriptions generated from normal images. Using contrastive learning with positive texts and contradiction-based negative texts synthesized from these descriptions, our method learns embeddings that capture logical attributes rather than low-level features. Extensive experiments demonstrate consistent improvements over baselines across the evaluated settings. The dataset is available at: https://github.com/nkthiroto/VID-AD.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.13964</guid>
|
||||
<pubDate>Sat, 14 Mar 2026 14:21:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Video-CoE: Reinforcing Video Event Prediction via Chain of Events</title>
|
||||
<link>https://arxiv.org/abs/2603.14935</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14935.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qile Su, Jing Tang, Rui Chen, Lei Sun, Xiangxiang Chu</p><p><b>Upvotes:</b> 82</p><p><b>Summary:</b> Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained temporal modeling of videos and establish logical relationships between videos and future events, which current MLLMs still struggle with. In this work, we first present a comprehensive evaluation of current leading MLLMs on the VEP task, revealing the reasons behind their inaccurate predictions, including lack of logical reasoning ability for future events prediction and insufficient utilization of visual information. To address these challenges, we propose Chain of Events (CoE) paradigm, which constructs temporal event chains to implicitly enforce MLLM focusing on the visual content and the logical connections between videos and future events, incentivizing model's reasoning capability with multiple training protocols. Experimental results on public benchmarks demonstrate that our method outperforms both leading open-source and commercial MLLMs, establishing a new state-of-the-art on the VEP task. Codes and models will be released soon.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.14935</guid>
|
||||
<pubDate>Mon, 16 Mar 2026 07:38:15 +0000</pubDate>
|
||||
<title>PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark</title>
|
||||
<link>https://arxiv.org/abs/2603.14456</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14456.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Javad Ranjbar Kalahroodi, Mohammad Amini, Parmis Bathayan, Heshaam Faili, Azadeh Shakery</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Persian poses unique audio understanding challenges through its classical poetry, traditional music, and pervasive code-switching - none captured by existing benchmarks. We introduce PARSA-Bench (Persian Audio Reasoning and Speech Assessment Benchmark), the first benchmark for evaluating large audio-language models on Persian language and culture, comprising 16 tasks and over 8,000 samples across speech understanding, paralinguistic analysis, and cultural audio understanding. Ten tasks are newly introduced, including poetry meter and style detection, traditional Persian music understanding, and code-switching detection. Text-only baselines consistently outperform audio counterparts, suggesting models may not leverage audio-specific information beyond what transcription alone provides. Culturally-grounded tasks expose a qualitatively distinct failure mode: all models perform near random chance on vazn detection regardless of scale, suggesting prosodic perception remains beyond the reach of current models. The dataset is publicly available at https://huggingface.co/datasets/MohammadJRanjbar/PARSA-Bench</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.14456</guid>
|
||||
<pubDate>Sun, 15 Mar 2026 16:06:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models</title>
|
||||
<link>https://arxiv.org/abs/2603.15618</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulin Luo, Hao Chen, Zhuangzhe Wu, Bowen Sui, Jiaming Liu, Chenyang Gu, Zhuoyang Liu, Qiuxuan Feng, Jiale Yu, Shuo Gu, Peng Jia, Pheng-Ann Heng, Shanghang Zhang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose DeepVision-VLA, built on a Vision-Language Mixture-of-Transformers (VL-MoT) framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce Action-Guided Visual Pruning (AGVP), which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0\% and 7.5\% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.15618</guid>
|
||||
<pubDate>Mon, 16 Mar 2026 17:59:54 +0000</pubDate>
|
||||
<title>VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining</title>
|
||||
<link>https://arxiv.org/abs/2603.15030</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15030.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanyu Zhu, Yuhao Dong, Rundong Wang, Yang Shi, Zhipeng Wu, Yinlun Peng, YiFan Zhang, Yihang Lou, Yuanxing Zhang, Ziwei Liu, Yan Bai, Yuan Zhou</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advancements extend Multimodal Large Language Models (MLLMs) beyond standard visual question answering to utilizing external tools for advanced visual tasks. Despite this progress, precisely executing and effectively composing diverse tools for complex tasks remain persistent bottleneck. Constrained by sparse tool-sets and simple tool-use trajectories, existing benchmarks fail to capture complex and diverse tool interactions, falling short in evaluating model performance under practical, real-world conditions. To bridge this gap, we introduce VisualToolChain-Bench(VTC-Bench), a comprehensive benchmark designed to evaluate tool-use proficiency in MLLMs. To align with realistic computer vision pipelines, our framework features 32 diverse OpenCV-based visual operations. This rich tool-set enables extensive combinations, allowing VTC-Bench to rigorously assess multi-tool composition and long-horizon, multi-step plan execution. For precise evaluation, we provide 680 curated problems structured across a nine-category cognitive hierarchy, each with ground-truth execution trajectories. Extensive experiments on 19 leading MLLMs reveal critical limitations in current models' visual agentic capabilities. Specifically, models struggle to adapt to diverse tool-sets and generalize to unseen operations, with the leading model Gemini-3.0-Pro only achieving 51% on our benchmark. Furthermore, multi-tool composition remains a persistent challenge. When facing complex tasks, models struggle to formulate efficient execution plans, relying heavily on a narrow, suboptimal subset of familiar functions rather than selecting the optimal tools. By identifying these fundamental challenges, VTC-Bench establishes a rigorous baseline to guide the development of more generalized visual agentic models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.15030</guid>
|
||||
<pubDate>Mon, 16 Mar 2026 09:31:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents</title>
|
||||
<link>https://arxiv.org/abs/2603.16496</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16496.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16496</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 13:22:54 +0000</pubDate>
|
||||
<title>ReactMotion: Generating Reactive Listener Motions from Speaker Utterance</title>
|
||||
<link>https://arxiv.org/abs/2603.15083</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15083.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Luo, Bizhu Wu, Bing Li, Jianfeng Ren, Ruibin Bai, Rong Qu, Linlin Shen, Bernard Ghanem</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> In this paper, we introduce a new task, Reactive Listener Motion Generation from Speaker Utterance, which aims to generate naturalistic listener body motions that appropriately respond to a speaker's utterance. However, modeling such nonverbal listener behaviors remains underexplored and challenging due to the inherently non-deterministic nature of human reactions. To facilitate this task, we present ReactMotionNet, a large-scale dataset that pairs speaker utterances with multiple candidate listener motions annotated with varying degrees of appropriateness. This dataset design explicitly captures the one-to-many nature of listener behavior and provides supervision beyond a single ground-truth motion. Building on this dataset design, we develop preference-oriented evaluation protocols tailored to evaluate reactive appropriateness, where conventional motion metrics focusing on input-motion alignment ignore. We further propose ReactMotion, a unified generative framework that jointly models text, audio, emotion, and motion, and is trained with preference-based objectives to encourage both appropriate and diverse listener responses. Extensive experiments show that ReactMotion outperforms retrieval baselines and cascaded LLM-based pipelines, generating more natural, diverse, and appropriate listener motions.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.15083</guid>
|
||||
<pubDate>Mon, 16 Mar 2026 10:37:42 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting</title>
|
||||
<link>https://arxiv.org/abs/2603.16542</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16542.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanpeng Zhang, Hao Luo, Sipeng Zheng, Yicheng Feng, Haiweng Xu, Ziheng Xi, Chaoyi Xu, Haoqi Yuan, Zongqing Lu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying quality, so many trajectories reflect recovery behavior, inconsistent operator skill, or weakly informative supervision. Uniform post-training gives equal credit to all samples and can therefore average over conflicting or low-attribution data. We propose Posterior-Transition Reweighting (PTR), a reward-free and conservative post-training method that decides how much each training sample should influence the supervised update. For each sample, PTR encodes the observed post-action consequence as a latent target, inserts it into a candidate pool of mismatched targets, and uses a separate transition scorer to estimate a softmax identification posterior over target indices. The posterior-to-uniform ratio defines the PTR score, which is converted into a clipped-and-mixed weight and applied to the original action objective through self-normalized weighted regression. This construction requires no tractable policy likelihood and is compatible with both diffusion and flow-matching action heads. Rather than uniformly trusting all recorded supervision, PTR reallocates credit according to how attributable each sample's post-action consequence is under the current representation, improving conservative offline adaptation to heterogeneous robot data.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16542</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 14:05:35 +0000</pubDate>
|
||||
<title>MOSS-TTS Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2603.18090</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18090.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yitian Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuangwei Chen, Yaozhou Jiang, Cheng Chang, Dong Hong, Mingshu Chen, Ruixiao Li, Yiyang Zhang, Yang Gao, Hanfu Chen, Ke Chen, Songlin Wang, Xiaogui Yang, Yuqian Zhang, Kexin Huang, ZhengYuan Lin, Kang Yu, Ziqi Chen, Jin Wang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18090</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 09:08:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs</title>
|
||||
<link>https://arxiv.org/abs/2603.16557</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangyeon Yoon, Sunkyoung Kim, Hyesoo Hong, Wonje Jeung, Yongil Kim, Wooseok Seo, Heuiyeen Yeen, Albert No</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS, which evaluates whether memory-based user preferences are appropriately applied or suppressed across communication contexts. Using two complementary metrics, Misapplication Rate (MR) and Appropriate Application Rate (AAR), we find even frontier LLMs struggle to apply preferences in a context-sensitive manner. Models with stronger preference adherence exhibit higher rates of over-application, and neither reasoning capability nor prompt-based defenses fully resolve this issue. These results suggest current LLMs treat personalized preferences as globally enforceable rules rather than as context-dependent normative signals.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16557</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 14:19:05 +0000</pubDate>
|
||||
<title>Prompt-Free Universal Region Proposal Network</title>
|
||||
<link>https://arxiv.org/abs/2603.17554</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17554.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qihong Tang, Changhan Liu, Shaofeng Zhang, Wenbin Li, Qi Fan, Yang Gao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Identifying potential objects is critical for object recognition and analysis across various computer vision applications. Existing methods typically localize potential objects by relying on exemplar images, predefined categories, or textual descriptions. However, their reliance on image and text prompts often limits flexibility, restricting adaptability in real-world scenarios. In this paper, we introduce a novel Prompt-Free Universal Region Proposal Network (PF-RPN), which identifies potential objects without relying on external prompts. First, the Sparse Image-Aware Adapter (SIA) module performs initial localization of potential objects using a learnable query embedding dynamically updated with visual features. Next, the Cascade Self-Prompt (CSP) module identifies the remaining potential objects by leveraging the self-prompted learnable embedding, autonomously aggregating informative visual features in a cascading manner. Finally, the Centerness-Guided Query Selection (CG-QS) module facilitates the selection of high-quality query embeddings using a centerness scoring network. Our method can be optimized with limited data (e.g., 5% of MS COCO data) and applied directly to various object detection application domains for identifying potential objects without fine-tuning, such as underwater object detection, industrial defect detection, and remote sensing image object detection. Experimental results across 19 datasets validate the effectiveness of our method. Code is available at https://github.com/tangqh03/PF-RPN.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17554</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 10:02:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>When AI Navigates the Fog of War</title>
|
||||
<link>https://arxiv.org/abs/2603.16642</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Li, Xirui Li, Tianyi Zhou</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Can AI reason about a war before its trajectory becomes historically obvious? Analyzing this capability is difficult because retrospective geopolitical prediction is heavily confounded by training-data leakage. We address this challenge through a temporally grounded case study of the early stages of the 2026 Middle East conflict, which unfolded after the training cutoff of current frontier models. We construct 11 critical temporal nodes, 42 node-specific verifiable questions, and 5 general exploratory questions, requiring models to reason only from information that would have been publicly available at each moment. This design substantially mitigates training-data leakage concerns, creating a setting well-suited for studying how models analyze an unfolding crisis under the fog of war, and provides, to our knowledge, the first temporally grounded analysis of LLM reasoning in an ongoing geopolitical conflict. Our analysis reveals three main findings. First, current state-of-the-art large language models often display a striking degree of strategic realism, reasoning beyond surface rhetoric toward deeper structural incentives. Second, this capability is uneven across domains: models are more reliable in economically and logistically structured settings than in politically ambiguous multi-actor environments. Finally, model narratives evolve over time, shifting from early expectations of rapid containment toward more systemic accounts of regional entrenchment and attritional de-escalation. Since the conflict remains ongoing at the time of writing, this work can serve as an archival snapshot of model reasoning during an unfolding geopolitical crisis, enabling future studies without the hindsight bias of retrospective analysis.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16642</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 15:13:10 +0000</pubDate>
|
||||
<title>Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.18002</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kevin Qu, Haozhe Qi, Mihai Dusmanu, Mahdi Rad, Rui Wang, Marc Pollefeys</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input representations with geometric cues rather than explicitly teaching models to reason in 3D space. We introduce Loc3R-VLM, a framework that equips 2D Vision-Language Models with advanced 3D understanding capabilities from monocular video input. Inspired by human spatial cognition, Loc3R-VLM relies on two joint objectives: global layout reconstruction to build a holistic representation of the scene structure, and explicit situation modeling to anchor egocentric perspective. These objectives provide direct spatial supervision that grounds both perception and language in a 3D context. To ensure geometric consistency and metric-scale alignment, we leverage lightweight camera pose priors extracted from a pre-trained 3D foundation model. Loc3R-VLM achieves state-of-the-art performance in language-based localization and outperforms existing 2D- and video-based approaches on situated and general 3D question-answering benchmarks, demonstrating that our spatial supervision framework enables strong 3D understanding. Project page: https://kevinqu7.github.io/loc3r-vlm</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18002</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:59:10 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.16653</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Md Jahidul Islam</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue that this homogeneity ignores the distinct structural nature of the modalities -- spatial locality in images versus semantic density in text. To address this, we propose HeBA (Heterogeneous Bottleneck Adapter), a unified architectural framework that introduces modality-specific structural inductive biases. HeBA departs from conventional designs through three key architectural innovations: (1) Heterogeneity: It processes visual tokens via 2D depthwise-separable convolutions to preserve spatial correlations, while distinctively processing text tokens via dense linear projections to capture semantic relationships; (2) Bottleneck Regularization: Unlike standard expanding adapters, HeBA employs a compression bottleneck (D -> D/4) that explicitly forces the model to learn compact, robust features and acts as a structural regularizer; and (3) Active Gradient Initialization: We challenge the restrictive zero-initialization paradigm, utilizing a Kaiming initialization strategy that ensures sufficient initial gradient flow to accelerate convergence without compromising the frozen backbone's pre-trained knowledge. Extensive experiments demonstrate that HeBA's architecturally specialized design achieves superior stability and accuracy, establishing a new state-of-the-art on 11 few-shot benchmarks. Code is available at https://github.com/Jahid12012021/VLM-HeBA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.16653</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 15:23:04 +0000</pubDate>
|
||||
<title>AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents</title>
|
||||
<link>https://arxiv.org/abs/2603.18429</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18429.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibo Shi, Jungang Li, Linghao Zhang, Zihao Dongfang, Biao Wu, Sicheng Tao, Yibo Yan, Chenxi Qin, Weiting Liu, Zhixin Lin, Hanqian Li, Yu Huang, Song Dai, Yonghua Hei, Yue Ding, Xiang Li, Shikang Wang, Chengdong Xu, Jingqi Liu, Xueying Ma, Zhiwen Zheng, Xiaofei Zhang, Bincheng Wang, Nichen Yang, Jie Wu, Lihua Tian, Chen Li, Xuming Hu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18429</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 02:45:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PRISM: Demystifying Retention and Interaction in Mid-Training</title>
|
||||
<link>https://arxiv.org/abs/2603.17074</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17074.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bharat Runwal, Ashish Agrawal, Anurag Roy, Rameswar Panda</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and attention-Mamba hybrid), and scales from 3B to 24B parameters, we show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance. The full PRISM to RL pipeline improves macro-average across six reasoning benchmarks from under 12 to 29-42 (a 3-4x improvement), whereas RL applied directly to most of the base models remains substantially less effective, with AIME scores near zero. Data composition matters most at mid-training, not RL: including science data during mid-training unlocks +17 to +28 point GPQA-Diamond gains during RL, while changing the RL mix produces less than 2 point differences. Mechanistically, mid-training densely restructures over 90% of model weights, while RL makes sparse, front-loaded refinements to approximately 5% of parameters. Representation analysis (CKA) confirms that RL consistently preserves mid-training's representational geometry (over 0.998 CKA) across architectures. Crucially, RL applies identical weight changes regardless of starting point, yet only succeeds on mid-trained models, consistent with mid-training placing the model in a configuration from which RL can effectively improve performance. Our results demonstrate that retention-aware mid-training is highly effective for reliable reasoning enhancement and provide practical guidance for designing robust mid-training pipelines.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17074</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 19:04:33 +0000</pubDate>
|
||||
<title>Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding</title>
|
||||
<link>https://arxiv.org/abs/2603.18472</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18472.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinghui Li, Jiayi Kuang, Peng Xing, Daixian Liu, Junnan Dong, Shu-Yu Guo, Yangning Li, Qingyu Zhou, Wenhao Jiang, Hai-Tao Zheng, Ying Shen, Liang Lin, Philip S. Yu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> While Multimodal Large Language Models (MLLMs) have achieved remarkable success in interpreting natural scenes, their ability to process discrete symbols -- the fundamental building blocks of human cognition -- remains a critical open question. Unlike continuous visual data, symbols such as mathematical formulas, chemical structures, and linguistic characters require precise, deeper interpretation. This paper introduces a comprehensive benchmark to evaluate how top-tier MLLMs navigate these "discrete semantic spaces" across five domains: language, culture, mathematics, physics, and chemistry. Our investigation uncovers a counterintuitive phenomenon: models often fail at basic symbol recognition yet succeed in complex reasoning tasks, suggesting they rely on linguistic probability rather than true visual perception. By exposing this "cognitive mismatch", we highlight a significant gap in current AI capabilities: the struggle to truly perceive and understand the symbolic languages that underpin scientific discovery and abstract thought. This work offers a roadmap for developing more rigorous, human-aligned intelligent systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18472</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 04:08:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.17079</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> M. Arda Aydın, Melih B. Yilmaz, Aykut Koç, Tolga Çukur</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The success of CLIP-like vision-language models (VLMs) on natural images has inspired medical counterparts, yet existing approaches largely fall into two extremes: specialist models trained on single-domain data, which capture domain-specific details but generalize poorly, and generalist medical VLMs trained on multi-domain data, which retain broad semantics but dilute fine-grained diagnostic cues. Bridging this specialization-generalization trade-off remains challenging. To address this problem, we propose ACE-LoRA, a parameter-efficient adaptation framework for generalist medical VLMs that maintains robust zero-shot generalization. ACE-LoRA integrates Low-Rank Adaptation (LoRA) modules into frozen image-text encoders and introduces an Attention-based Context Enhancement Hypergraph Neural Network (ACE-HGNN) module that captures higher-order contextual interactions beyond pairwise similarity to enrich global representations with localized diagnostic cues, addressing a key limitation of prior Parameter-Efficient Fine-Tuning (PEFT) methods that overlook fine-grained details. To further enhance cross-modal alignment, we formulate a label-guided InfoNCE loss to effectively suppress false negatives between semantically related image-text pairs. Despite adding only 0.95M trainable parameters, ACE-LoRA consistently outperforms state-of-the-art medical VLMs and PEFT baselines across zero-shot classification, segmentation, and detection benchmarks spanning multiple domains. Our code is available at https://github.com/icon-lab/ACE-LoRA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17079</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 19:06:33 +0000</pubDate>
|
||||
<title>3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model</title>
|
||||
<link>https://arxiv.org/abs/2603.18524</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18524.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun-kyu Ko, Jihyeon Park, Younghyun Kim, Dongheok Park, Eunbyung Park</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Creating dynamic, view-consistent videos of customized subjects is highly sought after for a wide range of emerging applications, including immersive VR/AR, virtual production, and next-generation e-commerce. However, despite rapid progress in subject-driven video generation, existing methods predominantly treat subjects as 2D entities, focusing on transferring identity through single-view visual features or textual prompts. Because real-world subjects are inherently 3D, applying these 2D-centric approaches to 3D object customization reveals a fundamental limitation: they lack the comprehensive spatial priors necessary to reconstruct the 3D geometry. Consequently, when synthesizing novel views, they must rely on generating plausible but arbitrary details for unseen regions, rather than preserving the true 3D identity. Achieving genuine 3D-aware customization remains challenging due to the scarcity of multi-view video datasets. While one might attempt to fine-tune models on limited video sequences, this often leads to temporal overfitting. To resolve these issues, we introduce a novel framework for 3D-aware video customization, comprising 3DreamBooth and 3Dapter. 3DreamBooth decouples spatial geometry from temporal motion through a 1-frame optimization paradigm. By restricting updates to spatial representations, it effectively bakes a robust 3D prior into the model without the need for exhaustive video-based training. To enhance fine-grained textures and accelerate convergence, we incorporate 3Dapter, a visual conditioning module. Following single-view pre-training, 3Dapter undergoes multi-view joint optimization with the main generation branch via an asymmetrical conditioning strategy. This design allows the module to act as a dynamic selective router, querying view-specific geometric hints from a minimal reference set. Project page: https://ko-lani.github.io/3DreamBooth/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18524</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 06:14:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MosaicMem: Hybrid Spatial Memory for Controllable Video World Models</title>
|
||||
<link>https://arxiv.org/abs/2603.17117</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Yu, Runjia Qian, Yumeng Li, Liquan Wang, Songheng Yin, Sri Siddarth Chakaravarthy P, Dennis Anthony, Yang Ye, Yidi Li, Weiwei Wan, Animesh Garg</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses. We propose Mosaic Memory (MosaicMem), a hybrid spatial memory that lifts patches into 3D for reliable localization and targeted retrieval, while exploiting the model's native conditioning to preserve prompt-following generation. MosaicMem composes spatially aligned patches in the queried view via a patch-and-compose interface, preserving what should persist while allowing the model to inpaint what should evolve. With PRoPE camera conditioning and two new memory alignment methods, experiments show improved pose adherence compared to implicit memory and stronger dynamic modeling than explicit baselines. MosaicMem further enables minute-level navigation, memory-based scene editing, and autoregressive rollout.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17117</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 20:19:44 +0000</pubDate>
|
||||
<title>Memento-Skills: Let Agents Design Agents</title>
|
||||
<link>https://arxiv.org/abs/2603.18743</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao, Zhixun Chen, Menglong Zhang, Yihang Chen, Jinsong Li, Runyu Yang, Qiangbin Liu, Xinlei Yu, Jianmin Zhou, Na Wang, Chunyang Sun, Jun Wang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> We introduce Memento-Skills, a generalist, continually-learnable LLM agent system that functions as an agent-designing agent: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with stateful prompts, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions. Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the Read--Write Reflective Learning mechanism introduced in Memento~2~wang2025memento2. In the read phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the write phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables continual learning without updating LLM parameters, as all adaptation is realised through the evolution of externalised skills and prompts. Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to design agents end-to-end for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18743</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 10:45:22 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild</title>
|
||||
<link>https://arxiv.org/abs/2603.17187</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17187.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17187</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 22:30:30 +0000</pubDate>
|
||||
<title>ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents</title>
|
||||
<link>https://arxiv.org/abs/2603.18815</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han, Jian Hu, Zhenghui Jin, Yuchi Zhang, Shizhe Diao, Ximing Lu, Binfeng Xu, Zhiding Yu, Jan Kautz, Yi Dong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and maintain. Under the rollout-as-a-service philosophy, we present ProRL Agent , a scalable infrastructure that serves the full agentic rollout lifecycle through an API service. ProRL Agent also provides standardized and extensible sandbox environments that support diverse agentic tasks in rootless HPC settings. We validate ProRL Agent through RL training on software engineering, math, STEM, and coding tasks. ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18815</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 12:08:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AI Scientist via Synthetic Task Scaling</title>
|
||||
<link>https://arxiv.org/abs/2603.17216</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Cai, Harkirat Behl</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and current LLMs often generate plausible-looking but ineffective ideas. To make progress on training agents that can learn from doing, we provide a novel synthetic environment generation pipeline targeting machine learning agents. Our pipeline automatically synthesizes machine learning challenges compatible with the SWE-agent framework, covering topic sampling, dataset proposal, and code generation. The resulting synthetic tasks are 1) grounded in real machine learning datasets, because the proposed datasets are verified against the Huggingface API and are 2) verified for higher quality with a self-debugging loop. To validate the effectiveness of our synthetic tasks, we tackle MLGym, a benchmark for machine learning tasks. From the synthetic tasks, we sample trajectories from a teacher model (GPT-5), then use the trajectories to train a student model (Qwen3-4B and Qwen3-8B). The student models trained with our synthetic tasks achieve improved performance on MLGym, raising the AUP metric by 9% for Qwen3-4B and 12% for Qwen3-8B.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17216</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 23:43:16 +0000</pubDate>
|
||||
<title>Reasoning over mathematical objects: on-policy reward modeling and test time aggregation</title>
|
||||
<link>https://arxiv.org/abs/2603.18886</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18886.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, Ilia Kulikov, Jack Lanchantin, Xian Li, Tianjian Li, Bo Liu, Graham Neubig, Anaelia Ovalle, Swarnadeep Saha, Sainbayar Sukhbaatar, Sean Welleck, Jason Weston, Chenxi Whitehouse, Adina Williams, Jing Xu, Ping Yu, Weizhe Yuan, Jingyu Zhang, Wenting Zhao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formally structured expressions. Yet, current LM evaluations of mathematical and scientific reasoning rely heavily on simplified answer formats such as numerical values or multiple choice options due to the convenience of automated assessment. In this paper we provide three contributions for improving reasoning over mathematical objects: (i) we build and release training data and benchmarks for deriving mathematical objects, the Principia suite; (ii) we provide training recipes with strong LLM-judges and verifiers, where we show that on-policy judge training boosts performance; (iii) we show how on-policy training can also be used to scale test-time compute via aggregation. We find that strong LMs such as Qwen3-235B and o3 struggle on Principia, while our training recipes can bring significant improvements over different LLM backbones, while simultaneously improving results on existing numerical and MCQA tasks, demonstrating cross-format generalization of reasoning abilities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18886</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 13:27:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Alignment Makes Language Models Normative, Not Descriptive</title>
|
||||
<link>https://arxiv.org/abs/2603.17218</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17218.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eilam Shapira, Moshe Tennenholtz, Roi Reichart</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions in multi-round strategic games - bargaining, persuasion, negotiation, and repeated matrix games. In these settings, base models outperform their aligned counterparts in predicting human choices by nearly 10:1, robustly across model families, prompt formulations, and game configurations. This pattern reverses, however, in settings where human behavior is more likely to follow normative predictions: aligned models dominate on one-shot textbook games across all 12 types tested and on non-strategic lottery choices - and even within the multi-round games themselves, at round one, before interaction history develops. This boundary-condition pattern suggests that alignment induces a normative bias: it improves prediction when human behavior is relatively well captured by normative solutions, but hurts prediction in multi-round strategic settings, where behavior is shaped by descriptive dynamics such as reciprocity, retaliation, and history-dependent adaptation. These results reveal a fundamental trade-off between optimizing models for human use and using them as proxies for human behavior.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17218</guid>
|
||||
<pubDate>Tue, 17 Mar 2026 23:47:08 +0000</pubDate>
|
||||
<title>What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?</title>
|
||||
<link>https://arxiv.org/abs/2603.19017</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19017.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard, Wei Zhao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, German, Chinese, Arabic, and Hausa) and multiple calendar conventions (Gregorian, Hijri, and Chinese Lunar). MultiTempBench contains 15,000 examples built by translating 750 curated English questions and expanding each into controlled date-format variants. We evaluate 20 LLMs and introduce the multilingual Date Fragmentation Ratio (mDFR), calibrated with human severity ratings, together with geometric-probing analyses of internal temporal representations. We find tokenisation quality of temporal artefacts is a resource-dependent bottleneck: in low-resource languages and rarer calendar formats, fragmentation disrupts Year/Month/Day separation and accuracy collapses, while high-resource settings are often robust to digit-level splitting. Beyond tokenisation, crossed mixed-effects regression shows that temporal linearity is the strongest predictor of temporal reasoning in high-resource languages, whereas fragmentation is the stronger predictor in low-resource languages. Code is available at: https://github.com/gagan3012/mtb</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19017</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 15:22:03 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GigaWorld-Policy: An Efficient Action-Centered World--Action Model</title>
|
||||
<link>https://arxiv.org/abs/2603.17240</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Hao Li, Hengtao Li, Jie Li, Jindi Lv, Jingyu Liu, Min Cao, Peng Li, Qiuping Deng, Wenjun Mei, Xiaofeng Wang, Xinze Chen, Xinyu Zhou, Yang Wang, Yifan Chang, Yifan Li, Yukun Zhou, Yun Ye, Zhichao Liu, Zheng Zhu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17240</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 00:52:02 +0000</pubDate>
|
||||
<title>FASTER: Rethinking Real-Time Flow VLAs</title>
|
||||
<link>https://arxiv.org/abs/2603.19199</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19199.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Lu, Zhe Liu, Xianzhe Fan, Zhenya Yang, Jinghua Hou, Junyi Li, Kaixin Ding, Hengshuang Zhao</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference methods primarily optimize trajectory smoothness, but neglect the critical latency in reacting to environmental changes. By rethinking the notion of reaction in action chunking policies, this paper presents a systematic analysis of the factors governing reaction time. We show that reaction time follows a uniform distribution determined jointly by the Time to First Action (TTFA) and the execution horizon. Moreover, we reveal that the standard practice of applying a constant schedule in flow-based VLAs can be inefficient and forces the system to complete all sampling steps before any movement can start, forming the bottleneck in reaction latency. To overcome this issue, we propose Fast Action Sampling for ImmediaTE Reaction (FASTER). By introducing a Horizon-Aware Schedule, FASTER adaptively prioritizes near-term actions during flow sampling, compressing the denoising of the immediate reaction by tenfold (e.g., in π_{0.5} and X-VLA) into a single step, while preserving the quality of long-horizon trajectory. Coupled with a streaming client-server pipeline, FASTER substantially reduces the effective reaction latency on real robots, especially when deployed on consumer-grade GPUs. Real-world experiments, including a highly dynamic table tennis task, prove that FASTER unlocks unprecedented real-time responsiveness for generalist policies, enabling rapid generation of accurate and smooth trajectories.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19199</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:51:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Stereo World Model: Camera-Guided Stereo Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2603.17375</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Tian Sun, Zehuan Huang, Yifan Niu, Lin Ma, Yan-Pei Cao, Yuewen Ma, Xiaojuan Qi</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity. To efficiently achieve consistent stereo generation, our approach introduces two key designs: (1) a unified camera-frame RoPE that augments latent tokens with camera-aware rotary positional encoding, enabling relative, view- and time-consistent conditioning while preserving pretrained video priors via a stable attention initialization; and (2) a stereo-aware attention decomposition that factors full 4D attention into 3D intra-view attention plus horizontal row attention, leveraging the epipolar prior to capture disparity-aligned correspondences with substantially lower compute. Across benchmarks, StereoWorld improves stereo consistency, disparity accuracy, and camera-motion fidelity over strong monocular-then-convert pipelines, achieving more than 3x faster generation with an additional 5% gain in viewpoint consistency. Beyond benchmarks, StereoWorld enables end-to-end binocular VR rendering without depth estimation or inpainting, enhances embodied policy learning through metric-scale depth grounding, and is compatible with long-video distillation for extended interactive stereo synthesis.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17375</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 05:42:22 +0000</pubDate>
|
||||
<title>Tinted Frames: Question Framing Blinds Vision-Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.19203</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher, Leonid Sigal, Ritwik Gupta</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of attention applied to visual inputs based on linguistic framing even when alternative framings demand identical visual reasoning. Using visual attention as a probe, we quantify how framing alters both the amount and distribution of attention over the image. Constrained framings, such as multiple choice and yes/no, induce substantially lower attention to image context compared to open-ended, reduce focus on task-relevant regions, and shift attention towards uninformative tokens. We further demonstrate that this attention misallocation is the principal cause of degraded accuracy and cross-framing inconsistency. Building on this mechanistic insight, we introduce a lightweight prompt-tuning method using learnable tokens that encourages the robust, visually grounded attention patterns observed in open-ended settings, improving visual grounding and improving performance across framings.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19203</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:53:09 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Efficient Exploration at Scale</title>
|
||||
<link>https://arxiv.org/abs/2603.17378</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17378.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla, Xiuyuan Lu, Mehdi Jafarnia, Victor Minden, Zheng Wen, Benjamin Van Roy</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The reward model is fit to the choice data, while the language model is updated by a variation of reinforce, with reinforcement signals provided by the reward model. Several features enable the efficiency gains: a small affirmative nudge added to each reinforcement signal, an epistemic neural network that models reward uncertainty, and information-directed exploration. With Gemma large language models (LLMs), our algorithm matches the performance of offline RLHF trained on 200K labels using fewer than 20K labels, representing more than a 10x gain in data efficiency. Extrapolating from our results, we expect our algorithm trained on 1M labels to match offline RLHF trained on 1B labels. This represents a 1,000x gain. To our knowledge, these are the first results to demonstrate that such large improvements are possible.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17378</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 05:47:59 +0000</pubDate>
|
||||
<title>DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising</title>
|
||||
<link>https://arxiv.org/abs/2603.19216</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19216.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, Jerry Xiong, Yifan Shen, Ying Shen, Ismini Lourentzou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19216</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:58:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2603.17541</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linghao Zhang, Jungang Li, Yonghua Hei, Sicheng Tao, Song Dai, Yibo Yan, Zihao Dongfang, Weiting Liu, Chenxi Qin, Hanqian Li, Xin Zou, Jiahao Zhang, Shuhang Xun, Haiyun Jiang, Xuming Hu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of visual capabilities, particularly the balance between spatial and temporal understanding, remains poorly understood. In this paper, we systematically study how Video-SFT reshapes visual capabilities in MLLMs. Across architectures, parameter scales, and frame sampling settings, we observe a consistent pattern: Video-SFT reliably improves video performance, but often yields limited gains or even degradation on static image benchmarks. We further show that this trade-off is closely tied to temporal budget: increasing the number of sampled frames generally improves video performance, but does not reliably improve static image performance. Motivated by this finding, we study an instruction-aware Hybrid-Frame strategy that adaptively allocates frame counts and partially mitigates the image-video trade-off. Our results indicate that Video-SFT is not a free lunch for MLLMs, and preserving spatial understanding remains a central challenge in joint image-video training.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17541</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 09:46:44 +0000</pubDate>
|
||||
<title>LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs</title>
|
||||
<link>https://arxiv.org/abs/2603.19217</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19217.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keda Tao, Yuhua Zheng, Jia Xu, Wenjie Du, Kele Shao, Hesong Wang, Xueyi Chen, Xin Jin, Junhan Zhu, Bohan Yu, Weiqiang Wang, Jian Liu, Can Qin, Yulun Zhang, Ming-Hsuan Yang, Huan Wang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily focus on short audio and video clips ranging from 10 seconds to 5 minutes, failing to reflect the demands of real-world applications, where videos typically run for tens of minutes. To address this critical gap, we introduce LVOmniBench, a new benchmark designed specifically for the cross-modal comprehension of long-form audio and video. This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics. Through rigorous manual selection and annotation, LVOmniBench comprises 275 videos, ranging in duration from 10 to 90 minutes, and 1,014 question-answer (QA) pairs. LVOmniBench aims to rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception. Our extensive evaluation reveals that current OmniLLMs encounter significant challenges when processing extended audio-visual inputs. Open-source models generally achieve accuracies below 35%, whereas the Gemini 3 Pro reaches a peak accuracy of approximately 65%. We anticipate that this dataset, along with our empirical findings, will stimulate further research and the development of advanced models capable of resolving complex cross-modal understanding problems within long-form audio-visual contexts.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19217</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:58:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Complementary Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2603.17621</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dilxat Muhtar, Jiashun Liu, Wei Gao, Weixun Wang, Shaopan Xiong, Ju Huang, Siran Yang, Wenbo Su, Jiamang Wang, Ling Pan, Bo Zheng</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior experience across episodes. While augmenting agents with historical experience offers a promising remedy, existing approaches suffer from a critical weakness: the experience distilled from history is either stored statically or fail to coevolve with the improving actor, causing a progressive misalignment between the experience and the actor's evolving capability that diminishes its utility over the course of training. Inspired by complementary learning systems in neuroscience, we present Complementary RL to achieve seamless co-evolution of an experience extractor and a policy actor within the RL optimization loop. Specifically, the actor is optimized via sparse outcome-based rewards, while the experience extractor is optimized according to whether its distilled experiences demonstrably contribute to the actor's success, thereby evolving its experience management strategy in lockstep with the actor's growing capabilities. Empirically, Complementary RL outperforms outcome-based agentic RL baselines that do not learn from experience, achieving 10% performance improvement in single-task scenarios and exhibits robust scalability in multi-task settings. These results establish Complementary RL as a paradigm for efficient experience-driven agent learning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17621</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 11:38:01 +0000</pubDate>
|
||||
<title>Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation</title>
|
||||
<link>https://arxiv.org/abs/2603.19220</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19220</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:58:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FINER: MLLMs Hallucinate under Fine-grained Negative Queries</title>
|
||||
<link>https://arxiv.org/abs/2603.17662</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Xiao, Sanghwan Kim, Yongqin Xian, Zeynep Akata, Stephan Alaniz</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coarse image-related questions. We introduce FIne-grained NEgative queRies (FINER), alongside two benchmarks: FINER-CompreCap and FINER-DOCCI. Using FINER, we analyze hallucinations across four settings: multi-object, multi-attribute, multi-relation, and ``what'' questions. Our benchmarks reveal that MLLMs hallucinate when fine-grained mismatches co-occur with genuinely present elements in the image. To address this, we propose FINER-Tuning, leveraging Direct Preference Optimization (DPO) on FINER-inspired data. Finetuning four frontier MLLMs with FINER-Tuning yields up to 24.2\% gains (InternVL3.5-14B) on hallucinations from our benchmarks, while simultaneously improving performance on eight existing hallucination suites, and enhancing general multimodal capabilities across six benchmarks. Code, benchmark, and models are available at https://explainableml.github.io/finer-project/{https://explainableml.github.io/finer-project/}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17662</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 12:28:05 +0000</pubDate>
|
||||
<title>F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World</title>
|
||||
<link>https://arxiv.org/abs/2603.19223</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19223.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. By integrating a two-stage LLM-based embedding training pipeline with matryoshka learning, model pruning, and knowledge distillation techniques, we present models that are far more efficient than previous LLM-based embedding models while retaining competitive performances. Extensive evaluations confirm that F2LLM-v2-14B ranks first on 11 MTEB benchmarks, while the smaller models in the family also set a new state of the art for resource-constrained applications. To facilitate open-source embedding model research, we release all models, data, code, and intermediate checkpoints.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19223</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference</title>
|
||||
<link>https://arxiv.org/abs/2603.17891</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17891.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arpit Singh Gautam, Saurabh Jha</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Post training quantization is essential for deploying large language models (LLMs) on resource constrained hardware, yet state of the art methods enforce uniform bit widths across layers, yielding suboptimal accuracy efficiency trade offs. We present RAMP (Reinforcement Adaptive Mixed Precision), an off policy Soft Actor Critic framework that learns per layer bit width assignments to minimize perplexity under a global bit budget. The policy conditions on an 11 dimensional embedding of activation statistics, weight properties, and structural descriptors, enabling zero shot transfer across model families and scales. To enable stable sub 4 bit quantization, we introduce Scale Folding, a preconditioning technique that migrates activation outliers into weights via per channel scaling and normalization layer compensation. A quality prioritized reward with asymmetric penalties and budget cliffs drives rapid convergence. On Llama 2 7B, RAMP achieves 5.54 perplexity at 3.68GB (3.65 effective bits), outperforming uniform 4 bit AWQ (5.60 at 3.90 GB) and GPTQ by 6% in size and 1% to3% in quality. Critically, a policy trained only on Llama 2 7B generalizes zero shot to Llama 2 13B and Mistral 7B, often surpassing target specific training, supporting the hypothesis that quantization sensitivity is primarily architectural. The HALO pipeline exports allocations to GGUF format for kernel free inference on CPUs, GPUs, and edge devices, retaining 99.5% of FP16 commonsense reasoning performance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17891</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 16:16:28 +0000</pubDate>
|
||||
<title>EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing</title>
|
||||
<link>https://arxiv.org/abs/2603.19224</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19224.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Fu, Yike Zheng, Ziyun Dai, Henghui Ding</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds. Beyond method limitations, progress is further hampered by the lack of a comprehensive dataset that systematically captures common object effects across varied environments for training and evaluation. To address this, we introduce VOR (Video Object Removal), a large-scale dataset that provides diverse paired videos, each consisting of one video where the target object is present with its effects and a counterpart where the object and effects are absent, with corresponding object masks. VOR contains 60K high-quality video pairs from captured and synthetic sources, covers five effects types, and spans a wide range of object categories as well as complex, dynamic multi-object scenes. Building on VOR, we propose EffectErase, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme. The model includes task-aware region guidance that focuses learning on affected areas and enables flexible task switching. Then, an insertion-removal consistency objective that encourages complementary behaviors and shared localization of effect regions and structural cues. Trained on VOR, EffectErase achieves superior performance in extensive experiments, delivering high-quality video object effect erasing across diverse scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19224</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:22 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing</title>
|
||||
<link>https://arxiv.org/abs/2603.17942</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17942.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Raghavv Goel, Mukul Gagrani, Mingu Lee, Chris Lott</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) exhibit latent multi-token prediction (MTP) capabilities despite being trained solely for next-token generation. We propose a simple, training-free MTP approach that probes an LLM using on-the-fly mask tokens drawn from its embedding space, enabling parallel prediction of future tokens without modifying model weights or relying on auxiliary draft models. Our method constructs a speculative token tree by sampling top-K candidates from mask-token logits and applies a lightweight pruning strategy to retain high-probability continuations. During decoding, candidate predictions are verified in parallel, resulting in lossless generation while substantially reducing the number of model calls and improving token throughput. Across benchmarks, our probing-based MTP consistently outperforms existing training-free baselines, increasing acceptance length by approximately 12\% on LLaMA3 and 8--12\% on Qwen3, and achieving throughput gains of up to 15--19\%. Finally, we provide theoretical insights and empirical evidence showing that decoder layers naturally align mask-token representations with next-token states, enabling accurate multi-step prediction without retraining or auxiliary models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17942</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:14:01 +0000</pubDate>
|
||||
<title>Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer</title>
|
||||
<link>https://arxiv.org/abs/2603.19227</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19227.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai, Lei Yang, Ziwei Liu</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19227</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VideoAtlas: Navigating Long-Form Video in Logarithmic Compute</title>
|
||||
<link>https://arxiv.org/abs/2603.17948</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17948.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamed Eltahir, Ali Habibullah, Yazan Alshoibi, Lama Ayash, Tanveer Hussain, Naeemullah Khan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Extending language models to video introduces two challenges: representation, where existing methods rely on lossy approximations, and long-context, where caption- or agent-based pipelines collapse video into text and lose visual fidelity. To overcome this, we introduce VideoAtlas, a task-agnostic environment to represent video as a hierarchical grid that is simultaneously lossless, navigable, scalable, caption- and preprocessing-free. An overview of the video is available at a glance, and any region can be recursively zoomed into, with the same visual representation used uniformly for the video, intermediate investigations, and the agent's memory, eliminating lossy text conversion end-to-end. This hierarchical structure ensures access depth grows only logarithmically with video length. For long-context, Recursive Language Models (RLMs) recently offered a powerful solution for long text, but extending them to visual domain requires a structured environment to recurse into, which VideoAtlas provides. VideoAtlas as a Markov Decision Process unlocks Video-RLM: a parallel Master-Worker architecture where a Master coordinates global exploration while Workers concurrently drill into assigned regions to accumulate lossless visual evidence. We demonstrate three key findings: (1)~logarithmic compute growth with video duration, further amplified by a 30-60\% multimodal cache hit rate arising from the grid's structural reuse. (2)~environment budgeting, where bounding the maximum exploration depth provides a principled compute-accuracy hyperparameter. (3)~emergent adaptive compute allocation that scales with question granularity. When scaling from 1-hour to 10-hour benchmarks, Video-RLM remains the most duration-robust method with minimal accuracy degradation, demonstrating that structured environment navigation is a viable and scalable paradigm for video understanding.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17948</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:20:19 +0000</pubDate>
|
||||
<title>SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing</title>
|
||||
<link>https://arxiv.org/abs/2603.19228</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19228.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyao Zhang, Wenkai Dong, Yuxin Song, Bo Fang, Qi Zhang, Jing Wang, Fan Chen, Hui Zhang, Haocheng Feng, Yu Lu, Hang Zhou, Chun Yuan, Jingdong Wang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Current instruction-guided video editing models struggle to simultaneously balance precise semantic modifications with faithful motion preservation. While existing approaches rely on injecting explicit external priors (e.g., VLM features or structural conditions) to mitigate these issues, this reliance severely bottlenecks model robustness and generalization. To overcome this limitation, we present SAMA (factorized Semantic Anchoring and Motion Alignment), a framework that factorizes video editing into semantic anchoring and motion modeling. First, we introduce Semantic Anchoring, which establishes a reliable visual anchor by jointly predicting semantic tokens and video latents at sparse anchor frames, enabling purely instruction-aware structural planning. Second, Motion Alignment pre-trains the same backbone on motion-centric video restoration pretext tasks (cube inpainting, speed perturbation, and tube shuffle), enabling the model to internalize temporal dynamics directly from raw videos. SAMA is optimized with a two-stage pipeline: a factorized pre-training stage that learns inherent semantic-motion representations without paired video-instruction editing data, followed by supervised fine-tuning on paired editing data. Remarkably, the factorized pre-training alone already yields strong zero-shot video editing ability, validating the proposed factorization. SAMA achieves state-of-the-art performance among open-source models and is competitive with leading commercial systems (e.g., Kling-Omni). Code, models, and datasets will be released.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19228</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition</title>
|
||||
<link>https://arxiv.org/abs/2603.17965</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17965.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vlad-Constantin Lungu-Stan, Ionut Mironica, Mariana-Iuliana Georgescu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Media design layer generation enables the creation of fully editable, layered design documents such as posters, flyers, and logos using only natural language prompts. Existing methods either restrict outputs to a fixed number of layers or require each layer to contain only spatially continuous regions, causing the layer count to scale linearly with design complexity. We propose LaDe (Layered Media Design), a latent diffusion framework that generates a flexible number of semantically meaningful layers. LaDe combines three components: an LLM-based prompt expander that transforms a short user intent into structured per-layer descriptions that guide the generation, a Latent Diffusion Transformer with a 4D RoPE positional encoding mechanism that jointly generates the full media design and its constituent RGBA layers, and an RGBA VAE that decodes each layer with full alpha-channel support. By conditioning on layer samples during training, our unified framework supports three tasks: text-to-image generation, text-to-layers media design generation, and media design decomposition. We compare LaDe to Qwen-Image-Layered on text-to-layers and image-to-layers tasks on the Crello test set. LaDe outperforms Qwen-Image-Layered in text-to-layers generation by improving text-to-layer alignment, as validated by two VLM-as-a-judge evaluators (GPT-4o mini and Qwen3-VL).</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17965</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:34:07 +0000</pubDate>
|
||||
<title>MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction</title>
|
||||
<link>https://arxiv.org/abs/2603.19231</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19231.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haitian Li, Haozhe Xie, Junxiang Xu, Beichen Wen, Fangzhou Hong, Ziwei Liu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Reconstructing articulated 3D objects from a single image requires jointly inferring object geometry, part structure, and motion parameters from limited visual evidence. A key difficulty lies in the entanglement between motion cues and object structure, which makes direct articulation regression unstable. Existing methods address this challenge through multi-view supervision, retrieval-based assembly, or auxiliary video generation, often sacrificing scalability or efficiency. We present MonoArt, a unified framework grounded in progressive structural reasoning. Rather than predicting articulation directly from image features, MonoArt progressively transforms visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture. This structured reasoning process enables stable and interpretable articulation inference without external motion templates or multi-stage pipelines. Extensive experiments on PartNet-Mobility demonstrate that OM achieves state-of-the-art performance in both reconstruction accuracy and inference speed. The framework further generalizes to robotic manipulation and articulated scene reconstruction.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19231</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LoST: Level of Semantics Tokenization for 3D Shapes</title>
|
||||
<link>https://arxiv.org/abs/2603.17995</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.17995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra, Xuelin Chen</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. State-of-the-art (SOTA) methods primarily rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression. These spatial hierarchies are often token-inefficient and lack semantic coherence for AR modeling. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience, such that early prefixes decode into complete, plausible shapes that possess principal semantics, while subsequent tokens refine instance-specific geometric and semantic details. To train LoST, we introduce Relational Inter-Distance Alignment (RIDA), a novel 3D semantic alignment loss that aligns the relational structure of the 3D shape latent space with that of the semantic DINO feature space. Experiments show that LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics. Moreover, LoST achieves efficient, high-quality AR 3D generation and enables downstream tasks like semantic retrieval, while using only 0.1%-10% of the tokens needed by prior AR models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.17995</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:56:06 +0000</pubDate>
|
||||
<title>Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens</title>
|
||||
<link>https://arxiv.org/abs/2603.19232</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Wang, Chuofan Ma, Zhijie Lin, Yao Teng, Lijun Yu, Shuai Wang, Jiaming Han, Jiashi Feng, Yi Jiang, Xihui Liu</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discrete generation methods remain limited to low-dimensional latent tokens (typically 8-32 dims), sacrificing the semantic richness essential for understanding. While high-dimensional pretrained representations (768-1024 dims) could bridge this gap, their discrete generation poses fundamental challenges. In this paper, we present Cubic Discrete Diffusion (CubiD), the first discrete generation model for high-dimensional representations. CubiD performs fine-grained masking throughout the high-dimensional discrete representation -- any dimension at any position can be masked and predicted from partial observations. This enables the model to learn rich correlations both within and across spatial positions, with the number of generation steps fixed at T regardless of feature dimensionality, where T ll hwd. On ImageNet-256, CubiD achieves state-of-the-art discrete generation with strong scaling behavior from 900M to 3.7B parameters. Crucially, we validate that these discretized tokens preserve original representation capabilities, demonstrating that the same discrete tokens can effectively serve both understanding and generation tasks. We hope this work will inspire future research toward unified multimodal architectures. Code is available at: https://github.com/YuqingWang1029/CubiD.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19232</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Unified Spatio-Temporal Token Scoring for Efficient Video VLMs</title>
|
||||
<link>https://arxiv.org/abs/2603.18004</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.18004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianrui Zhang, Yue Yang, Rohun Tripathi, Winson Han, Ranjay Krishna, Christopher Clark, Yong Jae Lee, Sangho Lee</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the vision transformer (ViT) exclusively for unimodal perception tasks such as action recognition and object segmentation, without adapting to downstream vision-language tasks; or (2) only within the LLM while leaving the ViT output intact, often requiring complex text-conditioned token selection mechanisms. In this paper, we introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM without text conditioning or token merging, and is fully compatible with end-to-end training. By learning how to score temporally via an auxiliary loss and spatially via LLM downstream gradients, aided by our efficient packing algorithm, STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference with only a 0.7% drop in average performance across 13 short and long video QA tasks. Efficiency gains increase with more sampled frames per video. Applying test-time scaling for long-video QA further yields performance gains of 0.5-1% compared to the baseline. Overall, STTS represents a novel, simple yet effective technique for unified, architecture-wide vision token pruning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.18004</guid>
|
||||
<pubDate>Wed, 18 Mar 2026 17:59:56 +0000</pubDate>
|
||||
<title>Matryoshka Gaussian Splatting</title>
|
||||
<link>https://arxiv.org/abs/2603.19234</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19234.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty, Jeffrey Hu, Nursena Koprucu Aslan, Wenzhao Li, Canberk Baykal, Albert Miao, Josef Bengtson, Chenliang Zhou, Weihao Xia, Cristina Nader Vasconcelos. Cengiz Oztireli</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existing discrete LoD methods expose only a limited set of operating points, while concurrent continuous LoD approaches enable smoother scaling but often suffer noticeable quality degradation at full capacity, making LoD a costly design decision. We introduce Matryoshka Gaussian Splatting (MGS), a training framework that enables continuous LoD for standard 3DGS pipelines without sacrificing full-capacity rendering quality. MGS learns a single ordered set of Gaussians such that rendering any prefix, the first k splats, produces a coherent reconstruction whose fidelity improves smoothly with increasing budget. Our key idea is stochastic budget training: each iteration samples a random splat budget and optimises both the corresponding prefix and the full set. This strategy requires only two forward passes and introduces no architectural modifications. Experiments across four benchmarks and six baselines show that MGS matches the full-capacity performance of its backbone while enabling a continuous speed-quality trade-off from a single model. Extensive ablations on ordering strategies, training objectives, and model capacity further validate the designs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19234</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding</title>
|
||||
<link>https://arxiv.org/abs/2603.19235</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.19235.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xianjin Wu, Dingkang Liang, Tianrui Feng, Kui Xia, Yumeng Zhang, Xiaofan Li, Xiao Tan, Xiang Bai</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on explicit 3D modalities or complex geometric scaffolding, which are limited by data scarcity and generalization challenges. In this work, we propose a paradigm shift by leveraging the implicit spatial prior within large-scale video generation models. We posit that to synthesize temporally coherent videos, these models inherently learn robust 3D structural priors and physical laws. We introduce VEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator. By extracting spatiotemporal features from intermediate noise levels and integrating them with semantic representations via a token-level adaptive gated fusion mechanism, we enrich MLLMs with dense geometric cues without explicit 3D supervision. Extensive experiments across 3D scene understanding, spatial reasoning, and embodied manipulation benchmarks demonstrate that our method outperforms state-of-the-art baselines, validating that generative priors provide a scalable foundation for physical-world understanding. Code is publicly available at https://github.com/H-EmbodVis/VEGA-3D.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2603.19235</guid>
|
||||
<pubDate>Thu, 19 Mar 2026 17:59:58 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user