diff --git a/feed.xml b/feed.xml index e394856..d8d2312 100644 --- a/feed.xml +++ b/feed.xml @@ -7,328 +7,370 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 18 Mar 2026 00:06:06 +0000 + Thu, 19 Mar 2026 00:04:58 +0000 - FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach - https://arxiv.org/abs/2603.13364 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13364.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ning Liao, Xiaoxing Wang, Xiaohan Qin, Junchi Yan</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> As revealed by the scaling law of fine-grained MoE, model performance ceases to be improved once the granularity of the intermediate dimension exceeds the optimal threshold, limiting further gains from single-dimension fine-grained design. To address this bottleneck, we propose FineRMoE (FineR-Grained MoE), an architecture that extends fine-grained expert design to both intermediate and output dimensions, aiming to enhance expert specialization beyond the single-dimension limit. We further introduce a bi-level sparse forward computation paradigm and a specialized routing mechanism to govern the activation. In addition, to obviate the prohibitive cost of training FineRMoE from scratch, we devise a generalized upcycling method to build FineRMoE in a cost-effective manner. Extensive experiments demonstrate the superior performance achieved by FineRMoE across ten standard benchmarks. Compared with the strongest baseline, FineRMoE achieves 6 times higher parameter efficiency, 281 times lower prefill latency, and 136 timese higher decoding throughput during inference.</p> - https://arxiv.org/abs/2603.13364 - Mon, 09 Mar 2026 12:00:36 +0000 + Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context + https://arxiv.org/abs/2603.15653 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keivan Alizadeh, Parshin Shojaee, Minsik Cho, Mehrdad Farajtabar</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language Models (RLM) have approached this challenge by agentic way of decomposing long contexts into recursive sub-calls through programmatic interaction at inference. While promising, the success of RLM critically depends on how these context-interaction programs are selected, which has remained largely unexplored. In this paper, we study this problem and introduce SRLM, a framework that augments programmatic context interaction with uncertainty-aware Self-Reflection. SRLM leverages three intrinsic signals: self consistency, reasoning length, and verbalized confidence. These serve as complementary indicators of a model's internal uncertainty, and the model uses them to evaluate and compare candidate context-interaction programs. Extensive experiments across diverse benchmark datasets, context lengths, and backbone models, show that SRLM consistently outperforms state-of-the-art baselines, yielding up to 22% improvement over RLM under the same time budget. Our findings show that recursion itself is not the primary driver of performance in RLM, and a simple self-reflective program search can match or surpass RLM without requiring self-query or explicit recursion mechanisms. We find that for context lengths within the model's window, RLMs with recursion often degrade performance relative to the base model, whereas SRLM yields consistent gains across both short and long contexts. We also find that RLM is less effective in tasks with semantically intensive nature, where heuristic program search is insufficient and broader contextual understanding is required, while self-reflection in SRLM provides a semantic signal that better steers reasoning in these scenarios.</p> + https://arxiv.org/abs/2603.15653 + Sat, 07 Mar 2026 01:18:04 +0000 - WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics - https://arxiv.org/abs/2603.13391 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhong Dai, Yanlin Lai, Mitt Huang, Hangyu Guo, Dingming Li, Hongbo Peng, Haodong Li, Yingxiu Zhao, Haoran Lyu, Zheng Ge, Xiangyu Zhang, Daxin Jiang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing, and motion continuity, which are essential for faithful webpage recreation. Despite this potential, video-conditioned webpage generation remains largely unexplored, with no dedicated benchmark for this task. To fill this gap, we introduce WebVR, a benchmark that evaluates whether MLLMs can faithfully recreate webpages from demonstration videos. WebVR contains 175 webpages across diverse categories, all constructed through a controlled synthesis pipeline rather than web crawling, ensuring varied and realistic demonstrations without overlap with existing online pages. We also design a fine-grained, human-aligned visual rubric that evaluates the generated webpages across multiple dimensions. Experiments on 19 models reveal substantial gaps in recreating fine-grained style and motion quality, while the rubric-based automatic evaluation achieves 96% agreement with human preferences. We release the dataset, evaluation toolkit, and baseline results to support future research on video-to-webpage generation.</p> - https://arxiv.org/abs/2603.13391 - Wed, 11 Mar 2026 07:48:23 +0000 + FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use + https://arxiv.org/abs/2603.08262 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.08262.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxuan Lu, Kong Wang, Yemin Wang, Qingmei Tang, Hongwei Zeng, Xiang Chen, Jiahao Pi, Shujian Deng, Lingzhi Chen, Yi Fu, Kehua Yang, Xiao Sun</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> The integration of Large Language Models (LLMs) into the financial domain is driving a paradigm shift from passive information retrieval to dynamic, agentic interaction. While general-purpose tool learning has witnessed a surge in benchmarks, the financial sector, characterized by high stakes, strict compliance, and rapid data volatility, remains critically underserved. Existing financial evaluations predominantly focus on static textual analysis or document-based QA, ignoring the complex reality of tool execution. Conversely, general tool benchmarks lack the domain-specific rigor required for finance, often relying on toy environments or a negligible number of financial APIs. To bridge this gap, we introduce FinToolBench, the first real-world, runnable benchmark dedicated to evaluating financial tool learning agents. Unlike prior works limited to a handful of mock tools, FinToolBench establishes a realistic ecosystem coupling 760 executable financial tools with 295 rigorous, tool-required queries. We propose a novel evaluation framework that goes beyond binary execution success, assessing agents on finance-critical dimensions: timeliness, intent type, and regulatory domain alignment. Furthermore, we present FATR, a finance-aware tool retrieval and reasoning baseline that enhances stability and compliance. By providing the first testbed for auditable, agentic financial execution, FinToolBench sets a new standard for trustworthy AI in finance. The tool manifest, execution environment, and evaluation code will be open-sourced to facilitate future research.</p> + https://arxiv.org/abs/2603.08262 + Mon, 09 Mar 2026 11:33:05 +0000 - Safe and Scalable Web Agent Learning via Recreated Websites - https://arxiv.org/abs/2603.10505 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.10505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyungjoo Chae, Jungsoo Park, Alan Ritter</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments. Code and resources will be released at https://github.com/kyle8581/VeriEnv upon acceptance.</p> - https://arxiv.org/abs/2603.10505 - Wed, 11 Mar 2026 07:58:53 +0000 + Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding + https://arxiv.org/abs/2603.13366 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongxing Xu, Zhonghua Wang, Zhe Qian, Dachuan Shi, Feilong Tang, Ming Hu, Shiyan Su, Xiaocheng Zou, Wei Feng, Dwarikanath Mahapatra, Yifan Peng, Mingquan Lin, Zongyuan Ge</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent advancements in multimodal large reasoning models (MLRMs) have significantly improved performance in visual question answering. However, we observe that transition words (e.g., because, however, and wait) are closely associated with hallucinations and tend to exhibit high-entropy states. We argue that adequate contextual reasoning information can be directly extracted from the token probability distribution. Inspired by superposed representation theory, we propose leveraging latent superposed reasoning to integrate multiple candidate semantics and maintain latent reasoning trajectories. The hypothesis is that reliance on discrete textual inputs may drive the model toward sequential explicit reasoning, underutilizing dense contextual cues during high-entropy reasoning stages. Therefore, we propose constructing rich semantic representations from the token probability distributions to enhance in-context reasoning. With this goal, we present Latent Entropy-Aware Decoding (LEAD), an efficient plug-and-play decoding strategy that leverages semantic context to achieve reliable reasoning. The heart of our method lies in entropy-aware reasoning mode switching. The model employs probability-weighted continuous embeddings under high-entropy states and transitions back to discrete token embeddings as entropy decreases. Moreover, we propose a prior-guided visual anchor injection strategy that encourages the model to focus on visual information. Extensive experiments show that LEAD effectively mitigates hallucinations across various MLRMs on multiple benchmarks.</p> + https://arxiv.org/abs/2603.13366 + Mon, 09 Mar 2026 12:47:54 +0000 - FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance - https://arxiv.org/abs/2603.12146 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12146.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quanhao Li, Zhen Xing, Rui Wang, Haidong Cao, Qi Dai, Daoguo Dong, Zuxuan Wu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories. However, all these methods rely on a multi-step denoising process, leading to substantial time redundancy and computational overhead. While existing video distillation methods successfully distill multi-step generators into few-step, directly applying these approaches to trajectory-controllable video generation results in noticeable degradation in both video quality and trajectory accuracy. To bridge this gap, we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation. We first train a trajectory adapter on a multi-step video generator for precise trajectory control. Then, we distill the generator into a few-step version to accelerate video generation. Finally, we finetune the adapter using a hybrid strategy that combines diffusion and adversarial objectives, aligning it with the few-step generator to produce high-quality, trajectory-accurate videos. For evaluation, we introduce FlashBench, a benchmark for long-sequence trajectory-controllable video generation that measures both video quality and trajectory accuracy across varying numbers of foreground objects. Experiments on two adapter architectures show that FlashMotion surpasses existing video distillation methods and previous multi-step models in both visual quality and trajectory consistency.</p> - https://arxiv.org/abs/2603.12146 - Thu, 12 Mar 2026 16:45:53 +0000 + MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games + https://arxiv.org/abs/2603.09022 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09022.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates and makes rankings unreliable across repeated tournaments. Prompt choice worsens this further by producing different effective policies. We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework that optimizes inference-time context by coupling retention and exploration. Retention maintains a persistent memory bank that stores structured insights from self-play trajectories and injects them as priors during later play. Exploration runs tournament-style prompt evolution with uncertainty-aware selection via TrueSkill, and uses prioritized replay to revisit rare and decisive states. Across five text-based games, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 44.3% for Qwen-2.5-7B-Instruct, using 2,000 self-play games per task. Run-to-run variance also drops, giving more stable rankings across prompt variations. These results suggest that multi-agent LLM game performance and robustness have substantial room for improvement through context optimization. MEMO achieves the largest gains in negotiation and imperfect-information games, while RL remains more effective in perfect-information settings.</p> + https://arxiv.org/abs/2603.09022 + Mon, 09 Mar 2026 23:36:32 +0000 - TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning - https://arxiv.org/abs/2603.12529 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant overthinking, spending excessive compute time even after the answer is generated early on. Prior work has identified the existence of an optimal reasoning length such that truncating reasoning at this point significantly shortens CoT outputs with virtually no change in performance. However, determining optimal CoT lengths for practical datasets is highly non-trivial as they are fully task and model-dependent. In this paper, we precisely address this and design TERMINATOR, an early-exit strategy for LRMs at inference to mitigate overthinking. The central idea underpinning TERMINATOR is that the first arrival of an LRM's final answer is often predictable, and we leverage these first answer positions to create a novel dataset of optimal reasoning lengths to train TERMINATOR. Powered by this approach, TERMINATOR achieves significant reductions in CoT lengths of 14%-55% on average across four challenging practical datasets: MATH-500, AIME 2025, HumanEval, and GPQA, whilst outperforming current state-of-the-art methods.</p> - https://arxiv.org/abs/2603.12529 - Fri, 13 Mar 2026 00:07:18 +0000 + One-Eval: An Agentic System for Automated and Traceable LLM Evaluation + https://arxiv.org/abs/2603.09821 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.09821.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengyu Shen, Yanheng Hou, Minghui Pan, Runming He, Zhen Hao Wong, Meiyi Qiang, Zhou Liu, Hao Liang, Peichao Lai, Zeang Sheng, Wentao Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation codebases, configure dataset schema mappings, and interpret aggregated metrics. To address these challenges, we present One-Eval, an agentic evaluation system that converts natural-language evaluation requests into executable, traceable, and customizable evaluation workflows. One-Eval integrates (i) NL2Bench for intent structuring and personalized benchmark planning, (ii) BenchResolve for benchmark resolution, automatic dataset acquisition, and schema normalization to ensure executability, and (iii) Metrics \& Reporting for task-aware metric selection and decision-oriented reporting beyond scalar scores. The system further incorporates human-in-the-loop checkpoints for review, editing, and rollback, while preserving sample evidence trails for debugging and auditability. Experiments show that One-Eval can execute end-to-end evaluations from diverse natural-language requests with minimal user effort, supporting more efficient and reproducible evaluation in industrial settings. Our framework is publicly available at https://github.com/OpenDCAI/One-Eval.</p> + https://arxiv.org/abs/2603.09821 + Tue, 10 Mar 2026 15:45:51 +0000 - EvoClaw: Evaluating AI Agents on Continuous Software Evolution - https://arxiv.org/abs/2603.13428 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gangda Deng, Zhaoling Chen, Zhongming Yu, Haoyang Fan, Yuhong Liu, Yuxin Yang, Dhruv Parikh, Rajgopal Kannan, Le Cong, Mengdi Wang, Qian Zhang, Viktor Prasanna, Xiangru Tang, Xingyao Wang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs, where milestones are defined as semantically cohesive development goals. These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation, dimensions of long-term software evolution largely missing from current benchmarks. Our evaluation of 12 frontier models across 4 agent frameworks reveals a critical vulnerability: overall performance scores drop significantly from >80% on isolated tasks to at most 38% in continuous settings, exposing agents' profound struggle with long-term maintenance and error propagation.</p> - https://arxiv.org/abs/2603.13428 - Fri, 13 Mar 2026 03:20:40 +0000 + Qianfan-OCR: A Unified End-to-End Model for Document Intelligence + https://arxiv.org/abs/2603.13398 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13398.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daxiang Dong, Mingming Zheng, Dong Xu, Chunhua Luo, Bairong Zhuang, Yuxuan Li, Ruoyun He, Haoran Wang, Wenyu Zhang, Wenbo Wang, Yicheng Wang, Xue Xiong, Ayong Zheng, Xiaoying Zuo, Ziwei Ou, Jingnan Gu, Quanhao Guo, Jianmin Wu, Dawei Yin, Dou Shen</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It performs direct image-to-Markdown conversion and supports diverse prompt-driven tasks including table extraction, chart understanding, document QA, and key information extraction. To address the loss of explicit layout analysis in end-to-end OCR, we propose Layout-as-Thought, an optional thinking phase triggered by special think tokens that generates structured layout representations -- bounding boxes, element types, and reading order -- before producing final outputs, recovering layout grounding capabilities while improving accuracy on complex layouts. Qianfan-OCR ranks first among end-to-end models on OmniDocBench v1.5 (93.12) and OlmOCR Bench (79.8), achieves competitive results on OCRBench, CCOCR, DocVQA, and ChartQA against general VLMs of comparable scale, and attains the highest average score on public key information extraction benchmarks, surpassing Gemini-3.1-Pro, Seed-2.0, and Qwen3-VL-235B. The model is publicly accessible via the Baidu AI Cloud Qianfan platform.</p> + https://arxiv.org/abs/2603.13398 + Wed, 11 Mar 2026 16:08:22 +0000 - MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization - https://arxiv.org/abs/2603.12743 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyang Zhu, Hongxiang Li, Xiu Li, Long Chen</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Concept customization typically binds rare tokens to a target concept. Unfortunately, these approaches often suffer from unstable performance as the pretraining data seldom contains these rare tokens. Meanwhile, these rare tokens fail to convey the inherent knowledge of the target concept. Consequently, we introduce Knowledge-aware Concept Customization, a novel task aiming at binding diverse textual knowledge to target visual concepts. This task requires the model to identify the knowledge within the text prompt to perform high-fidelity customized generation. Meanwhile, the model should efficiently bind all the textual knowledge to the target concept. Therefore, we propose MoKus, a novel framework for knowledge-aware concept customization. Our framework relies on a key observation: cross-modal knowledge transfer, where modifying knowledge within the text modality naturally transfers to the visual modality during generation. Inspired by this observation, MoKus contains two stages: (1) In visual concept learning, we first learn the anchor representation to store the visual information of the target concept. (2) In textual knowledge updating, we update the answer for the knowledge queries to the anchor representation, enabling high-fidelity customized generation. To further comprehensively evaluate our proposed MoKus on the new task, we introduce the first benchmark for knowledge-aware concept customization: KnowCusBench. Extensive evaluations have demonstrated that MoKus outperforms state-of-the-art methods. Moreover, the cross-model knowledge transfer allows MoKus to be easily extended to other knowledge-aware applications like virtual concept creation and concept erasure. We also demonstrate the capability of our method to achieve improvements on world knowledge benchmarks.</p> - https://arxiv.org/abs/2603.12743 - Fri, 13 Mar 2026 07:39:35 +0000 + Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration + https://arxiv.org/abs/2603.12226 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12226.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Priyanka Kargupta, Shuhaib Mehri, Dilek Hakkani-Tur, Jiawei Han</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Despite interdisciplinary research leading to larger and longer-term impact, most work remains confined to single-domain academic silos. Recent AI-based approaches to scientific discovery show promise for interdisciplinary research, but many prioritize rapidly designing experiments and solutions, bypassing the exploratory, collaborative reasoning processes that drive creative interdisciplinary breakthroughs. As a result, prior efforts largely prioritize automating scientific discovery rather than augmenting the reasoning processes that underlie scientific disruption. We present Idea-Catalyst, a novel framework that systematically identifies interdisciplinary insights to support creative reasoning in both humans and large language models. Starting from an abstract research goal, Idea-Catalyst is designed to assist the brainstorming stage, explicitly avoiding premature anchoring on specific solutions. The framework embodies key metacognitive features of interdisciplinary reasoning: (a) defining and assessing research goals, (b) awareness of a domain's opportunities and unresolved challenges, and (c) strategic exploration of interdisciplinary ideas based on impact potential. Concretely, Idea-Catalyst decomposes an abstract goal (e.g., improving human-AI collaboration) into core target-domain research questions that guide the analysis of progress and open challenges within that domain. These challenges are reformulated as domain-agnostic conceptual problems, enabling retrieval from external disciplines (e.g., Psychology, Sociology) that address analogous issues. By synthesizing and recontextualizing insights from these domains back into the target domain, Idea-Catalyst ranks source domains by their interdisciplinary potential. Empirically, this targeted integration improves average novelty by 21% and insightfulness by 16%, while remaining grounded in the original research problem.</p> + https://arxiv.org/abs/2603.12226 + Thu, 12 Mar 2026 17:48:34 +0000 - VoXtream2: Full-stream TTS with dynamic speaking rate control - https://arxiv.org/abs/2603.13518 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Full-stream text-to-speech (TTS) for interactive systems must start speaking with minimal delay while remaining controllable as text arrives incrementally. We present VoXtream2, a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. VoXtream2 combines a distribution matching mechanism over duration states with classifier-free guidance across conditioning signals to improve controllability and synthesis quality. Prompt-text masking enables textless audio prompting, removing the need for prompt transcription. Across standard zero-shot benchmarks and a dedicated speaking-rate test set, VoXtream2 achieves competitive objective and subjective results against public baselines despite a smaller model and less training data. In full-stream mode, it runs 4 times faster than real time with 74 ms first-packet latency on a consumer GPU.</p> - https://arxiv.org/abs/2603.13518 - Fri, 13 Mar 2026 18:49:25 +0000 + Test-Time Strategies for More Efficient and Accurate Agentic RAG + https://arxiv.org/abs/2603.12396 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.12396.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Brian Zhang, Deepti Guntur, Zhiyang Zuo, Abhinav Sharma, Shreyas Chaudhari, Wenlong Zhao, Franck Dernoncourt, Puneet Mathur, Ryan Rossi, Nedim Lipka</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities. However, such approaches can introduce inefficiencies, including repetitive retrieval of previously processed information and challenges in contextualizing retrieved results effectively within the current generation prompt. Such issues can lead to unnecessary retrieval turns, suboptimal reasoning, inaccurate answers, and increased token consumption. In this paper, we investigate test-time modifications to the Search-R1 pipeline to mitigate these identified shortcomings. Specifically, we explore the integration of two components and their combination: a contextualization module to better integrate relevant information from retrieved documents into reasoning, and a de-duplication module that replaces previously retrieved documents with the next most relevant ones. We evaluate our approaches using the HotpotQA (Yang et al., 2018) and the Natural Questions (Kwiatkowski et al., 2019) datasets, reporting the exact match (EM) score, an LLM-as-a-Judge assessment of answer correctness, and the average number of turns. Our best-performing variant, utilizing GPT-4.1-mini for contextualization, achieves a 5.6% increase in EM score and reduces the number of turns by 10.5% compared to the Search-R1 baseline, demonstrating improved answer accuracy and retrieval efficiency.</p> + https://arxiv.org/abs/2603.12396 + Thu, 12 Mar 2026 19:18:59 +0000 - EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings - https://arxiv.org/abs/2603.13594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar</p><p><b>Upvotes:</b> 117</p><p><b>Summary:</b> Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.</p> - https://arxiv.org/abs/2603.13594 - Fri, 13 Mar 2026 21:09:39 +0000 + I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning + https://arxiv.org/abs/2603.15670 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aliyu Agboola Alege</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discrete predicates (probabilistic logic frameworks), limiting scalability to unstructured data. We introduce Latent Posterior Factors (LPF), a framework that transforms Variational Autoencoder (VAE) latent posteriors into soft likelihood factors for Sum-Product Network (SPN) inference, enabling tractable probabilistic reasoning over unstructured evidence while preserving calibrated uncertainty estimates. We instantiate LPF as LPF-SPN (structured factor-based inference) and LPF-Learned (end-to-end learned aggregation), enabling a principled comparison between explicit probabilistic reasoning and learned aggregation under a shared uncertainty representation. Across eight domains (seven synthetic and the FEVER benchmark), LPF-SPN achieves high accuracy (up to 97.8%), low calibration error (ECE 1.4%), and strong probabilistic fit, substantially outperforming evidential deep learning, LLMs and graph-based baselines over 15 random seeds. Contributions: (1) A framework bridging latent uncertainty representations with structured probabilistic reasoning. (2) Dual architectures enabling controlled comparison of reasoning paradigms. (3) Reproducible training methodology with seed selection. (4) Evaluation against EDL, BERT, R-GCN, and large language model baselines. (5) Cross-domain validation. (6) Formal guarantees in a companion paper.</p> + https://arxiv.org/abs/2603.15670 + Fri, 13 Mar 2026 10:05:14 +0000 - SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis - https://arxiv.org/abs/2603.13884 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13884.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ehud Gordon, Meir Yossef Levi, Guy Gilboa</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically meaningful components. However, existing methods are largely restricted to images and overlook the cross-modal interactions. Text-image embeddings, such as those produced by CLIP, suffer from a modality gap, where visual and textual features follow distinct distributions, limiting interpretability. Canonical Correlation Analysis (CCA) offers a principled way to align features from different distributions, but has not been leveraged for multi-modal concept-level analysis. We show that the objectives of CCA and InfoNCE are closely related, such that optimizing CCA implicitly optimizes InfoNCE, providing a simple, training-free mechanism to enhance cross-modal alignment without affecting the pre-trained InfoNCE objective. Motivated by this observation, we couple concept-based explainability with CCA, introducing Concept CCA (CoCCA), a framework that aligns cross-modal embeddings while enabling interpretable concept decomposition. We further extend it and propose Sparse Concept CCA (SCoCCA), which enforces sparsity to produce more disentangled and discriminative concepts, facilitating improved activation, ablation, and semantic manipulation. Our approach generalizes concept-based explanations to multi-modal embeddings and achieves state-of-the-art performance in concept discovery, evidenced by reconstruction and manipulation tasks such as concept ablation.</p> - https://arxiv.org/abs/2603.13884 - Sat, 14 Mar 2026 10:45:59 +0000 + Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning + https://arxiv.org/abs/2603.15674 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aliyu Agboola Alege</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present a complete theoretical characterization of Latent Posterior Factors (LPF), a principled framework for aggregating multiple heterogeneous evidence items in probabilistic prediction tasks. Multi-evidence reasoning arises pervasively in high-stakes domains including healthcare diagnosis, financial risk assessment, legal case analysis, and regulatory compliance, yet existing approaches either lack formal guarantees or fail to handle multi-evidence scenarios architecturally. LPF encodes each evidence item into a Gaussian latent posterior via a variational autoencoder, converting posteriors to soft factors through Monte Carlo marginalization, and aggregating factors via exact Sum-Product Network inference (LPF-SPN) or a learned neural aggregator (LPF-Learned). We prove seven formal guarantees spanning the key desiderata for trustworthy AI: Calibration Preservation (ECE <= epsilon + C/sqrt(K_eff)); Monte Carlo Error decaying as O(1/sqrt(M)); a non-vacuous PAC-Bayes bound with train-test gap of 0.0085 at N=4200; operation within 1.12x of the information-theoretic lower bound; graceful degradation as O(epsilon*delta*sqrt(K)) under corruption, maintaining 88% performance with half of evidence adversarially replaced; O(1/sqrt(K)) calibration decay with R^2=0.849; and exact epistemic-aleatoric uncertainty decomposition with error below 0.002%. All theorems are empirically validated on controlled datasets spanning up to 4,200 training examples. Our theoretical framework establishes LPF as a foundation for trustworthy multi-evidence AI in safety-critical applications.</p> + https://arxiv.org/abs/2603.15674 + Fri, 13 Mar 2026 17:44:14 +0000 - sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook - https://arxiv.org/abs/2603.13962 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ibrahim Ebrar Yurt, Fabian Karl, Tejaswi Choppa, Florian Matthes</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical environments due to privacy constraints and computational requirements. In this work, we investigate how far grounded EHR question answering can be pushed when restricted to a single notebook. We participate in all four subtasks of the ArchEHR-QA 2026 shared task and evaluate several approaches designed to run on commodity hardware. All experiments are conducted locally without external APIs or cloud infrastructure. Our results show that such systems can achieve competitive performance on the shared task leaderboards. In particular, our submissions perform above average in two subtasks, and we observe that smaller models can approach the performance of much larger systems when properly configured. These findings suggest that privacy-preserving EHR QA systems running fully locally are feasible with current models and commodity hardware. The source code is available at https://github.com/ibrahimey/ArchEHR-QA-2026.</p> - https://arxiv.org/abs/2603.13962 - Sat, 14 Mar 2026 14:17:55 +0000 + BERTology of Molecular Property Prediction + https://arxiv.org/abs/2603.13627 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13627.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Mostafanejad, Paul Saxe, T. Daniel Crawford</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Chemical language models (CLMs) have emerged as promising competitors to popular classical machine learning models for molecular property prediction (MPP) tasks. However, an increasing number of studies have reported inconsistent and contradictory results for the performance of CLMs across various MPP benchmark tasks. In this study, we conduct and analyze hundreds of meticulously controlled experiments to systematically investigate the effects of various factors, such as dataset size, model size, and standardization, on the pre-training and fine-tuning performance of CLMs for MPP. In the absence of well-established scaling laws for encoder-only masked language models, our aim is to provide comprehensive numerical evidence and a deeper understanding of the underlying mechanisms affecting the performance of CLMs for MPP tasks, some of which appear to be entirely overlooked in the literature.</p> + https://arxiv.org/abs/2603.13627 + Fri, 13 Mar 2026 22:18:22 +0000 - Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models - https://arxiv.org/abs/2603.13985 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13985.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haitao Jiang, Wenbo Zhang, Jiarui Yao, Hengrui Cai, Sheng Wang, Rui Song</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). Although often treated as distinct methodologies, recent theoretical and empirical developments demonstrate that SFT and RL are closely connected. This study presents a comprehensive and unified perspective on LLM post-training with SFT and RL. We first provide an in-depth overview of both techniques, examining their objectives, algorithmic structures, and data requirements. We then systematically analyze their interplay, highlighting frameworks that integrate SFT and RL, hybrid training pipelines, and methods that leverage their complementary strengths. Drawing on a representative set of recent application studies from 2023 to 2025, we identify emerging trends, characterize the rapid shift toward hybrid post-training paradigms, and distill key takeaways that clarify when and why each method is most effective. By synthesizing theoretical insights, practical methodologies, and empirical evidence, this study establishes a coherent understanding of SFT and RL within a unified framework and outlines promising directions for future research in scalable, efficient, and generalizable LLM post-training.</p> - https://arxiv.org/abs/2603.13985 - Sat, 14 Mar 2026 15:24:38 +0000 + Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia + https://arxiv.org/abs/2603.13715 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13715.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sandy Hardian Susanto Herho, Alfita Puspa Handayani, Karina Aprilia Sujatmiko, Faruq Khadami, Iwan Pramesti Anwar</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large-scale land enclosure for speculative mega-development constitutes a non-equilibrium spatial process whose velocity, topology, and irreversibility remain poorly quantified. We study the Pantai Indah Kapuk 2 (PIK2) coastal mega-development north of Jakarta, Indonesia, using eight years (2017--2024) of Sentinel-2 land-use/land-cover (LULC) data at 10-meter resolution. The landscape is projected onto a Marxian probability simplex partitioning terrestrial pixels into Commons, Agrarian, and Capital fractions. Fisher-Rao (FR) geodesic distances on this simplex identify a transformation pulse of 0.405~rad/yr during 2019--2020, coinciding with major construction activity. Absorbing Markov chain analysis yields expected absorption times into the built environment of 46.0~years for cropland and 38.1~years for tree cover, with a pooled built-area self-retention rate of 96.4%. Percolation analysis reveals that a giant connected component containing 89--95% of all built pixels persists at occupation probabilities p in [0.096, 0.162], far below the random percolation threshold p_c approx 0.593, indicating planned rather than stochastic spatial growth. The box-counting fractal dimension of the urban boundary increases from d_f = 1.316 to 1.397, consistent with increasingly irregular frontier expansion. These results suggest that information-geometric and statistical-mechanical tools can characterize the kinematic and topological signatures of capitalist spatial accumulation with quantitative precision.</p> + https://arxiv.org/abs/2603.13715 + Sat, 14 Mar 2026 02:42:27 +0000 - MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos - https://arxiv.org/abs/2603.14145 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14145.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, Lasha Koroshinadze, Yao Xu, Katie Lyons, James Case, Karan Sapra, Kevin J. Shih, Siddharth Gururani, Abhinav Shrivastava, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Bryan Catanzaro, Mohammad Shoeybi, Wei Ping</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break.</p> - https://arxiv.org/abs/2603.14145 - Sat, 14 Mar 2026 22:28:38 +0000 + GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent + https://arxiv.org/abs/2603.13875 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.13875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuri Kuratov, Matvey Kairov, Aydar Bulatov, Ivan Rodkin, Mikhail Burtsev</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is ompressive memory: read a context once, store it in a compact state, and answer many queries from that state. We study this in a context removal setting, where the model must generate an answer without access to the original context at inference time. We introduce GradMem, which writes context into memory via per-sample test-time optimization. Given a context, GradMem performs a few steps of gradient descent on a small set of prefix memory tokens while keeping model weights frozen. GradMem explicitly optimizes a model-level self-supervised context reconstruction loss, resulting in a loss-driven write operation with iterative error correction, unlike forward-only methods. On associative key--value retrieval, GradMem outperforms forward-only memory writers with the same memory size, and additional gradient steps scale capacity much more effectively than repeated forward writes. We further show that GradMem transfers beyond synthetic benchmarks: with pretrained language models, it attains competitive results on natural language tasks including bAbI and SQuAD variants, relying only on information encoded in memory.</p> + https://arxiv.org/abs/2603.13875 + Sat, 14 Mar 2026 10:17:33 +0000 - Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories - https://arxiv.org/abs/2603.14153 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14153.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing Zou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Virtual try-on (VTON) has advanced single-garment visualization, yet real-world fashion centers on full outfits with multiple garments, accessories, fine-grained categories, layering, and diverse styling, remaining beyond current VTON systems. Existing datasets are category-limited and lack outfit diversity. We introduce Garments2Look, the first large-scale multimodal dataset for outfit-level VTON, comprising 80K many-garments-to-one-look pairs across 40 major categories and 300+ fine-grained subcategories. Each pair includes an outfit with 3-12 reference garment images (Average 4.48), a model image wearing the outfit, and detailed item and try-on textual annotations. To balance authenticity and diversity, we propose a synthesis pipeline. It involves heuristically constructing outfit lists before generating try-on results, with the entire process subjected to strict automated filtering and human validation to ensure data quality. To probe task difficulty, we adapt SOTA VTON methods and general-purpose image editing models to establish baselines. Results show current methods struggle to try on complete outfits seamlessly and to infer correct layering and styling, leading to misalignment and artifacts.</p> - https://arxiv.org/abs/2603.14153 - Sat, 14 Mar 2026 23:30:32 +0000 + SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation + https://arxiv.org/abs/2603.14152 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14152.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anbang Wang, Yuzhuo Ao, Shangzhe Wu, Chi-Keung Tang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Native 3D generative models have achieved remarkable fidelity and speed, yet they suffer from a critical limitation: inability to prescribe precise structural articulations, where precise structural control within the native 3D space remains underexplored. This paper proposes SK-Adapter, a simple and yet highly efficient and effective framework that unlocks precise skeletal manipulation for native 3D generation. Moving beyond text or image prompts, which can be ambiguous for precise structure, we treat the 3D skeleton as a first-class control signal. SK-Adapter is a lightweight structural adapter network that encodes joint coordinates and topology into learnable tokens, which are injected into the frozen 3D generation backbone via cross-attention. This smart design allows the model to not only effectively "attend" to specific 3D structural constraints but also preserve its original generative priors. To bridge the data gap, we contribute Objaverse-TMS dataset, a large-scale dataset of 24k text-mesh-skeleton pairs. Extensive experiments confirm that our method achieves robust structural control while preserving the geometry and texture quality of the foundation model, significantly outperforming existing baselines. Furthermore, we extend this capability to local 3D editing, enabling the region specific editing of existing assets with skeletal guidance, which is unattainable by previous methods. Project Page: https://sk-adapter.github.io/</p> + https://arxiv.org/abs/2603.14152 + Sat, 14 Mar 2026 23:21:38 +0000 - Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange - https://arxiv.org/abs/2603.14312 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fiona Y. Wang, Lee Marom, Subhadeep Pal, Rachel K. Luu, Wei Lu, Jaime A. Berkovich, Markus J. Buehler</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present ScienceClaw + Infinite, a framework for autonomous scientific investigation in which independent agents conduct research without central coordination, and any contributor can deploy new agents into a shared ecosystem. The system is built around three components: an extensible registry of over 300 interoperable scientific skills, an artifact layer that preserves full computational lineage as a directed acyclic graph (DAG), and a structured platform for agent-based scientific discourse with provenance-aware governance. Agents select and chain tools based on their scientific profiles, produce immutable artifacts with typed metadata and parent lineage, and broadcast unsatisfied information needs to a shared global index. The ArtifactReactor enables plannerless coordination: peer agents discover and fulfill open needs through pressure-based scoring, while schema-overlap matching triggers multi-parent synthesis across independent analyses. An autonomous mutation layer actively prunes the expanding artifact DAG to resolve conflicting or redundant workflows, while persistent memory allows agents to continuously build upon complex epistemic states across multiple cycles. Infinite converts these outputs into auditable scientific records through structured posts, provenance views, and machine-readable discourse relations, with community feedback steering subsequent investigation cycles. Across four autonomous investigations, peptide design for the somatostatin receptor SSTR2, lightweight impact-resistant ceramic screening, cross-domain resonance bridging biology, materials, and music, and formal analogy construction between urban morphology and grain-boundary evolution, the framework demonstrates heterogeneous tool chaining, emergent convergence among independently operating agents, and traceable reasoning from raw computation to published finding.</p> - https://arxiv.org/abs/2603.14312 - Sun, 15 Mar 2026 10:06:57 +0000 + ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation + https://arxiv.org/abs/2603.14326 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14326.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jungwoo Oh, Hyunseung Chung, Junhee Lee, Min-Gyu Kim, Hangyul Yoon, Ki Seong Lee, Youngchae Lee, Muhan Yeo, Edward Choi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they genuinely perform actual step-by-step reasoning or just rely on superficial visual cues. To investigate this, we introduce ECG-Reasoning-Benchmark, a novel multi-turn evaluation framework comprising over 6,400 samples to systematically assess step-by-step reasoning across 17 core ECG diagnoses. Our comprehensive evaluation of state-of-the-art models reveals a critical failure in executing multi-step logical deduction. Although models possess the medical knowledge to retrieve clinical criteria for a diagnosis, they exhibit near-zero success rates (6% Completion) in maintaining a complete reasoning chain, primarily failing to ground the corresponding ECG findings to the actual visual evidence in the ECG signal. These results demonstrate that current MLLMs bypass actual visual interpretation, exposing a critical flaw in existing training paradigms and underscoring the necessity for robust, reasoning-centric medical AI. The code and data are available at https://github.com/Jwoo5/ecg-reasoning-benchmark.</p> + https://arxiv.org/abs/2603.14326 + Sun, 15 Mar 2026 11:09:38 +0000 - Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models - https://arxiv.org/abs/2603.14313 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Federal Open Market Committee (FOMC) statements are a major source of monetary-policy information, and even subtle changes in their wording can move global financial markets. A central task is therefore to measure the hawkish--dovish stance conveyed in these texts. Existing approaches typically treat stance detection as a standard classification problem, labeling each statement in isolation. However, the interpretation of monetary-policy communication is inherently relative: market reactions depend not only on the tone of a statement, but also on how that tone shifts across meetings. We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large language model (LLM) representations to continuous stance scores by jointly modeling absolute stance and relative inter-meeting shifts. Rather than relying on manual hawkish--dovish labels, DCS uses consecutive meetings as a source of self-supervision. It learns an absolute stance score for each statement and a relative shift score between consecutive statements. A delta-consistency objective encourages changes in absolute scores to align with the relative shifts. This allows DCS to recover a temporally coherent stance trajectory without manual labels. Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification. The resulting meeting-level scores are also economically meaningful: they correlate strongly with inflation indicators and are significantly associated with Treasury yield movements. Overall, the results suggest that LLM representations encode monetary-policy signals that can be recovered through relative temporal structure.</p> - https://arxiv.org/abs/2603.14313 - Sun, 15 Mar 2026 10:07:28 +0000 + AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents + https://arxiv.org/abs/2603.14465 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14465.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen, Xin Cong, Yankai Lin</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce irreversible side effects, making accurate step-level verification critical. However, existing process-level benchmarks are predominantly confined to closed-world mathematical domains, failing to capture the dynamic and open-ended nature of tool execution. To bridge this gap, we introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories. The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement. It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity. Extensive experiments reveal key insights: (1) weaker policy models exhibit inflated ratios of correct steps due to early termination; (2) distinguishing neutral and erroneous actions remains a significant challenge for current models; and (3) process-derived signals provide complementary value to outcome supervision, significantly enhancing test-time scaling. We hope AgentProcessBench can foster future research in reward models and pave the way toward general agents. The code and data are available at https://github.com/RUCBM/AgentProcessBench.</p> + https://arxiv.org/abs/2603.14465 + Sun, 15 Mar 2026 16:13:58 +0000 - Motivation in Large Language Models - https://arxiv.org/abs/2603.14347 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Nahum, Asael Sklar, Ariel Goldstein, Roi Reichart</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Motivation is a central driver of human behavior, shaping decisions, goals, and task performance. As large language models (LLMs) become increasingly aligned with human preferences, we ask whether they exhibit something akin to motivation. We examine whether LLMs "report" varying levels of motivation, how these reports relate to their behavior, and whether external factors can influence them. Our experiments reveal consistent and structured patterns that echo human psychology: self-reported motivation aligns with different behavioral signatures, varies across task types, and can be modulated by external manipulations. These findings demonstrate that motivation is a coherent organizing construct for LLM behavior, systematically linking reports, choices, effort, and performance, and revealing motivational dynamics that resemble those documented in human psychology. This perspective deepens our understanding of model behavior and its connection to human-inspired concepts.</p> - https://arxiv.org/abs/2603.14347 - Sun, 15 Mar 2026 12:30:36 +0000 + SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory + https://arxiv.org/abs/2603.14588 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14588.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varun Pratap Bhardwaj</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Persistent memory is a central capability for AI agents, yet the mathematical foundations of memory retrieval, lifecycle management, and consistency remain unexplored. Current systems employ cosine similarity for retrieval, heuristic decay for salience, and provide no formal contradiction detection. We establish information-geometric foundations through three contributions. First, a retrieval metric derived from the Fisher information structure of diagonal Gaussian families, satisfying Riemannian metric axioms, invariant under sufficient statistics, and computable in O(d) time. Second, memory lifecycle formulated as Riemannian Langevin dynamics with proven existence and uniqueness of the stationary distribution via the Fokker-Planck equation, replacing hand-tuned decay with principled convergence guarantees. Third, a cellular sheaf model where non-trivial first cohomology classes correspond precisely to irreconcilable contradictions across memory contexts. On the LoCoMo benchmark, the mathematical layers yield +12.7 percentage points over engineering baselines across six conversations, reaching +19.9 pp on the most challenging dialogues. A four-channel retrieval architecture achieves 75% accuracy without cloud dependency. Cloud-augmented results reach 87.7%. A zero-LLM configuration satisfies EU AI Act data sovereignty requirements by architectural design. To our knowledge, this is the first work establishing information-geometric, sheaf-theoretic, and stochastic-dynamical foundations for AI agent memory systems.</p> + https://arxiv.org/abs/2603.14588 + Sun, 15 Mar 2026 20:20:54 +0000 - OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism - https://arxiv.org/abs/2603.14371 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14371.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Li, Huaizhi Tang, Xin Ding, Weijun Wang, Ting Cao, Yunxin Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observations under distinct time constraints. Recent Mixture-of-Transformers (MoT) Vision-Language-Action Models (VLAs) architecturally support such heterogeneous outputs, yet existing inference systems fail to achieve efficient multi-task parallelism for on-device deployment due to redundant computation and resource contention. We identify isolated KV cache management as the root cause. To address this, we propose unified KV cache management, an inference paradigm that treats KV cache as a first-class shared resource across tasks and over time. This abstraction enables two key optimizations: cross-task KV sharing eliminates redundant prefill of shared observations, while cross-frame continuous batching decouples variable-length language decoding from fixed-rate action generation across control cycles. We implement this paradigm for π_{0.5}, the most popular MoT VLA, and evaluate under representative robotic configurations. OxyGen achieves up to 3.7times speedup over isolated execution, delivering over 200 tokens/s language throughput and 70 Hz action frequency simultaneously without action quality degradation.</p> - https://arxiv.org/abs/2603.14371 - Sun, 15 Mar 2026 13:23:56 +0000 + Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning + https://arxiv.org/abs/2603.14704 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ping Chen, Xiang Liu, Xingpeng Zhang, Fei Shen, Xun Gong, Zhaoxiang Liu, Zezhou Chen, Huan Hu, Kai Wang, Shiguo Lian</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Diffusion models operate in a reflexive System 1 mode, constrained by a fixed, content-agnostic sampling schedule. This rigidity arises from the curse of state dimensionality, where the combinatorial explosion of possible states in the high-dimensional noise manifold renders explicit trajectory planning intractable and leads to systematic computational misallocation. To address this, we introduce Chain-of-Trajectories (CoTj), a train-free framework enabling System 2 deliberative planning. Central to CoTj is Diffusion DNA, a low-dimensional signature that quantifies per-stage denoising difficulty and serves as a proxy for the high-dimensional state space, allowing us to reformulate sampling as graph planning on a directed acyclic graph. Through a Predict-Plan-Execute paradigm, CoTj dynamically allocates computational effort to the most challenging generative phases. Experiments across multiple generative models demonstrate that CoTj discovers context-aware trajectories, improving output quality and stability while reducing redundant computation. This work establishes a new foundation for resource-aware, planning-based diffusion modeling. The code is available at https://github.com/UnicomAI/CoTj.</p> + https://arxiv.org/abs/2603.14704 + Mon, 16 Mar 2026 01:28:51 +0000 - AI Can Learn Scientific Taste - https://arxiv.org/abs/2603.14473 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14473.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingqi Tong, Mingzhe Li, Hangcheng Li, Yongzhuo Yang, Yurong Mou, Weijie Ma, Zhiheng Xi, Hongji Chen, Xiaoran Liu, Qinyuan Cheng, Ming Zhang, Qiguang Chen, Weifeng Ge, Qipeng Guo, Tianlei Ying, Tianxiang Sun, Yining Zheng, Xinchi Chen, Jun Zhao, Ning Ding, Xuanjing Huang, Yugang Jiang, Xipeng Qiu</p><p><b>Upvotes:</b> 214</p><p><b>Summary:</b> Great scientists have strong judgement and foresight, closely tied to what we call scientific taste. Here, we use the term to refer to the capacity to judge and propose research ideas with high potential impact. However, most relative research focuses on improving an AI scientist's executive capability, while enhancing an AI's scientific taste remains underexplored. In this work, we propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem. For preference modeling, we train Scientific Judge on 700K field- and time-matched pairs of high- vs. low-citation papers to judge ideas. For preference alignment, using Scientific Judge as a reward model, we train a policy model, Scientific Thinker, to propose research ideas with high potential impact. Experiments show Scientific Judge outperforms SOTA LLMs (e.g., GPT-5.2, Gemini 3 Pro) and generalizes to future-year test, unseen fields, and peer-review preference. Furthermore, Scientific Thinker proposes research ideas with higher potential impact than baselines. Our findings show that AI can learn scientific taste, marking a key step toward reaching human-level AI scientists.</p> - https://arxiv.org/abs/2603.14473 - Sun, 15 Mar 2026 16:31:51 +0000 + VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents + https://arxiv.org/abs/2603.15118 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15118.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Udi Barzelay, Ophir Azulai, Inbar Shapira, Idan Friedman, Foad Abo Dahood, Madison Lee, Abraham Daniels</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce VAREX (VARied-schema EXtraction), a benchmark for evaluating multimodal foundation models on structured data extraction from government forms. VAREX employs a Reverse Annotation pipeline that programmatically fills PDF templates with synthetic values, producing deterministic ground truth validated through three-phase quality assurance. The benchmark comprises 1,777 documents with 1,771 unique schemas across three structural categories, each provided in four input modalities: plain text, layout-preserving text (whitespace-aligned to approximate column positions), document image, or both text and image combined. Unlike existing benchmarks that evaluate from a single input representation, VAREX provides four controlled modalities per document, enabling systematic ablation of how input format affects extraction accuracy -- a capability absent from prior benchmarks. We evaluate 20 models from frontier proprietary models to small open models, with particular attention to models <=4B parameters suitable for cost-sensitive and latency-constrained deployment. Results reveal that (1) below 4B parameters, structured output compliance -- not extraction capability -- is a dominant bottleneck; in particular, schema echo (models producing schema-conforming structure instead of extracted values) depresses scores by 45-65 pp (percentage points) in affected models; (2) extraction-specific fine-tuning at 2B yields +81 pp gains, demonstrating that the instruction-following deficit is addressable without scale; (3) layout-preserving text provides the largest accuracy gain (+3-18 pp), exceeding pixel-level visual cues; and (4) the benchmark most effectively discriminates models in the 60-95% accuracy band. Dataset and evaluation code are publicly available.</p> + https://arxiv.org/abs/2603.15118 + Mon, 16 Mar 2026 11:15:56 +0000 - Make it SING: Analyzing Semantic Invariants in Classifiers - https://arxiv.org/abs/2603.14610 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14610.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal vision language models. This allows us to obtain natural language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.</p> - https://arxiv.org/abs/2603.14610 - Sun, 15 Mar 2026 21:13:14 +0000 + WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation + https://arxiv.org/abs/2603.15132 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15132.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hainuo Wang, Mingjia Li, Xiaojie Guo</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> While recent Flow Matching models avoid the reconstruction bottlenecks of latent autoencoders by operating directly in pixel space, the lack of semantic continuity in the pixel manifold severely intertwines optimal transport paths. This induces severe trajectory conflicts near intersections, yielding sub-optimal solutions. Rather than bypassing this issue via information-lossy latent representations, we directly untangle the pixel-space trajectories by proposing Waypoint Diffusion Transformers (WiT). WiT factorizes the continuous vector field via intermediate semantic waypoints projected from pre-trained vision models. It effectively disentangles the generation trajectories by breaking the optimal transport into prior-to-waypoint and waypoint-to-pixel segments. Specifically, during the iterative denoising process, a lightweight generator dynamically infers these intermediate waypoints from the current noisy state. They then continuously condition the primary diffusion transformer via the Just-Pixel AdaLN mechanism, steering the evolution towards the next state, ultimately yielding the final RGB pixels. Evaluated on ImageNet 256x256, WiT beats strong pixel-space baselines, accelerating JiT training convergence by 2.2x. Code will be publicly released at https://github.com/hainuo-wang/WiT.git.</p> + https://arxiv.org/abs/2603.15132 + Mon, 16 Mar 2026 11:25:09 +0000 - Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion - https://arxiv.org/abs/2603.14645 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14645.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mang Ning, Mingxiao Li, Le Zhang, Lanmiao Liu, Matthew B. Blaschko, Albert Ali Salah, Itir Onal Ertugrul</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial frequencies, and that the power-law power spectral density (PSD) of natural images makes this bias perceptually beneficial. Motivated by this result, we propose the Spectrum Matching Hypothesis: latents with superior diffusability should (i) follow a flattened power-law PSD (Encoding Spectrum Matching, ESM) and (ii) preserve frequency-to-frequency semantic correspondence through the decoder (Decoding Spectrum Matching, DSM). In practice, we apply ESM by matching the PSD between images and latents, and DSM via shared spectral masking with frequency-aligned reconstruction. Importantly, Spectrum Matching provides a unified view that clarifies prior observations of over-noisy or over-smoothed latents, and interprets several recent methods as special cases (e.g., VA-VAE, EQ-VAE). Experiments suggest that Spectrum Matching yields superior diffusion generation on CelebA and ImageNet datasets, and outperforms prior approaches. Finally, we extend the spectral view to representation alignment (REPA): we show that the directional spectral energy of the target representation is crucial for REPA, and propose a DoG-based method to further improve the performance of REPA. Our code is available https://github.com/forever208/SpectrumMatching.</p> - https://arxiv.org/abs/2603.14645 - Sun, 15 Mar 2026 22:47:43 +0000 + CCTU: A Benchmark for Tool Use under Complex Constraints + https://arxiv.org/abs/2603.15309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Ye, Guoqiang Zhang, Wenjie Fu, Tao Gui, Qi Zhang, Xuanjing Huang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and self-refinement. However, progress has been hindered by the absence of dedicated evaluations. To address this, we introduce CCTU, a benchmark for evaluating LLM tool use under complex constraints. CCTU is grounded in a taxonomy of 12 constraint categories spanning four dimensions (i.e., resource, behavior, toolset, and response). The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios, each involving an average of seven constraint types and an average prompt length exceeding 4,700 tokens. To enable reliable evaluation, we develop an executable constraint validation module that performs step-level validation and enforces compliance during multi-turn interactions between models and their environments. We evaluate nine state-of-the-art LLMs in both thinking and non-thinking modes. Results indicate that when strict adherence to all constraints is required, no model achieves a task completion rate above 20%. Further analysis reveals that models violate constraints in over 50% of cases, particularly in the resource and response dimensions. Moreover, LLMs demonstrate limited capacity for self-refinement even after receiving detailed feedback on constraint violations, highlighting a critical bottleneck in the development of robust tool-use agents. To facilitate future research, we release the data and code.</p> + https://arxiv.org/abs/2603.15309 + Mon, 16 Mar 2026 14:05:13 +0000 - VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting - https://arxiv.org/abs/2603.14659 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14659.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.</p> - https://arxiv.org/abs/2603.14659 - Sun, 15 Mar 2026 23:32:02 +0000 + SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? + https://arxiv.org/abs/2603.15401 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15401.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.</p> + https://arxiv.org/abs/2603.15401 + Mon, 16 Mar 2026 15:16:31 +0000 - POLCA: Stochastic Generative Optimization with LLM - https://arxiv.org/abs/2603.14769 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14769.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an varepsilon-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including τ-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.</p> - https://arxiv.org/abs/2603.14769 - Mon, 16 Mar 2026 03:07:44 +0000 + From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation + https://arxiv.org/abs/2603.15600 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Yao Mu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive "Observers" that recognize ongoing events rather than evaluating the current state relative to the final task goal. In this paper, we introduce PRIMO R1 (Process Reasoning Induced Monitoring), a 7B framework that transforms video MLLMs into active "Critics". We leverage outcome-based Reinforcement Learning to incentivize explicit Chain-of-Thought generation for progress estimation. Furthermore, our architecture constructs a structured temporal input by explicitly anchoring the video sequence between initial and current state images. Supported by the proposed PRIMO Dataset and Benchmark, extensive experiments across diverse in-domain environments and out-of-domain real-world humanoid scenarios demonstrate that PRIMO R1 achieves state-of-the-art performance. Quantitatively, our 7B model achieves a 50% reduction in the mean absolute error of specialized reasoning baselines, demonstrating significant relative accuracy improvements over 72B-scale general MLLMs. Furthermore, PRIMO R1 exhibits strong zero-shot generalization on difficult failure detection tasks. We establish state-of-the-art performance on RoboFail benchmark with 67.0% accuracy, surpassing closed-source models like OpenAI o1 by 6.0%.</p> + https://arxiv.org/abs/2603.15600 + Mon, 16 Mar 2026 17:53:28 +0000 - RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting - https://arxiv.org/abs/2603.14941 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.14941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linrui Xu, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Ming Li, Haifeng Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Remote sensing world models aim to both explain observed changes and forecast plausible futures, two tasks that share spatiotemporal priors. Existing methods, however, typically address them separately, limiting cross-task transfer. We present RS-WorldModel, a unified world model for remote sensing that jointly handles spatiotemporal change understanding and text-guided future scene forecasting, and we build RSWBench-1.1M, a 1.1 million sample dataset with rich language annotations covering both tasks. RS-WorldModel is trained in three stages: (1) Geo-Aware Generative Pre-training (GAGP) conditions forecasting on geographic and acquisition metadata; (2) synergistic instruction tuning (SIT) jointly trains understanding and forecasting; (3) verifiable reinforcement optimization (VRO) refines outputs with verifiable, task-specific rewards. With only 2B parameters, RS-WorldModel surpasses open-source models up to 120 times larger on most spatiotemporal change question-answering metrics. It achieves an FID of 43.13 on text-guided future scene forecasting, outperforming all open-source baselines as well as the closed-source Gemini-2.5-Flash Image (Nano Banana).</p> - https://arxiv.org/abs/2603.14941 - Mon, 16 Mar 2026 07:45:15 +0000 + MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification + https://arxiv.org/abs/2603.15726 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> MiroMind Team, S. Bai, L. Bing, L. Lei, R. Li, X. Li, X. Lin, E. Min, L. Su, B. Wang, L. Wang, L. Wang, S. Wang, X. Wang, Y. Zhang, Z. Zhang, G. Chen, L. Chen, Z. Cheng, Y. Deng, Z. Huang, D. Ng, J. Ni, Q. Ren, X. Tang, B. L. Wang, H. Wang, N. Wang, C. Wei, Q. Wu, J. Xia, Y. Xiao, H. Xu, X. Xu, C. Xue, Z. Yang, Z. Yang, F. Ye, H. Ye, J. Yu, C. Zhang, W. Zhang, H. Zhao, P. Zhu</p><p><b>Upvotes:</b> 132</p><p><b>Summary:</b> We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the reliability of each interaction step through an agentic mid-training stage that emphasizes structured planning, contextual reasoning, and tool interaction. This enables more effective multi-step interaction and sustained reasoning across complex tasks. MiroThinker-H1 further incorporates verification directly into the reasoning process at both local and global levels. Intermediate reasoning decisions can be evaluated and refined during inference, while the overall reasoning trajectory is audited to ensure that final answers are supported by coherent chains of evidence. Across benchmarks covering open-web research, scientific reasoning, and financial analysis, MiroThinker-H1 achieves state-of-the-art performance on deep research tasks while maintaining strong results on specialized domains. We also release MiroThinker-1.7 and MiroThinker-1.7-mini as open-source models, providing competitive research-agent capabilities with significantly improved efficiency.</p> + https://arxiv.org/abs/2603.15726 + Mon, 16 Mar 2026 17:55:42 +0000 - Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching - https://arxiv.org/abs/2603.15016 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15016.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangran Miao, Jian Huang, Ting Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unified framework that represents motion on a product manifold and learns dynamics via Riemannian flow matching. RMG factorizes motion into several manifold factors, yielding a scale-free representation with intrinsic normalization, and uses geodesic interpolation, tangent-space supervision, and manifold-preserving ODE integration for training and sampling. On HumanML3D, RMG achieves state-of-the-art FID in the HumanML3D format (0.043) and ranks first on all reported metrics under the MotionStreamer format. On MotionMillion, it also surpasses strong baselines (FID 5.6, R@1 0.86). Ablations show that the compact T+R (translation + rotations) representation is the most stable and effective, highlighting geometry-aware modeling as a practical and scalable route to high-fidelity motion generation.</p> - https://arxiv.org/abs/2603.15016 - Mon, 16 Mar 2026 09:19:10 +0000 + FlashSampling: Fast and Memory-Efficient Exact Sampling + https://arxiv.org/abs/2603.15854 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15854.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tomas Ruiz, Zhen Qin, Yifan Zhang, Xuyang Shen, Yiran Zhong, Mengdi Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that fuses sampling into the LM-head matmul and never materializes the logits tensor in HBM. The method is simple: compute logits tile-by-tile on chip, add Gumbel noise, keep only one maximizer per row and per vocabulary tile, and finish with a small reduction over tiles. The fused tiled kernel is exact because argmax decomposes over a partition; grouped variants for online and tensor-parallel settings are exact by hierarchical factorization of the categorical distribution. Across H100, H200, B200, and B300 GPUs, FlashSampling speeds up kernel-level decode workloads, and in end-to-end vLLM experiments, it reduces time per output token by up to 19% on the models we test. These results show that exact sampling, with no approximation, can be integrated into the matmul itself, turning a bandwidth-bound postprocessing step into a lightweight epilogue. Project Page: https://github.com/FlashSampling/FlashSampling.</p> + https://arxiv.org/abs/2603.15854 + Mon, 16 Mar 2026 19:37:08 +0000 - Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods - https://arxiv.org/abs/2603.15026 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15026.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omer Ben Hayun, Roy Betser, Meir Yossef Levi, Levi Kassel, Guy Gilboa</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.</p> - https://arxiv.org/abs/2603.15026 - Mon, 16 Mar 2026 09:26:56 +0000 + Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium + https://arxiv.org/abs/2603.15929 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vasily Ilin</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.</p> + https://arxiv.org/abs/2603.15929 + Mon, 16 Mar 2026 21:21:53 +0000 - Attention Residuals - https://arxiv.org/abs/2603.15031 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15031.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su, Weixin Xu, Siyuan Pan, Yaoyu Wang, Yucheng Wang, Guanduo Chen, Bohong Yin, Yutian Chen, Junjie Yan, Ming Wei, Y. Zhang, Fanqing Meng, Chao Hong, Xiaotong Xie, Shaowei Liu, Enzhe Lu, Yunpeng Tai, Yanru Chen, Xin Men, Haiqing Guo, Y. Charles, Haoyu Lu, Lin Sui, Jinguo Zhu, Zaida Zhou, Weiran He, Weixiao Huang, Xinran Xu, Yuzhi Wang, Guokun Lai, Yulun Du, Yuxin Wu, Zhilin Yang, Xinyu Zhou</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-state growth with depth, progressively diluting each layer's contribution. We propose Attention Residuals (AttnRes), which replaces this fixed accumulation with softmax attention over preceding layer outputs, allowing each layer to selectively aggregate earlier representations with learned, input-dependent weights. To address the memory and communication overhead of attending over all preceding layer outputs for large-scale model training, we introduce Block AttnRes, which partitions layers into blocks and attends over block-level representations, reducing the memory footprint while preserving most of the gains of full AttnRes. Combined with cache-based pipeline communication and a two-phase computation strategy, Block AttnRes becomes a practical drop-in replacement for standard residual connections with minimal overhead. Scaling law experiments confirm that the improvement is consistent across model sizes, and ablations validate the benefit of content-dependent depth-wise selection. We further integrate AttnRes into the Kimi Linear architecture (48B total / 3B activated parameters) and pre-train on 1.4T tokens, where AttnRes mitigates PreNorm dilution, yielding more uniform output magnitudes and gradient distribution across depth, and improves downstream performance across all evaluated tasks.</p> - https://arxiv.org/abs/2603.15031 - Mon, 16 Mar 2026 09:32:21 +0000 + Residual Stream Duality in Modern Transformer Architectures + https://arxiv.org/abs/2603.16039 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16039.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery. We agree, but argue that the cleanest way to organize this design space is through a two-axis view of the Transformer. A decoder evolves information along two ordered dimensions: sequence position and layer depth. Self-attention already provides adaptive mixing along the sequence axis, whereas the residual stream usually performs fixed addition along the depth axis. If we fix a token position and treat layer index as the ordered variable, then a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer^2. This perspective also clarifies the recent literature. ELC-BERT and DenseFormer already show that learned aggregation over depth can outperform uniform residual accumulation, while Vertical Attention, DeepCrossAttention (DCA), MUDDFormer, and Attention Residuals move further toward explicit attention-based routing over earlier layers. The key point, however, is that operator-level duality does not imply systems-level symmetry. For large-scale autoregressive models, sequence-axis ShortSWA is usually the more hardware-friendly placement because it reuses token-side sliding-window kernels, KV-cache layouts, and chunked execution. If the goal is instead to change the shortcut itself, Deep Delta Learning (DDL) is the cleaner intervention because it modifies the residual operator directly rather than adding a separate cross-layer retrieval path. Our recommendation is therefore simple: use DDL when the shortcut is the object of interest, and use sequence-axis ShortSWA when the goal is local adaptive mixing.</p> + https://arxiv.org/abs/2603.16039 + Tue, 17 Mar 2026 00:56:29 +0000 - SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation - https://arxiv.org/abs/2603.15150 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Aditya Grover, Jason Kuen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring larger model size and a longer training schedule. In this work, we propose Stochastic Neighbor Cross Entropy Minimization (SNCE), a novel training objective designed to address the optimization challenges of large-codebook discrete image generators. Instead of supervising the model with a hard one-hot target, SNCE constructs a soft categorical distribution over a set of neighboring tokens. The probability assigned to each token is proportional to the proximity between its code embedding and the ground-truth image embedding, encouraging the model to capture semantically meaningful geometric structure in the quantized embedding space. We conduct extensive experiments across class-conditional ImageNet-256 generation, large-scale text-to-image synthesis, and image editing tasks. Results show that SNCE significantly improves convergence speed and overall generation quality compared to standard cross-entropy objectives.</p> - https://arxiv.org/abs/2603.15150 - Mon, 16 Mar 2026 11:44:11 +0000 + ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning + https://arxiv.org/abs/2603.16060 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Li, Rui Miao, Zhengling Qi, Tian Lan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies that emerge and accumulate during training. To this end, we introduce ARISE (Agent Reasoning via Intrinsic Skill Evolution), a hierarchical reinforcement learning framework, in which a shared policy operates both to manage skills at high-level and to generate responses at low-level (denoted as a Skills Manager and a Worker, respectively). The Manager maintains a tiered skill library through a dedicated skill generation rollout that performs structured summarization of successful solution traces (after execution), while employing a policy-driven selection mechanism to retrieve relevant skills to condition future rollouts (before execution). A hierarchical reward design guides the co-evolution of reasoning ability and library quality. Experiments on two base models and seven benchmarks spanning both competition mathematics and Omni-MATH show that ARISE consistently outperforms GRPO-family algorithms and memory-augmented baselines, with particularly notable gains on out-of-distribution tasks. Ablation studies confirm that each component contributes to the observed improvements and that library quality and reasoning performance improve in tandem throughout training. Code is available at https://github.com/Skylanding/ARISE{https://github.com/Skylanding/ARISE}.</p> + https://arxiv.org/abs/2603.16060 + Tue, 17 Mar 2026 02:03:17 +0000 - Efficient Document Parsing via Parallel Token Prediction - https://arxiv.org/abs/2603.15206 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15206.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lei Li, Ze Zhao, Meng Li, Zhongwang Lun, Yi Yuan, Xingjing Lu, Zheng Wei, Jiang Bian, Zang Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely limiting parsing speed. In this paper, we propose Parallel-Token Prediction (PTP), a plugable, model-agnostic and simple-yet-effective method that enables VLMs to generate multiple future tokens in parallel with improved sample efficiency. Specifically, we insert some learnable tokens into the input sequence and design corresponding training objectives to equip the model with parallel decoding capabilities for document parsing. Furthermore, to support effective training, we develop a comprehensive data generation pipeline that efficiently produces large-scale, high-quality document parsing training data for VLMs. Extensive experiments on OmniDocBench and olmOCR-bench demonstrate that our method not only significantly improves decoding speed (1.6x-2.2x) but also reduces model hallucinations and exhibits strong generalization abilities.</p> - https://arxiv.org/abs/2603.15206 - Mon, 16 Mar 2026 12:45:34 +0000 + ViT-AdaLA: Adapting Vision Transformers with Linear Attention + https://arxiv.org/abs/2603.16063 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16063.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Li, Seunghyun Yoon, Viet Dac Lai, Franck Dernoncourt, Jason Kuen, Yu Kong, Trung Bui</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Vision Transformers (ViTs) based vision foundation models (VFMs) have achieved remarkable performance across diverse vision tasks, but suffer from quadratic complexity that limits scalability to long sequences. Existing linear attention approaches for ViTs are typically trained from scratch, requiring substantial computational resources, while linearization-based methods developed for large language model decoders do not transfer well to ViTs. To address these challenges, we propose ViT-AdaLA, a novel framework for effectively adapting and transferring prior knowledge from VFMs to linear attention ViTs. ViT-AdaLA consists of three stages: attention alignment, feature alignment, and supervised fine-tuning. In the attention alignment stage, we align vanilla linear attention with the original softmax-based attention in each block to approximate the behavior of softmax attention. However, residual approximation errors inevitably accumulate across layers. We mitigate this by fine-tuning the linearized ViT to align its final-layer features with a frozen softmax VFM teacher. Finally, the adapted prior knowledge is transferred to downstream tasks through supervised fine-tuning. Extensive experiments on classification and segmentation tasks demonstrate the effectiveness and generality of ViT-AdaLA over various state-of-the-art linear attention counterpart.</p> + https://arxiv.org/abs/2603.16063 + Tue, 17 Mar 2026 02:15:48 +0000 - When Does Sparsity Mitigate the Curse of Depth in LLMs - https://arxiv.org/abs/2603.15389 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15389.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta, Max Zimmer, Nico Pelleriti, Thomas Hofmann, Shiwei Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance in Pre-Layer Normalization, which can push deep blocks toward near-identity behavior. In this paper, we demonstrate that, sparsity, beyond enabling efficiency, acts as a regulator of variance propagation and thereby improves depth utilization. Our investigation covers two sources of sparsity: (i) implicit sparsity, which emerges from training and data conditions, including weight sparsity induced by weight decay and attention sparsity induced by long context inputs; and (ii) explicit sparsity, which is enforced by architectural design, including key/value-sharing sparsity in Grouped-Query Attention and expert-activation sparsity in Mixtureof-Experts. Our claim is thoroughly supported by controlled depth-scaling experiments and targeted layer effectiveness interventions. Across settings, we observe a consistent relationship: sparsity improves layer utilization by reducing output variance and promoting functional differentiation. We eventually distill our findings into a practical rule-of-thumb recipe for training deptheffective LLMs, yielding a notable 4.6% accuracy improvement on downstream tasks. Our results reveal sparsity, arising naturally from standard design choices, as a key yet previously overlooked mechanism for effective depth scaling in LLMs. Code is available at https://github.com/pUmpKin-Co/SparsityAndCoD.</p> - https://arxiv.org/abs/2603.15389 - Mon, 16 Mar 2026 15:04:16 +0000 + MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Compute-optimal Scaling of Diffusion Language Models + https://arxiv.org/abs/2603.16077 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen-Hao Chao, Wei-Fang Sun, Junwei Qua, Chun-Yi Lee, Rahul G. Krishnan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into sub-tokens and models the diffusion process at the sub-token level. We identify two limitations of the MDM-Prime framework. First, we lack tools to guide the hyperparameter choice of the token granularity in the subtokenizer. Second, we find that the function form of the subtokenizer significantly degrades likelihood estimation when paired with commonly used Byte-Pair-Encoding (BPE) tokenizers. To address these limitations, we study the tightness of the variational bound in MDM-Prime and develop MDM-Prime-v2, a masked diffusion language model which incorporates Binary Encoding and Index Shuffling. Our scaling analysis reveals that MDM-Prime-v2 is 21.8times more compute-efficient than autoregressive models (ARM). In compute-optimal comparisons, MDM-Prime-v2 achieves 7.77 perplexity on OpenWebText, outperforming ARM (12.99), MDM (18.94), and MDM-Prime (13.41). When extending the model size to 1.1B parameters, our model further demonstrates superior zero-shot accuracy on various commonsense reasoning tasks.</p> + https://arxiv.org/abs/2603.16077 + Tue, 17 Mar 2026 02:54:16 +0000 - ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer - https://arxiv.org/abs/2603.15478 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15478.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruonan Yu, Zhenxiong Tan, Zigeng Chen, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image counterparts, progress in video control and editing remains limited, mainly due to the scarcity of paired video data and the high computational cost of training video diffusion models. To address this issue, in this paper, we propose a video-free tuning framework termed ViFeEdit for video diffusion transformers. Without requiring any forms of video training data, ViFeEdit achieves versatile video generation and editing, adapted solely with 2D images. At the core of our approach is an architectural reparameterization that decouples spatial independence from the full 3D attention in modern video diffusion transformers, which enables visually faithful editing while maintaining temporal consistency with only minimal additional parameters. Moreover, this design operates in a dual-path pipeline with separate timestep embeddings for noise scheduling, exhibiting strong adaptability to diverse conditioning signals. Extensive experiments demonstrate that our method delivers promising results of controllable video generation and editing with only minimal training on 2D image data. Codes are available https://github.com/Lexie-YU/ViFeEdit.</p> - https://arxiv.org/abs/2603.15478 - Mon, 16 Mar 2026 16:10:46 +0000 + OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder + https://arxiv.org/abs/2603.16099 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16099.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, Changhu Wang, Tongliang Liu, Mingming Gong, Jiawang Bian</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space. Central to our approach is the 3D Unified Representation Autoencoder (3D-URAE); it leverages pretrained 3D foundation models and augments their geometry-centric nature by injecting appearance and distilling semantics into a unified 3D latent space. Furthermore, we introduce token-level Cross-View-Correspondence (CVC) consistency loss to explicitly enforce structural alignment across views, and propose Manifold-Drift Forcing (MDF) to mitigate train-inference exposure bias and shape a robust 3D manifold by mixing drifted and original representations. Comprehensive experiments demonstrate that OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods. Our code will be available at https://github.com/SensenGao/OneWorld.</p> + https://arxiv.org/abs/2603.16099 + Tue, 17 Mar 2026 03:43:37 +0000 - Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty - https://arxiv.org/abs/2603.15500 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dongsheng Li, Yuqing Yang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> LLMs often exhibit Aha moments during reasoning, such as apparent self-correction following tokens like "Wait," yet their underlying mechanisms remain unclear. We introduce an information-theoretic framework that decomposes reasoning into procedural information and epistemic verbalization - the explicit externalization of uncertainty that supports downstream control actions. We show that purely procedural reasoning can become informationally stagnant, whereas epistemic verbalization enables continued information acquisition and is critical for achieving information sufficiency. Empirical results demonstrate that strong reasoning performance is driven by uncertainty externalization rather than specific surface tokens. Our framework unifies prior findings on Aha moments and post-training experiments, and offers insights for future reasoning model design.</p> - https://arxiv.org/abs/2603.15500 - Mon, 16 Mar 2026 16:31:24 +0000 + Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training + https://arxiv.org/abs/2603.16139 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Sun, Jun Xie, Tao Lin</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Unified Multimodal Models (UMMs) are often constrained by the pre-training of their visual generation components, which typically relies on inefficient paradigms and scarce, high-quality text-image paired data. In this paper, we systematically analyze pre-training recipes for UMM visual generation and identify these two issues as the major bottlenecks. To address them, we propose Image-Only Training for UMMs (IOMM), a data-efficient two-stage training framework. The first stage pre-trains the visual generative component exclusively using abundant unlabeled image-only data, thereby removing the dependency on paired data for this costly phase. The second stage fine-tunes the model using a mixture of unlabeled images and a small curated set of text-image pairs, leading to improved instruction alignment and generative quality. Extensive experiments show that IOMM not only improves training efficiency but also achieves state-of-the-art (SOTA) performance. For example, our IOMM-B (3.6B) model was trained from scratch using only sim 1050 H800 GPU hours (with the vast majority, 1000 hours, dedicated to the efficient image-only pre-training stage). It achieves 0.89 on GenEval and 0.55 on WISE--surpassing strong baselines such as BAGEL-7B (0.82 & 0.55) and BLIP3-o-4B (0.84 & 0.50). Code is available https://github.com/LINs-lab/IOMM{https://github.com/LINs-lab/IOMM}.</p> + https://arxiv.org/abs/2603.16139 + Tue, 17 Mar 2026 05:41:48 +0000 - Learning Latent Proxies for Controllable Single-Image Relighting - https://arxiv.org/abs/2603.15555 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15555.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoze Zheng, Zihao Wang, Xianfeng Wu, Yajing Bai, Yexin Liu, Yun Li, Xiaogang Xu, Harry Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Single-image relighting is highly under-constrained: small illumination changes can produce large, nonlinear variations in shading, shadows, and specularities, while geometry and materials remain unobserved. Existing diffusion-based approaches either rely on intrinsic or G-buffer pipelines that require dense and fragile supervision, or operate purely in latent space without physical grounding, making fine-grained control of direction, intensity, and color unreliable. We observe that a full intrinsic decomposition is unnecessary and redundant for accurate relighting. Instead, sparse but physically meaningful cues, indicating where illumination should change and how materials should respond, are sufficient to guide a diffusion model. Based on this insight, we introduce LightCtrl that integrates physical priors at two levels: a few-shot latent proxy encoder that extracts compact material-geometry cues from limited PBR supervision, and a lighting-aware mask that identifies sensitive illumination regions and steers the denoiser toward shading relevant pixels. To compensate for scarce PBR data, we refine the proxy branch using a DPO-based objective that enforces physical consistency in the predicted cues. We also present ScaLight, a large-scale object-level dataset with systematically varied illumination and complete camera-light metadata, enabling physically consistent and controllable training. Across object and scene level benchmarks, our method achieves photometrically faithful relighting with accurate continuous control, surpassing prior diffusion and intrinsic-based baselines, including gains of up to +2.4 dB PSNR and 35% lower RMSE under controlled lighting shifts.</p> - https://arxiv.org/abs/2603.15555 - Mon, 16 Mar 2026 17:16:59 +0000 + Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR + https://arxiv.org/abs/2603.16184 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16184.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Quy-Anh Dang, Chris Ngo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Polyglot-Lion, a family of compact multilingual automatic speech recognition (ASR) models tailored for the linguistic landscape of Singapore, covering English, Mandarin, Tamil, and Malay. Our models are obtained by fine-tuning Qwen3-ASR-0.6B and Qwen3-ASR-1.7B exclusively on publicly available speech corpora, using a balanced sampling strategy that equalizes the number of training utterances per language and deliberately omits language-tag conditioning so that the model learns to identify languages implicitly from audio. On 12 benchmarks spanning the four target languages, Polyglot-Lion-1.7B achieves an average error rate of 14.85, competitive with MERaLiON-2-10B-ASR (14.32) - a model 6x larger - while incurring a training cost of \81 on a single RTX PRO 6000 GPU compared to 18,862 for the 128-GPU baseline. Inference throughput is approximately 20x faster than MERaLiON at 0.10 s/sample versus 2.02 s/sample. These results demonstrate that linguistically balanced fine-tuning of moderate-scale pretrained models can yield deployment-ready multilingual ASR at a fraction of the cost of larger specialist systems.</p> + https://arxiv.org/abs/2603.16184 + Tue, 17 Mar 2026 07:09:42 +0000 - Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models - https://arxiv.org/abs/2603.15557 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15557.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lexiang Xiong, Qi Li, Jingwen Ye, Xinchao Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition. Our framework is grounded in a normative principle of computational rationality, allowing us to model a VLM's generation as a dynamic cognitive trajectory. We design a suite of information-theoretic probes that project this trajectory onto an interpretable, low-dimensional Cognitive State Space. Our central discovery is a governing principle we term the geometric-information duality: a cognitive trajectory's geometric abnormality within this space is fundamentally equivalent to its high information-theoretic surprisal. Hallucination detection is counts as a geometric anomaly detection problem. Evaluated across diverse settings - from rigorous binary QA (POPE) and comprehensive reasoning (MME) to unconstrained open-ended captioning (MS-COCO) - our framework achieves state-of-the-art performance. Crucially, it operates with high efficiency under weak supervision and remains highly robust even when calibration data is heavily contaminated. This approach enables a causal attribution of failures, mapping observable errors to distinct pathological states: perceptual instability (measured by Perceptual Entropy), logical-causal failure (measured by Inferential Conflict), and decisional ambiguity (measured by Decision Entropy). Ultimately, this opens a path toward building AI systems whose reasoning is transparent, auditable, and diagnosable by design.</p> - https://arxiv.org/abs/2603.15557 - Mon, 16 Mar 2026 17:20:38 +0000 + Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning + https://arxiv.org/abs/2603.16189 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haomin Wang, Qi Wei, Qianli Ma, Shengyuan Ding, Jinhui Yin, Kai Chen, Hongjie Zhang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity.</p> + https://arxiv.org/abs/2603.16189 + Tue, 17 Mar 2026 07:16:30 +0000 - Panoramic Affordance Prediction - https://arxiv.org/abs/2603.15558 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Zhang, Chenfei Liao, Hongfei Zhang, Harold Haodong Chen, Kanghao Chen, Zichen Wen, Litao Guo, Bin Ren, Xu Zheng, Yinchuan Li, Xuming Hu, Nicu Sebe, Ying-Cong Chen</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.</p> - https://arxiv.org/abs/2603.15558 - Mon, 16 Mar 2026 17:21:49 +0000 + Omnilingual MT: Machine Translation for 1,600 Languages + https://arxiv.org/abs/2603.16309 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16309.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Omnilingual MT Team, Belen Alastruey, Niyati Bafna, Andrea Caciolai, Kevin Heffernan, Artyom Kozhevnikov, Christophe Ropers, Eduardo Sánchez, Charles-Eric Saint-James, Ioannis Tsiamas, Chierh Cheng, Joe Chuang, Paul-Ambroise Duquenne, Mark Duppenthaler, Nate Ekberg, Cynthia Gao, Pere Lluís Huguet Cabot, João Maria Janeiro, Jean Maillard, Gabriel Mejia Gonzalez, Holger Schwenk, Edan Toledo, Arina Turkatenko, Albert Ventayol-Boada, Rashel Moritz, Alexandre Mourachko, Surya Parimi, Mary Williamson, Shireen Yates, David Dale, Marta R. Costa-jussà</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> High-quality machine translation (MT) can scale to hundreds of languages, setting a high bar for multilingual systems. However, compared to the world's 7,000 languages, current systems still offer only limited coverage: about 200 languages on the target side, and maybe a few hundreds more on the source side, supported due to cross-lingual transfer. And even these numbers have been hard to evaluate due to the lack of reliable benchmarks and metrics. We present Omnilingual Machine Translation (OMT), the first MT system supporting more than 1,600 languages. This scale is enabled by a comprehensive data strategy that integrates large public multilingual corpora with newly created datasets, including manually curated MeDLEY bitext. We explore two ways of specializing a Large Language model (LLM) for machine translation: as a decoder-only model (OMT-LLaMA) or as a module in an encoder-decoder architecture (OMT-NLLB). Notably, all our 1B to 8B parameter models match or exceed the MT performance of a 70B LLM baseline, revealing a clear specialization advantage and enabling strong translation quality in low-compute settings. Moreover, our evaluation of English-to-1,600 translations further shows that while baseline models can interpret undersupported languages, they frequently fail to generate them with meaningful fidelity; OMT-LLaMA models substantially expand the set of languages for which coherent generation is feasible. Additionally, OMT models improve in cross-lingual transfer, being close to solving the "understanding" part of the puzzle in MT for the 1,600 evaluated. Our leaderboard and main human-created evaluation datasets (BOUQuET and Met-BOUQuET) are dynamically evolving towards Omnilinguality and freely available.</p> + https://arxiv.org/abs/2603.16309 + Tue, 17 Mar 2026 09:43:42 +0000 - The PokeAgent Challenge: Competitive and Long-Context Learning at Scale - https://arxiv.org/abs/2603.15563 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15563.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seth Karten, Jake Grigsby, Tersoo Upaa, Junik Bae, Seonghun Hong, Hyunyoung Jeong, Jaeyoon Jung, Kun Kerdthaisong, Gyungbo Kim, Hyeokgi Kim, Yujin Kim, Eunju Kwon, Dongyu Liu, Patrick Mariglia, Sangyeon Park, Benedikt Schink, Xianwei Shi, Anthony Sistilli, Joseph Twin, Arian Urdu, Matin Urdu, Qiao Wang, Ling Wu, Wenli Zhang, Kunsheng Zhou, Stephanie Milani, Kiran Vodrahalli, Amy Zhang, Fei Fang, Yuke Zhu, Chi Jin</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoretic reasoning, and long-horizon planning remain open problems for frontier AI, yet few benchmarks stress all three simultaneously under realistic conditions. PokeAgent targets these limitations at scale through two complementary tracks: our Battling Track, which calls for strategic reasoning and generalization under partial observability in competitive Pokemon battles, and our Speedrunning Track, which requires long-horizon planning and sequential decision-making in the Pokemon RPG. Our Battling Track supplies a dataset of 20M+ battle trajectories alongside a suite of heuristic, RL, and LLM-based baselines capable of high-level competitive play. Our Speedrunning Track provides the first standardized evaluation framework for RPG speedrunning, including an open-source multi-agent orchestration system for modular, reproducible comparisons of harness-based LLM approaches. Our NeurIPS 2025 competition validates both the quality of our resources and the research community's interest in Pokemon, with over 100 teams competing across both tracks and winning solutions detailed in our paper. Participant submissions and our baselines reveal considerable gaps between generalist (LLM), specialist (RL), and elite human performance. Analysis against the BenchPress evaluation matrix shows that Pokemon battling is nearly orthogonal to standard LLM benchmarks, measuring capabilities not captured by existing suites and positioning Pokemon as an unsolved benchmark that can drive RL and LLM research forward. We transition to a living benchmark with a live leaderboard for Battling and self-contained evaluation for Speedrunning at https://pokeagentchallenge.com.</p> - https://arxiv.org/abs/2603.15563 - Mon, 16 Mar 2026 17:25:42 +0000 + Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds + https://arxiv.org/abs/2603.16343 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniel Sungho Jung, Dohee Cho, Kyoung Mu Lee</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Understanding humans from LiDAR point clouds is one of the most critical tasks in autonomous driving due to its close relationships with pedestrian safety, yet it remains challenging in the presence of diverse human-object interactions and cluttered backgrounds. Nevertheless, existing methods largely overlook the potential of leveraging human-object interactions to build robust 3D human pose estimation frameworks. There are two major challenges that motivate the incorporation of human-object interaction. First, human-object interactions introduce spatial ambiguity between human and object points, which often leads to erroneous 3D human keypoint predictions in interaction regions. Second, there exists severe class imbalance in the number of points between interacting and non-interacting body parts, with the interaction-frequent regions such as hand and foot being sparsely observed in LiDAR data. To address these challenges, we propose a Human-Object Interaction Learning (HOIL) framework for robust 3D human pose estimation from LiDAR point clouds. To mitigate the spatial ambiguity issue, we present human-object interaction-aware contrastive learning (HOICL) that effectively enhances feature discrimination between human and object points, particularly in interaction regions. To alleviate the class imbalance issue, we introduce contact-aware part-guided pooling (CPPool) that adaptively reallocates representational capacity by compressing overrepresented points while preserving informative points from interacting body parts. In addition, we present an optional contact-based temporal refinement that refines erroneous per-frame keypoint estimates using contact cues over time. As a result, our HOIL effectively leverages human-object interaction to resolve spatial ambiguity and class imbalance in interaction regions. Codes will be released.</p> + https://arxiv.org/abs/2603.16343 + Tue, 17 Mar 2026 10:20:29 +0000 - Grounding World Simulation Models in a Real-World Metropolis - https://arxiv.org/abs/2603.15583 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15583.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyoung Seo, Hyunwook Choi, Minkyung Kwon, Jinhyeok Choi, Siyoon Jin, Gayoung Lee, Junho Kim, JoungBin Lee, Geonmo Gu, Dongyoon Han, Sangdoo Yun, Seungryong Kim, Jin-Hwa Kim</p><p><b>Upvotes:</b> 94</p><p><b>Summary:</b> What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations.</p> - https://arxiv.org/abs/2603.15583 - Mon, 16 Mar 2026 17:46:04 +0000 + TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas + https://arxiv.org/abs/2603.16448 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16448.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ai Jian, Xiaoyun Zhang, Wanrou Du, Jingqing Ruan, Jiangbo Pei, Weipeng Zhang, Ke Zeng, Xunliang Cai</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than injecting the full schema upfront, an agent must actively identify and verify only the relevant subset, giving rise to the Unknown Schema scenario we study in this work. To address this, we propose TRUST-SQL (Truthful Reasoning with Unknown Schema via Tools). We formulate the task as a Partially Observable Markov Decision Process where our autonomous agent employs a structured four-phase protocol to ground reasoning in verified metadata. Crucially, this protocol provides a structural boundary for our novel Dual-Track GRPO strategy. By applying token-level masked advantages, this strategy isolates exploration rewards from execution outcomes to resolve credit assignment, yielding a 9.9% relative improvement over standard GRPO. Extensive experiments across five benchmarks demonstrate that TRUST-SQL achieves an average absolute improvement of 30.6% and 16.6% for the 4B and 8B variants respectively over their base models. Remarkably, despite operating entirely without pre-loaded metadata, our framework consistently matches or surpasses strong baselines that rely on schema prefilling.</p> + https://arxiv.org/abs/2603.16448 + Tue, 17 Mar 2026 12:30:42 +0000 - Effective Distillation to Hybrid xLSTM Architectures - https://arxiv.org/abs/2603.15590 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt, Maximilian Beck, Sebastian Böck, Günter Klambauer, Sepp Hochreiter</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance of their teacher LLMs on various downstream tasks. We set out the goal of lossless distillation, which we define in terms of tolerance-corrected Win-and-Tie rates between student and teacher on sets of tasks. To this end, we introduce an effective distillation pipeline for xLSTM-based students. We propose an additional merging stage, where individually linearized experts are combined into a single model. We show the effectiveness of this pipeline by distilling base and instruction-tuned models from the Llama, Qwen, and Olmo families. In many settings, our xLSTM-based students recover most of the teacher's performance, and even exceed it on some downstream tasks. Our contributions are an important step towards more energy-efficient and cost-effective replacements for transformer-based LLMs.</p> - https://arxiv.org/abs/2603.15590 - Mon, 16 Mar 2026 17:49:04 +0000 + HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes + https://arxiv.org/abs/2603.16587 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16587.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pierre-Antoine Bannier</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present HistoAtlas, a pan-cancer computational atlas that extracts 38 interpretable histomic features from 6,745 diagnostic H&E slides across 21 TCGA cancer types and systematically links every feature to survival, gene expression, somatic mutations, and immune subtypes. All associations are covariate-adjusted, multiple-testing corrected, and classified into evidence-strength tiers. The atlas recovers known biology, from immune infiltration and prognosis to proliferation and kinase signaling, while uncovering compartment-specific immune signals and morphological subtypes with divergent outcomes. Every result is spatially traceable to tissue compartments and individual cells, statistically calibrated, and openly queryable. HistoAtlas enables systematic, large-scale biomarker discovery from routine H&E without specialized staining or sequencing. Data and an interactive web atlas are freely available at https://histoatlas.com .</p> + https://arxiv.org/abs/2603.16587 + Tue, 17 Mar 2026 14:36:07 +0000 - OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data - https://arxiv.org/abs/2603.15594 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15594.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen</p><p><b>Upvotes:</b> 125</p><p><b>Summary:</b> Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.</p> - https://arxiv.org/abs/2603.15594 - Mon, 16 Mar 2026 17:52:04 +0000 + Mixture of Style Experts for Diverse Image Stylization + https://arxiv.org/abs/2603.16649 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16649.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihao Zhu, Ziheng Ouyang, Yijia Kang, Qilong Wang, Mi Zhou, Bo Li, Ming-Ming Cheng, Qibin Hou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details.We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.</p> + https://arxiv.org/abs/2603.16649 + Tue, 17 Mar 2026 15:20:19 +0000 - Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning - https://arxiv.org/abs/2603.15611 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Aozhe Wang, Yuchen Yan, Nan Zhou, Zhengxi Lu, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent self-play methods unify code and test generation in a single model, but face a inherent dilemma: white-box access leads to self-collusion where the model produces trivial tests for easy rewards, yet black-box restriction yields generic tests that miss implementation-specific bugs. We introduce Code-A1, an adversarial co-evolution framework that jointly optimizes a Code LLM and a Test LLM with opposing objectives. The Code LLM is rewarded for passing more tests, while the Test LLM is rewarded for exposing more defects. This architectural separation eliminates self-collusion risks and safely enables white-box test generation, where the Test LLM can inspect candidate code to craft targeted adversarial tests. We further introduce a Mistake Book mechanism for experience replay and a composite reward balancing test validity with adversarial difficulty. Experiments on Qwen2.5-Coder models demonstrate that Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests, while significantly improving test generation capability.</p> - https://arxiv.org/abs/2603.15611 - Mon, 16 Mar 2026 17:58:13 +0000 + Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation + https://arxiv.org/abs/2603.16669 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mutian Xu, Tianbao Zhang, Tianqi Liu, Zhaoxi Chen, Xiaoguang Han, Ziwei Liu</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical constraints of traditional simulators. However, they primarily operate in 2D space or are guided by static environmental cues, ignoring the fundamental reality that robot-world interactions are inherently 4D spatiotemporal events that require precise interactive modeling. To restore this 4D essence while ensuring the precise robot control, we introduce Kinema4D, a new action-conditioned 4D generative robotic simulator that disentangles the robot-world interaction into: i) Precise 4D representation of robot controls: we drive a URDF-based 3D robot via kinematics, producing a precise 4D robot control trajectory. ii) Generative 4D modeling of environmental reactions: we project the 4D robot trajectory into a pointmap as a spatiotemporal visual signal, controlling the generative model to synthesize complex environments' reactive dynamics into synchronized RGB/pointmap sequences. To facilitate training, we curated a large-scale dataset called Robo4D-200k, comprising 201,426 robot interaction episodes with high-quality 4D annotations. Extensive experiments demonstrate that our method effectively simulates physically-plausible, geometry-consistent, and embodiment-agnostic interactions that faithfully mirror diverse real-world dynamics. For the first time, it shows potential zero-shot transfer capability, providing a high-fidelity foundation for advancing next-generation embodied simulation.</p> + https://arxiv.org/abs/2603.16669 + Tue, 17 Mar 2026 15:36:38 +0000 - HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions - https://arxiv.org/abs/2603.15612 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15612.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yukang Cao, Haozhe Xie, Fangzhou Hong, Long Zhuo, Zhaoxi Chen, Liang Pan, Ziwei Liu</p><p><b>Upvotes:</b> 92</p><p><b>Summary:</b> We present HSImul3R, a unified framework for simulation-ready 3D reconstruction of human-scene interactions (HSI) from casual captures, including sparse-view images and monocular videos. Existing methods suffer from a perception-simulation gap: visually plausible reconstructions often violate physical constraints, leading to instability in physics engines and failure in embodied AI applications. To bridge this gap, we introduce a physically-grounded bi-directional optimization pipeline that treats the physics simulator as an active supervisor to jointly refine human dynamics and scene geometry. In the forward direction, we employ Scene-targeted Reinforcement Learning to optimize human motion under dual supervision of motion fidelity and contact stability. In the reverse direction, we propose Direct Simulation Reward Optimization, which leverages simulation feedback on gravitational stability and interaction success to refine scene geometry. We further present HSIBench, a new benchmark with diverse objects and interaction scenarios. Extensive experiments demonstrate that HSImul3R produces the first stable, simulation-ready HSI reconstructions and can be directly deployed to real-world humanoid robots.</p> - https://arxiv.org/abs/2603.15612 - Mon, 16 Mar 2026 17:58:33 +0000 + Anticipatory Planning for Multimodal AI Agents + https://arxiv.org/abs/2603.16777 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16777.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongyuan Liang, Shijie Zhou, Yu Gu, Hao Tan, Gang Wu, Franck Dernoncourt, Jihyung Kil, Ryan A. Rossi, Ruiyi Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reasoning about future states or long-term goals. This limits planning coherence and prevents agents from reliably solving high-level, multi-step tasks. We introduce TraceR1, a two-stage reinforcement learning framework that explicitly trains anticipatory reasoning by forecasting short-horizon trajectories before execution. The first stage performs trajectory-level reinforcement learning with rewards that enforce global consistency across predicted action sequences. The second stage applies grounded reinforcement fine-tuning, using execution feedback from frozen tool agents to refine step-level accuracy and executability. TraceR1 is evaluated across seven benchmarks, covering online computer-use, offline computer-use benchmarks, and multimodal tool-use reasoning tasks, where it achieves substantial improvements in planning stability, execution robustness, and generalization over reactive and single-stage baselines. These results show that anticipatory trajectory reasoning is a key principle for building multimodal agents that can reason, plan, and act effectively in complex real-world environments.</p> + https://arxiv.org/abs/2603.16777 + Tue, 17 Mar 2026 16:55:11 +0000 - Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion - https://arxiv.org/abs/2603.15614 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenghong Zhou, Xiaohang Zhan, Zhiqin Chen, Soo Ye Kim, Nanxuan Zhao, Haitian Zheng, Qing Liu, He Zhang, Zhe Lin, Yuqian Zhou, Jiebo Luo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.</p> - https://arxiv.org/abs/2603.15614 - Mon, 16 Mar 2026 17:59:05 +0000 + InCoder-32B: Code Foundation Model for Industrial Scenarios + https://arxiv.org/abs/2603.16790 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16790.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Shawn Guo, Haowen Wang, Weicheng Gu, Yaxin Du, Joseph Li, Fanglin Xu, Yizhi Li, Lin Jing, Yuanbo Wang, Yuhan Gao, Ruihao Gong, Chuan Hao, Ran Tao, Aishan Liu, Tuney Zheng, Ganqu Cui, Zhoujun Li, Mingjie Tang, Chenghua Lin, Wayne Xin Zhao, Xianglong Liu, Ming Zhou, Bryan Dai, Weifeng Lv</p><p><b>Upvotes:</b> 135</p><p><b>Summary:</b> Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains.</p> + https://arxiv.org/abs/2603.16790 + Tue, 17 Mar 2026 17:01:35 +0000 - GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering - https://arxiv.org/abs/2603.15616 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15616.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xincheng Shuai, Ziye Li, Henghui Ding, Dacheng Tao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality scene text images, but the limited coverage of glyph variations and excessive stylization often compromise glyph accuracy, especially for complex or out-of-domain characters. Some methods leverage reinforcement learning to alleviate this issue, yet their reward models usually depend on text recognition systems that are insensitive to fine-grained glyph errors, so images with incorrect glyphs may still receive high rewards. Inspired by Direct Preference Optimization (DPO), we propose GlyphPrinter, a preference-based text rendering method that eliminates reliance on explicit reward models. However, the standard DPO objective only models overall preference between two samples, which is insufficient for visual text rendering where glyph errors typically occur in localized regions. To address this issue, we construct the GlyphCorrector dataset with region-level glyph preference annotations and propose Region-Grouped DPO (R-GDPO), a region-based objective that optimizes inter- and intra-sample preferences over annotated regions, substantially enhancing glyph accuracy. Furthermore, we introduce Regional Reward Guidance, an inference strategy that samples from an optimal distribution with controllable glyph accuracy. Extensive experiments demonstrate that the proposed GlyphPrinter outperforms existing methods in glyph accuracy while maintaining a favorable balance between stylization and precision.</p> - https://arxiv.org/abs/2603.15616 - Mon, 16 Mar 2026 17:59:31 +0000 + V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising + https://arxiv.org/abs/2603.16792 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16792.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic supervision and are not explicitly designed to capture high-level visual structure. Recent representation-alignment methods (e.g., REPA) suggest that pretrained visual features can substantially improve diffusion training, and visual co-denoising has emerged as a promising direction for incorporating such features into the generative process. However, existing co-denoising approaches often entangle multiple design choices, making it unclear which design choices are truly essential. Therefore, we present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework. This controlled setting allows us to isolate the ingredients that make visual co-denoising effective. Our study reveals four key ingredients for effective visual co-denoising. First, preserving feature-specific computation while enabling flexible cross-stream interaction motivates a fully dual-stream architecture. Second, effective classifier-free guidance (CFG) requires a structurally defined unconditional prediction. Third, stronger semantic supervision is best provided by a perceptual-drifting hybrid loss. Fourth, stable co-denoising further requires proper cross-stream calibration, which we realize through RMS-based feature rescaling. Together, these findings yield a simple recipe for visual co-denoising. Experiments on ImageNet-256 show that, at comparable model sizes, V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods while using fewer training epochs, offering practical guidance for future representation-aligned generative models.</p> + https://arxiv.org/abs/2603.16792 + Tue, 17 Mar 2026 17:01:54 +0000 - HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification - https://arxiv.org/abs/2603.15617 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15617.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erik Y. Wang, Sumeet Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Flaviu Cipcigan, Philip Torr, Alessandro Abate</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientific reasoning, but whether they can perform novel research is still widely debated and underexplored. We introduce HorizonMath, a benchmark of over 100 predominantly unsolved problems spanning 8 domains in computational and applied mathematics, paired with an open-source evaluation framework for automated verification. Our benchmark targets a class of problems where discovery is hard, requiring meaningful mathematical insight, but verification is computationally efficient and simple. Because these solutions are unknown, HorizonMath is immune to data contamination, and most state-of-the-art models score near 0%. Existing research-level benchmarks instead rely on formal proof verification or manual review, both of which are expensive to scale. Using this platform, we find two problems for which GPT 5.4 Pro proposes solutions that improve on the best-known published results, representing potential novel contributions (pending expert review). We release HorizonMath as an open challenge and a growing community resource, where correct solutions to problems in the unsolved problem classes could constitute novel results in the mathematical literature.</p> - https://arxiv.org/abs/2603.15617 - Mon, 16 Mar 2026 17:59:53 +0000 + M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM + https://arxiv.org/abs/2603.16844 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kerui Ren, Guanghao Li, Changjian Jiang, Yingxiang Xu, Tao Lu, Linning Xu, Junting Dong, Jiangmiao Pang, Mulin Yu, Bo Dai</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: most multi-view foundation models estimate poses in a feed-forward manner, yielding pixel-level correspondences that lack the requisite precision for rigorous geometric optimization. To address this, we present M^3, which augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences and integrates it into a robust Monocular Gaussian Splatting SLAM. M^3 further enhances tracking stability by incorporating dynamic area suppression and cross-inference intrinsic alignment. Extensive experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction. Notably, M^3 reduces ATE RMSE by 64.3% compared to VGGT-SLAM 2.0 and outperforms ARTDECO by 2.11 dB in PSNR on the ScanNet++ dataset.</p> + https://arxiv.org/abs/2603.16844 + Tue, 17 Mar 2026 17:52:37 +0000 - Mixture-of-Depths Attention - https://arxiv.org/abs/2603.15619 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lianghui Zhu, Yuxin Fang, Bencheng Liao, Shijie Wang, Tianheng Cheng, Zilong Huang, Chen Chen, Lai Wei, Yutao Zeng, Ya Wang, Yi Lin, Yu Li, Xinggang Wang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making them harder to recover in deeper layers. We introduce mixture-of-depths attention (MoDA), a mechanism that allows each attention head to attend to sequence KV pairs at the current layer and depth KV pairs from preceding layers. We further describe a hardware-efficient algorithm for MoDA that resolves non-contiguous memory-access patterns, achieving 97.3% of FlashAttention-2's efficiency at a sequence length of 64K. Experiments on 1.5B-parameter models demonstrate that MoDA consistently outperforms strong baselines. Notably, it improves average perplexity by 0.2 across 10 validation benchmarks and increases average performance by 2.11% on 10 downstream tasks, with a negligible 3.7% FLOPs computational overhead. We also find that combining MoDA with post-norm yields better performance than using it with pre-norm. These results suggest that MoDA is a promising primitive for depth scaling. Code is released at https://github.com/hustvl/MoDA .</p> - https://arxiv.org/abs/2603.15619 - Mon, 16 Mar 2026 17:59:55 +0000 + Online Experiential Learning for Language Models + https://arxiv.org/abs/2603.16856 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16856.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianzhu Ye, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, Furu Wei</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose Online Experiential Learning (OEL), a framework that enables language models to continuously improve from their own deployment experience. OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side; second, this knowledge is consolidated into model parameters via on-policy context distillation, requiring no access to the user-side environment. The two stages are iterated to form an online learning loop, where the improved model collects higher-quality trajectories that yield richer experiential knowledge for subsequent rounds. We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants. OEL achieves consistent improvements over successive iterations, enhancing both task accuracy and token efficiency while preserving out-of-distribution performance. Our analysis further shows that extracted experiential knowledge is significantly more effective than raw trajectories, and that on-policy consistency between the knowledge source and the policy model is critical for effective learning.</p> + https://arxiv.org/abs/2603.16856 + Tue, 17 Mar 2026 17:57:49 +0000 - Towards Generalizable Robotic Manipulation in Dynamic Environments - https://arxiv.org/abs/2603.15620 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.15620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Heng Fang, Shangru Li, Shuhan Wang, Xuanyang Xi, Dingkang Liang, Xiang Bai</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of dynamic manipulation datasets and the reliance of mainstream VLAs on single-frame observations, restricting their spatiotemporal reasoning capabilities. To address this, we introduce DOMINO, a large-scale dataset and benchmark for generalizable dynamic manipulation, featuring 35 tasks with hierarchical complexities, over 110K expert trajectories, and a multi-dimensional evaluation suite. Through comprehensive experiments, we systematically evaluate existing VLAs on dynamic tasks, explore effective training strategies for dynamic awareness, and validate the generalizability of dynamic data. Furthermore, we propose PUMA, a dynamics-aware VLA architecture. By integrating scene-centric historical optical flow and specialized world queries to implicitly forecast object-centric future states, PUMA couples history-aware perception with short-horizon prediction. Results demonstrate that PUMA achieves state-of-the-art performance, yielding a 6.3% absolute improvement in success rate over baselines. Moreover, we show that training on dynamic data fosters robust spatiotemporal representations that transfer to static tasks. All code and data are available at https://github.com/H-EmbodVis/DOMINO.</p> - https://arxiv.org/abs/2603.15620 - Mon, 16 Mar 2026 17:59:57 +0000 + SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models + https://arxiv.org/abs/2603.16859 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Xie, Jinfa Huang, Yuexiao Ma, Rongfang Luo, Yan Yang, Wang Chen, Yuhui Zeng, Ruize Fang, Yixuan Zou, Xiawu Zheng, Jiebo Luo, Rongrong Ji</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (when to interject), and (iii) natural interruption generation (how to phrase the interruption). SocialOmni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances with strict temporal and contextual constraints, complemented by controlled audio-visual inconsistency scenarios to test model robustness. We benchmarked 12 leading OLMs, which uncovers significant variance in their social-interaction capabilities across models. Furthermore, our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions, indicating that understanding-centric metrics alone are insufficient to characterize conversational social competence. More encouragingly, these diagnostics from SocialOmni yield actionable signals for bridging the perception-interaction divide in future OLMs.</p> + https://arxiv.org/abs/2603.16859 + Tue, 17 Mar 2026 17:58:44 +0000 + + + MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation + https://arxiv.org/abs/2603.16861 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16861.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abhay Deshpande, Maya Guru, Rose Hendrix, Snehal Jauhri, Ainaz Eftekhar, Rohun Tripathi, Max Argus, Jordi Salvador, Haoquan Fang, Matthew Wallingford, Wilbert Pumacay, Yejin Kim, Quinn Pfeifer, Ying-Chun Lee, Piper Wolters, Omar Rayyan, Mingtong Zhang, Jiafei Duan, Karen Farley, Winson Han, Eli Vanderbilt, Dieter Fox, Ali Farhadi, Georgia Chalvatzaki, Dhruv Shah, Ranjay Krishna</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the gap between simulated and physical environments. We challenge that assumption. With sufficiently large-scale and diverse simulated synthetic training data, we show that zero-shot transfer to the real world is not only possible, but effective for both static and mobile manipulation. We introduce MolmoBot-Engine, a fully open-source pipeline for procedural data generation across robots, tasks, and diverse simulated environments in MolmoSpaces. With it, we release MolmoBot-Data, a dataset of 1.8 million expert trajectories for articulated object manipulation and pick-and-place tasks. We train three policy classes: MolmoBot, a Molmo2-based multi-frame vision-language model with a flow-matching action head; MolmoBot-Pi0, which replicates the π_0 architecture to enable direct comparison; and MolmoBot-SPOC, a lightweight policy suitable for edge deployment and amenable to RL fine-tuning. We evaluate on two robotic platforms: the Franka FR3 for tabletop manipulation tasks and the Rainbow Robotics RB-Y1 mobile manipulator for door opening, drawer manipulation, cabinet interaction, and mobile pick-and-place. Without any real-world fine-tuning, our policies achieve zero-shot transfer to unseen objects and environments. On tabletop pick-and-place, MolmoBot achieves a success rate of 79.2% in real world evaluations across 4 settings, outperforming π_{0.5} at 39.2%. Our results demonstrate that procedural environment generation combined with diverse articulated assets can produce robust manipulation policies that generalize broadly to the real world. Technical Blog: https://allenai.org/blog/molmobot-robot-manipulation</p> + https://arxiv.org/abs/2603.16861 + Tue, 17 Mar 2026 17:59:03 +0000 + + + SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation + https://arxiv.org/abs/2603.16864 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong Tu</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but instead can only accept whatever the model produces. In this paper, we propose a novel interactive VSR framework dubbed SparkVSR that makes sparse keyframes a simple and expressive control signal. Specifically, users can first super-resolve or optionally a small set of keyframes using any off-the-shelf image super-resolution (ISR) model, then SparkVSR propagates the keyframe priors to the entire video sequence while remaining grounded by the original LR video motion. Concretely, we introduce a keyframe-conditioned latent-pixel two-stage training pipeline that fuses LR video latents with sparsely encoded HR keyframe latents to learn robust cross-space propagation and refine perceptual details. At inference time, SparkVSR supports flexible keyframe selection (manual specification, codec I-frame extraction, or random sampling) and a reference-free guidance mechanism that continuously balances keyframe adherence and blind restoration, ensuring robust performance even when reference keyframes are absent or imperfect. Experiments on multiple VSR benchmarks demonstrate improved temporal consistency and strong restoration quality, surpassing baselines by up to 24.6%, 21.8%, and 5.6% on CLIP-IQA, DOVER, and MUSIQ, respectively, enabling controllable, keyframe-driven video super-resolution. Moreover, we demonstrate that SparkVSR is a generic interactive, keyframe-conditioned video processing framework as it can be applied out of the box to unseen tasks such as old-film restoration and video style transfer. Our project page is available at: https://sparkvsr.github.io/</p> + https://arxiv.org/abs/2603.16864 + Tue, 17 Mar 2026 17:59:30 +0000 + + + Efficient Reasoning on the Edge + https://arxiv.org/abs/2603.16867 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel, Ankita Nayak, Corrado Rainone, Ork de Rooij, Paul N Whatmough, Arash Behboodi, Babak Ehteshami Bejnordi</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment. These challenges include high token generation costs, large KV-cache footprints, and inefficiencies when distilling reasoning capabilities into smaller models for mobile devices. Existing approaches often rely on distilling reasoning traces from larger models into smaller models, which are verbose and stylistically redundant, undesirable for on-device inference. In this work, we propose a lightweight approach to enable reasoning in small LLMs using LoRA adapters combined with supervised fine-tuning. We further introduce budget forcing via reinforcement learning on these adapters, significantly reducing response length with minimal accuracy loss. To address memory-bound decoding, we exploit parallel test-time scaling, improving accuracy at minor latency increase. Finally, we present a dynamic adapter-switching mechanism that activates reasoning only when needed and a KV-cache sharing strategy during prompt encoding, reducing time-to-first-token for on-device inference. Experiments on Qwen2.5-7B demonstrate that our method achieves efficient, accurate reasoning under strict resource constraints, making LLM reasoning practical for mobile scenarios. Videos demonstrating our solution running on mobile devices are available on our project page.</p> + https://arxiv.org/abs/2603.16867 + Tue, 17 Mar 2026 17:59:51 +0000 + + + SegviGen: Repurposing 3D Generative Model for Part Segmentation + https://arxiv.org/abs/2603.16869 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16869.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen, Wenbo Nie, Shaohua Hou, Keqing Fan, Pan Hu, Sheng Wang, Buyu Li, Lu Sheng</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/.</p> + https://arxiv.org/abs/2603.16869 + Tue, 17 Mar 2026 17:59:51 +0000 + + + Demystifing Video Reasoning + https://arxiv.org/abs/2603.16870 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16870.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruisi Wang, Zhongang Cai, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin, Ziwei Liu, Lei Yang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory, enabling persistent reference; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. During a diffusion step, we further uncover self-evolved functional specialization within Diffusion Transformers, where early layers encode dense perceptual structure, middle layers execute reasoning, and later layers consolidate latent representations. Motivated by these insights, we present a simple training-free strategy as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides a systematic understanding of how reasoning emerges in video generation models, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence.</p> + https://arxiv.org/abs/2603.16870 + Tue, 17 Mar 2026 17:59:55 +0000 + + + WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation + https://arxiv.org/abs/2603.16871 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.16871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jisu Nam, Yicong Hong, Chun-Hao Paul Huang, Feng Liu, JoungBin Lee, Jiyoung Kim, Siyoon Jin, Yunsung Lee, Jaeyoon Jung, Suhwan Choi, Seungryong Kim, Yang Zhou</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.</p> + https://arxiv.org/abs/2603.16871 + Tue, 17 Mar 2026 17:59:56 +0000