diff --git a/feed_weekly.xml b/feed_weekly.xml index 7834294..ae6b8f4 100644 --- a/feed_weekly.xml +++ b/feed_weekly.xml @@ -7,741 +7,741 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 02 Jun 2025 00:11:57 +0000 + Mon, 09 Jun 2025 00:12:26 +0000 - ModernGBERT: German-only 1B Encoder Model Trained from Scratch - https://arxiv.org/abs/2505.13136 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.13136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anton Ehrmanntraut, Julia Wunderle, Jan Pfister, Fotis Jannidis, Andreas Hotho</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Despite the prominence of decoder-only language models, encoders remain crucial for resource-constrained applications. We introduce ModernGBERT (134M, 1B), a fully transparent family of German encoder models trained from scratch, incorporating architectural innovations from ModernBERT. To evaluate the practical trade-offs of training encoders from scratch, we also present LL\"aMmlein2Vec (120M, 1B, 7B), a family of encoders derived from German decoder-only models via LLM2Vec. We benchmark all models on natural language understanding, text embedding, and long-context reasoning tasks, enabling a controlled comparison between dedicated encoders and converted decoders. Our results show that ModernGBERT 1B outperforms prior state-of-the-art German encoders as well as encoders adapted via LLM2Vec, with regard to performance and parameter-efficiency. All models, training data, checkpoints and code are publicly available, advancing the German NLP ecosystem with transparent, high-performance encoder models.</p> - https://arxiv.org/abs/2505.13136 - Mon, 19 May 2025 14:07:20 +0000 + Large Language Models for Data Synthesis + https://arxiv.org/abs/2505.14752 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.14752.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihong Tang, Menglin Kong, Lijun Sun</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Generating synthetic data that faithfully captures the statistical structure of real-world distributions is a fundamental challenge in data modeling. Classical approaches often depend on strong parametric assumptions or manual structural design and struggle in high-dimensional or heterogeneous domains. Recent progress in Large Language Models (LLMs) reveals their potential as flexible, high-dimensional priors over real-world distributions. However, when applied to data synthesis, standard LLM-based sampling is inefficient, constrained by fixed context limits, and fails to ensure statistical alignment. Given this, we introduce LLMSynthor, a general framework for data synthesis that transforms LLMs into structure-aware simulators guided by distributional feedback. LLMSynthor treats the LLM as a nonparametric copula simulator for modeling high-order dependencies and introduces LLM Proposal Sampling to generate grounded proposal distributions that improve sampling efficiency without requiring rejection. By minimizing discrepancies in the summary statistics space, the iterative synthesis loop aligns real and synthetic data while gradually uncovering and refining the latent generative structure. We evaluate LLMSynthor in both controlled and real-world settings using heterogeneous datasets in privacy-sensitive domains (e.g., e-commerce, population, and mobility) that encompass both structured and unstructured formats. The synthetic data produced by LLMSynthor shows high statistical fidelity, practical utility, and cross-data adaptability, positioning it as a valuable tool across economics, social science, urban studies, and beyond.</p> + https://arxiv.org/abs/2505.14752 + Tue, 20 May 2025 13:35:38 +0000 - NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in Brain MRI - https://arxiv.org/abs/2505.14064 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.14064.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cosmin I. Bercea, Jun Li, Philipp Raffler, Evamaria O. Riedel, Lena Schmitzer, Angela Kurz, Felix Bitzer, Paula Roßmüller, Julian Canisius, Mirjam L. Beyrle, Che Liu, Wenjia Bai, Bernhard Kainz, Julia A. Schnabel, Benedikt Wiestler</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> In many real-world applications, deployed models encounter inputs that differ from the data seen during training. Out-of-distribution detection identifies whether an input stems from an unseen distribution, while open-world recognition flags such inputs to ensure the system remains robust as ever-emerging, previously unknown categories appear and must be addressed without retraining. Foundation and vision-language models are pre-trained on large and diverse datasets with the expectation of broad generalization across domains, including medical imaging. However, benchmarking these models on test sets with only a few common outlier types silently collapses the evaluation back to a closed-set problem, masking failures on rare or truly novel conditions encountered in clinical use. We therefore present NOVA, a challenging, real-life evaluation-only benchmark of sim900 brain MRI scans that span 281 rare pathologies and heterogeneous acquisition protocols. Each case includes rich clinical narratives and double-blinded expert bounding-box annotations. Together, these enable joint assessment of anomaly localisation, visual captioning, and diagnostic reasoning. Because NOVA is never used for training, it serves as an extreme stress-test of out-of-distribution generalisation: models must bridge a distribution gap both in sample appearance and in semantic space. Baseline results with leading vision-language models (GPT-4o, Gemini 2.0 Flash, and Qwen2.5-VL-72B) reveal substantial performance drops across all tasks, establishing NOVA as a rigorous testbed for advancing models that can detect, localize, and reason about truly unknown anomalies.</p> - https://arxiv.org/abs/2505.14064 - Tue, 20 May 2025 08:10:57 +0000 + CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark + https://arxiv.org/abs/2505.16968 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16968.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmed Heakl, Sarim Hashmi, Gustavo Bertolo Stahl, Seung Hun Eddie Han, Salman Khan, Abdulrahman Mahmoud</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> We introduce CASS, the first large-scale dataset and model suite for cross-architecture GPU code transpilation, targeting both source-level (CUDA leftrightarrow HIP) and assembly-level (Nvidia SASS leftrightarrow AMD RDNA3) translation. The dataset comprises 70k verified code pairs across host and device, addressing a critical gap in low-level GPU code portability. Leveraging this resource, we train the CASS family of domain-specific language models, achieving 95% source translation accuracy and 37.5% assembly translation accuracy, substantially outperforming commercial baselines such as GPT-4o, Claude, and Hipify. Our generated code matches native performance in over 85% of test cases, preserving runtime and memory behavior. To support rigorous evaluation, we introduce CASS-Bench, a curated benchmark spanning 16 GPU domains with ground-truth execution. All data, models, and evaluation tools are released as open source to foster progress in GPU compiler tooling, binary compatibility, and LLM-guided hardware translation. Dataset and benchmark are on https://huggingface.co/datasets/MBZUAI/cass{blue{HuggingFace}}, with code at https://github.com/GustavoStahl/CASS{blue{GitHub}}.</p> + https://arxiv.org/abs/2505.16968 + Thu, 22 May 2025 17:48:53 +0000 - Quartet: Native FP4 Training Can Be Optimal for Large Language Models - https://arxiv.org/abs/2505.14669 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.14669.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roberto L. Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling, Jiale Chen, Mahdi Nikdan, Saleh Ashkboos, Dan Alistarh</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> The rapid advancement of large language models (LLMs) has been paralleled by unprecedented increases in computational demands, with training costs for state-of-the-art models doubling every few months. Training models directly in low-precision arithmetic offers a solution, by improving both computational throughput and energy efficiency. Specifically, NVIDIA's recent Blackwell architecture facilitates extremely low-precision operations, specifically FP4 variants, promising substantial efficiency gains. Yet, current algorithms for training LLMs in FP4 precision face significant accuracy degradation and often rely on mixed-precision fallbacks. In this paper, we systematically investigate hardware-supported FP4 training and introduce Quartet, a new approach enabling accurate, end-to-end FP4 training with all the major computations (in e.g. linear layers) being performed in low precision. Through extensive evaluations on Llama-type models, we reveal a new low-precision scaling law that quantifies performance trade-offs across varying bit-widths and allows us to identify a "near-optimal" low-precision training technique in terms of accuracy-vs-computation, called Quartet. We implement Quartet using optimized CUDA kernels tailored for NVIDIA Blackwell GPUs, and show that it can achieve state-of-the-art accuracy for FP4 precision, successfully training billion-scale models. Our method demonstrates that fully FP4-based training is a competitive alternative to standard-precision and FP8 training. Our code is available at https://github.com/IST-DASLab/Quartet.</p> - https://arxiv.org/abs/2505.14669 - Tue, 20 May 2025 17:55:50 +0000 + More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models + https://arxiv.org/abs/2505.21523 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengzhi Liu, Zhongxing Xu, Qingyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, Sheng Liu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors. Attention analysis shows that longer reasoning chains lead to reduced focus on visual inputs, which contributes to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, allowing us to evaluate whether the model preserves visual grounding during reasoning. We also release RH-Bench, a diagnostic benchmark that spans a variety of multimodal tasks, designed to assess the trade-off between reasoning ability and hallucination. Our analysis reveals that (i) larger models typically achieve a better balance between reasoning and perception, and (ii) this balance is influenced more by the types and domains of training data than by its overall volume. These findings underscore the importance of evaluation frameworks that jointly consider both reasoning quality and perceptual fidelity.</p> + https://arxiv.org/abs/2505.21523 + Fri, 23 May 2025 05:08:40 +0000 - PhyX: Does Your Model Have the "Wits" for Physical Reasoning? - https://arxiv.org/abs/2505.15929 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.15929.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hui Shen, Taiqiang Wu, Qi Han, Yunta Hsieh, Jizhou Wang, Yuyue Zhang, Yuxin Cheng, Zijian Hao, Yuansheng Ni, Xin Wang, Zhongwei Wan, Kai Zhang, Wendong Xu, Jing Xiong, Ping Luo, Wenhu Chen, Chaofan Tao, Zhuoqing Mao, Ngai Wong</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce PhyX: the first large-scale benchmark designed to assess models capacity for physics-grounded reasoning in visual scenarios. PhyX includes 3K meticulously curated multimodal questions spanning 6 reasoning types across 25 sub-domains and 6 core physics domains: thermodynamics, electromagnetism, mechanics, modern physics, optics, and wave\&acoustics. In our comprehensive evaluation, even state-of-the-art models struggle significantly with physical reasoning. GPT-4o, Claude3.7-Sonnet, and GPT-o4-mini achieve only 32.5\%, 42.2\%, and 45.8\% accuracy respectively-performance gaps exceeding 29\% compared to human experts. Our analysis exposes critical limitations in current models: over-reliance on memorized disciplinary knowledge, excessive dependence on mathematical formulations, and surface-level visual pattern matching rather than genuine physical understanding. We provide in-depth analysis through fine-grained statistics, detailed case studies, and multiple evaluation paradigms to thoroughly examine physical reasoning capabilities. To ensure reproducibility, we implement a compatible evaluation protocol based on widely-used toolkits such as VLMEvalKit, enabling one-click evaluation.</p> - https://arxiv.org/abs/2505.15929 - Wed, 21 May 2025 18:33:50 +0000 + Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation + https://arxiv.org/abs/2505.18842 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18842.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee, Min Soo Kim, Youngjae Yu</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs) that enables selective visual revisitation during inference. While current MLLMs typically consume visual input only once and reason purely over internal memory, v1 introduces a simple point-and-copy mechanism that allows the model to dynamically retrieve relevant image regions throughout the reasoning process. This mechanism augments existing architectures with minimal modifications, enabling contextual access to visual tokens based on the model's evolving hypotheses. To train this capability, we construct v1g, a dataset of 300K multimodal reasoning traces with interleaved visual grounding annotations. Experiments on three multimodal mathematical reasoning benchmarks -- MathVista, MathVision, and MathVerse -- demonstrate that v1 consistently improves performance over comparable baselines, particularly on tasks requiring fine-grained visual reference and multi-step reasoning. Our results suggest that dynamic visual access is a promising direction for enhancing grounded multimodal reasoning. Code, models, and data will be released to support future research.</p> + https://arxiv.org/abs/2505.18842 + Sat, 24 May 2025 19:30:47 +0000 - Position of Uncertainty: A Cross-Linguistic Study of Positional Bias in Large Language Models - https://arxiv.org/abs/2505.16134 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16134.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Menschikov Mikhail, Alexander Kharitonov, Maiia Kotyga, Vadim Porvatov, Anna Zhukovskaya, David Kagramanyan, Egor Shvetsov, Evgeny Burnaev</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Large language models exhibit positional bias -- systematic neglect of information at specific context positions -- yet its interplay with linguistic diversity remains poorly understood. We present a cross-linguistic study across five typologically distinct languages (English, Russian, German, Hindi, Vietnamese), examining how positional bias interacts with model uncertainty, syntax, and prompting. Key findings: (1) Positional bias is model-driven, with language-specific variations -- Qwen2.5-7B favors late positions, challenging assumptions of early-token bias; (2) Explicit positional guidance (e.g., correct context is at position X) reduces accuracy across languages, undermining prompt-engineering practices; (3) Aligning context with positional bias increases entropy, yet minimal entropy does not predict accuracy. (4) We further uncover that LLMs differently impose dominant word order in free-word-order languages like Hindi.</p> - https://arxiv.org/abs/2505.16134 - Thu, 22 May 2025 02:23:00 +0000 + CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects + https://arxiv.org/abs/2505.21437 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21437.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huaijin Pi, Zhi Cen, Zhiyang Dou, Taku Komura</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Synthesizing whole-body manipulation of articulated objects, including body motion, hand motion, and object motion, is a critical yet challenging task with broad applications in virtual humans and robotics. The core challenges are twofold. First, achieving realistic whole-body motion requires tight coordination between the hands and the rest of the body, as their movements are interdependent during manipulation. Second, articulated object manipulation typically involves high degrees of freedom and demands higher precision, often requiring the fingers to be placed at specific regions to actuate movable parts. To address these challenges, we propose a novel coordinated diffusion noise optimization framework. Specifically, we perform noise-space optimization over three specialized diffusion models for the body, left hand, and right hand, each trained on its own motion dataset to improve generalization. Coordination naturally emerges through gradient flow along the human kinematic chain, allowing the global body posture to adapt in response to hand motion objectives with high fidelity. To further enhance precision in hand-object interaction, we adopt a unified representation based on basis point sets (BPS), where end-effector positions are encoded as distances to the same BPS used for object geometry. This unified representation captures fine-grained spatial relationships between the hand and articulated object parts, and the resulting trajectories serve as targets to guide the optimization of diffusion noise, producing highly accurate interaction motion. We conduct extensive experiments demonstrating that our method outperforms existing approaches in motion quality and physical plausibility, and enables various capabilities such as object pose control, simultaneous walking and manipulation, and whole-body generation from hand-only data.</p> + https://arxiv.org/abs/2505.21437 + Tue, 27 May 2025 17:11:50 +0000 - AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models - https://arxiv.org/abs/2505.16211 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16211.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Li, Can Shen, Yile Liu, Jirui Han, Kelong Zheng, Xuechao Zou, Zhe Wang, Xingjian Du, Shun Zhang, Hanjun Luo, Yingbin Jin, Xinxin Xing, Ziyang Ma, Yue Liu, Xiaojun Jia, Yifan Zhang, Junfeng Fang, Kun Wang, Yibo Yan, Haoyang Li, Yiming Li, Xiaobin Zhuang, Yang Liu, Haibo Hu, Zhuo Chen, Zhizheng Wu, Xiaolin Hu, Eng-Siong Chng, XiaoFeng Wang, Wenyuan Xu, Wei Dong, Xinfeng Li</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> The rapid advancement and expanding applications of Audio Large Language Models (ALLMs) demand a rigorous understanding of their trustworthiness. However, systematic research on evaluating these models, particularly concerning risks unique to the audio modality, remains largely unexplored. Existing evaluation frameworks primarily focus on the text modality or address only a restricted set of safety dimensions, failing to adequately account for the unique characteristics and application scenarios inherent to the audio modality. We introduce AudioTrust-the first multifaceted trustworthiness evaluation framework and benchmark specifically designed for ALLMs. AudioTrust facilitates assessments across six key dimensions: fairness, hallucination, safety, privacy, robustness, and authentication. To comprehensively evaluate these dimensions, AudioTrust is structured around 18 distinct experimental setups. Its core is a meticulously constructed dataset of over 4,420 audio/text samples, drawn from real-world scenarios (e.g., daily conversations, emergency calls, voice assistant interactions), specifically designed to probe the multifaceted trustworthiness of ALLMs. For assessment, the benchmark carefully designs 9 audio-specific evaluation metrics, and we employ a large-scale automated pipeline for objective and scalable scoring of model outputs. Experimental results reveal the trustworthiness boundaries and limitations of current state-of-the-art open-source and closed-source ALLMs when confronted with various high-risk audio scenarios, offering valuable insights for the secure and trustworthy deployment of future audio models. Our platform and benchmark are available at https://github.com/JusperLee/AudioTrust.</p> - https://arxiv.org/abs/2505.16211 - Thu, 22 May 2025 04:27:46 +0000 + Training Language Models to Generate Quality Code with Program Analysis Feedback + https://arxiv.org/abs/2505.22704 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22704.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Feng Yao, Zilong Wang, Liyuan Liu, Junxia Cui, Li Zhong, Xiaohan Fu, Haohui Mai, Vish Krishnan, Jianfeng Gao, Jingbo Shang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g., missing type annotations). Existing methods, such as supervised fine-tuning and rule-based post-processing, rely on labor-intensive annotations or brittle heuristics, limiting their scalability and effectiveness. We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code using program analysis-guided feedback. Specifically, REAL integrates two automated signals: (1) program analysis detecting security or maintainability defects and (2) unit tests ensuring functional correctness. Unlike prior work, our framework is prompt-agnostic and reference-free, enabling scalable supervision without manual intervention. Experiments across multiple datasets and model scales demonstrate that REAL outperforms state-of-the-art methods in simultaneous assessments of functionality and code quality. Our work bridges the gap between rapid prototyping and production-ready code, enabling LLMs to deliver both speed and quality.</p> + https://arxiv.org/abs/2505.22704 + Wed, 28 May 2025 17:57:47 +0000 - Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance - https://arxiv.org/abs/2505.16348 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16348.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taeyoon Kwon, Dongwook Choi, Sunghwan Kim, Hyojun Kim, Seungjun Moon, Beong-woo Kwak, Kuan-Hao Huang, Jinyoung Yeo</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Embodied agents empowered by large language models (LLMs) have shown strong performance in household object rearrangement tasks. However, these tasks primarily focus on single-turn interactions with simplified instructions, which do not truly reflect the challenges of providing meaningful assistance to users. To provide personalized assistance, embodied agents must understand the unique semantics that users assign to the physical world (e.g., favorite cup, breakfast routine) by leveraging prior interaction history to interpret dynamic, real-world instructions. Yet, the effectiveness of embodied agents in utilizing memory for personalized assistance remains largely underexplored. To address this gap, we present MEMENTO, a personalized embodied agent evaluation framework designed to comprehensively assess memory utilization capabilities to provide personalized assistance. Our framework consists of a two-stage memory evaluation process design that enables quantifying the impact of memory utilization on task performance. This process enables the evaluation of agents' understanding of personalized knowledge in object rearrangement tasks by focusing on its role in goal interpretation: (1) the ability to identify target objects based on personal meaning (object semantics), and (2) the ability to infer object-location configurations from consistent user patterns, such as routines (user patterns). Our experiments across various LLMs reveal significant limitations in memory utilization, with even frontier models like GPT-4o experiencing a 30.5% performance drop when required to reference multiple memories, particularly in tasks involving user patterns. These findings, along with our detailed analyses and case studies, provide valuable insights for future research in developing more effective personalized embodied agents. Project website: https://connoriginal.github.io/MEMENTO</p> - https://arxiv.org/abs/2505.16348 - Thu, 22 May 2025 08:00:10 +0000 + EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge + https://arxiv.org/abs/2505.23009 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23009.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruskin Raj Manku, Yuzhi Tang, Xingjian Shi, Mu Li, Alex Smola</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on EmergentTTS, we introduce EmergentTTS-Eval, a comprehensive benchmark covering six challenging TTS scenarios: emotions, paralinguistics, foreign words, syntactic complexity, complex pronunciation (e.g. URLs, formulas), and questions. Crucially, our framework automates both test-case generation and evaluation, making the benchmark easily extensible. Starting from a small set of human-written seed prompts, we iteratively extend them using LLMs to target specific structural, phonetic and prosodic challenges, resulting in 1,645 diverse test cases. Moreover, we employ a model-as-a-judge approach, using a Large Audio Language Model (LALM) to assess the speech across multiple dimensions such as expressed emotion, prosodic, intonational, and pronunciation accuracy. We evaluate state-of-the-art open-source and proprietary TTS systems, such as 11Labs, Deepgram, and OpenAI's 4o-mini-TTS, on EmergentTTS-Eval, demonstrating its ability to reveal fine-grained performance differences. Results show that the model-as-a-judge approach offers robust TTS assessment and a high correlation with human preferences. We open source the evaluation https://github.com/boson-ai/EmergentTTS-Eval-public{code} and the https://huggingface.co/datasets/bosonai/EmergentTTS-Eval{dataset}.</p> + https://arxiv.org/abs/2505.23009 + Thu, 29 May 2025 02:36:24 +0000 - MMMR: Benchmarking Massive Multi-Modal Reasoning Tasks - https://arxiv.org/abs/2505.16459 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16459.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guiyao Tie, Xueyang Zhou, Tianhe Gu, Ruihang Zhang, Chaoran Hu, Sizhe Zhang, Mengqu Sun, Yan Zhang, Pan Zhou, Lichao Sun</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Recent advances in Multi-Modal Large Language Models (MLLMs) have enabled unified processing of language, vision, and structured inputs, opening the door to complex tasks such as logical deduction, spatial reasoning, and scientific analysis. Despite their promise, the reasoning capabilities of MLLMs, particularly those augmented with intermediate thinking traces (MLLMs-T), remain poorly understood and lack standardized evaluation benchmarks. Existing work focuses primarily on perception or final answer correctness, offering limited insight into how models reason or fail across modalities. To address this gap, we introduce the MMMR, a new benchmark designed to rigorously evaluate multi-modal reasoning with explicit thinking. The MMMR comprises 1) a high-difficulty dataset of 1,083 questions spanning six diverse reasoning types with symbolic depth and multi-hop demands and 2) a modular Reasoning Trace Evaluation Pipeline (RTEP) for assessing reasoning quality beyond accuracy through metrics like relevance, consistency, and structured error annotations. Empirical results show that MLLMs-T overall outperform non-thinking counterparts, but even top models like Claude-3.7-Sonnet and Gemini-2.5 Pro suffer from reasoning pathologies such as inconsistency and overthinking. This benchmark reveals persistent gaps between accuracy and reasoning quality and provides an actionable evaluation pipeline for future model development. Overall, the MMMR offers a scalable foundation for evaluating, comparing, and improving the next generation of multi-modal reasoning systems.</p> - https://arxiv.org/abs/2505.16459 - Thu, 22 May 2025 09:41:55 +0000 + From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval + https://arxiv.org/abs/2505.23059 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23059.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dohyeon Lee, Yeonseok Jeong, Seung-won Hwang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and semantically redundant traces with little or no benefit. We identify two key challenges in IR: redundant trajectories that revisit similar states and misguided reasoning that diverges from user intent. To address these, we propose State Machine Reasoning (SMR), a transition-based reasoning framework composed of discrete actions (Refine, Rerank, Stop) that support early stopping and fine-grained control. Experiments on the BEIR and BRIGHT benchmarks show that SMR improves retrieval performance (nDCG@10) by 3.4% while reducing token usage by 74.4%. It generalizes across LLMs and retrievers without requiring task-specific tuning, offering a practical alternative to conventional CoT reasoning. The code and details are available at https://github.com/ldilab/SMR.</p> + https://arxiv.org/abs/2505.23059 + Thu, 29 May 2025 04:04:25 +0000 - Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks - https://arxiv.org/abs/2505.16901 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.16901.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongyuan Tao, Ying Zhang, Zhenhao Tang, Hongen Peng, Xukun Zhu, Bingchang Liu, Yingguang Yang, Ziyin Zhang, Zhaogui Xu, Haipeng Zhang, Linchao Zhu, Rui Wang, Hang Yu, Jianguo Li, Peng Di</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability and limit accessibility, raising concerns about data privacy and model customization. This paper investigates whether open-source LLMs can effectively address repository-level tasks without requiring agent-based approaches. We demonstrate this is possible by enabling LLMs to comprehend functions and files within codebases through their semantic information and structural dependencies. To this end, we introduce Code Graph Models (CGMs), which integrate repository code graph structures into the LLM's attention mechanism and map node attributes to the LLM's input space using a specialized adapter. When combined with an agentless graph RAG framework, our approach achieves a 43.00% resolution rate on the SWE-bench Lite benchmark using the open-source Qwen2.5-72B model. This performance ranks first among open weight models, second among methods with open-source systems, and eighth overall, surpassing the previous best open-source model-based method by 12.33%.</p> - https://arxiv.org/abs/2505.16901 - Thu, 22 May 2025 17:00:55 +0000 + DINGO: Constrained Inference for Diffusion LLMs + https://arxiv.org/abs/2505.23061 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23061.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tarun Suresh, Debangshu Banerjee, Shubham Ugare, Sasa Misailovic, Gagandeep Singh</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffusion models lack the ability to provably enforce user-specified formal constraints, such as regular expressions, which makes them unreliable for tasks that require structured outputs, such as fixed-schema JSON generation. Unlike autoregressive models that generate tokens sequentially, diffusion LLMs predict a block of tokens in parallel. This parallelism makes traditional constrained decoding algorithms, which are designed for sequential token prediction, ineffective at preserving the true output distribution. To address this limitation, we propose DINGO, a dynamic programming-based constrained decoding strategy that is both efficient and provably distribution-preserving. DINGO enables sampling of output strings with the highest probability under the model's predicted distribution, while strictly satisfying any user-specified regular expression. On standard symbolic math and JSON generation benchmarks, DINGO achieves up to a 68 percentage point improvement over unconstrained inference</p> + https://arxiv.org/abs/2505.23061 + Thu, 29 May 2025 04:04:54 +0000 - Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models - https://arxiv.org/abs/2505.17225 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17225.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Doohyuk Jang, Yoonjeon Kim, Chanjae Park, Hyun Ryu, Eunho Yang</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Large language models have demonstrated remarkable proficiency in long and complex reasoning tasks. However, they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term reasoning rigidity. Despite explicit instructions from users, these models often override clearly stated conditions and default to habitual reasoning trajectories, leading to incorrect conclusions. This behavior presents significant challenges, particularly in domains such as mathematics and logic puzzle, where precise adherence to specified constraints is critical. To systematically investigate reasoning rigidity, a behavior largely unexplored in prior work, we introduce a expert-curated diagnostic set, . Our dataset includes specially modified variants of existing mathematical benchmarks, namely AIME and MATH500, as well as well-known puzzles deliberately redesigned to require deviation from familiar reasoning strategies. Using this dataset, we identify recurring contamination patterns that occur when models default to ingrained reasoning. Specifically, we categorize this contamination into three distinctive modes: (i) Interpretation Overload, (ii) Input Distrust, and (iii) Partial Instruction Attention, each causing models to ignore or distort provided instructions. We publicly release our diagnostic set to facilitate future research on mitigating reasoning rigidity in language models.</p> - https://arxiv.org/abs/2505.17225 - Thu, 22 May 2025 19:00:01 +0000 + Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles + https://arxiv.org/abs/2505.23590 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zifu Wang, Junyi Zhu, Bo Tang, Zhiyu Li, Feiyu Xiong, Jiaqian Yu, Matthew B. Blaschko</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This paper provides a comprehensive study of rule-based visual RL, using jigsaw puzzles as a structured experimental framework. Jigsaw puzzles offer inherent ground truth, adjustable difficulty, and demand complex decision-making, making them ideal for this study. Our research reveals several key findings: Firstly, we find that MLLMs, initially performing near to random guessing on the simplest jigsaw puzzles, achieve near-perfect accuracy and generalize to complex, unseen configurations through fine-tuning. Secondly, training on jigsaw puzzles can induce generalization to other visual tasks, with effectiveness tied to specific task configurations. Thirdly, MLLMs can learn and generalize with or without explicit reasoning, though open-source models often favor direct answering. Consequently, even when trained for step-by-step reasoning, they can ignore the thinking process in deriving the final answer. Fourthly, we observe that complex reasoning patterns appear to be pre-existing rather than emergent, with their frequency increasing alongside training and task difficulty. Finally, our results demonstrate that RL exhibits more effective generalization than Supervised Fine-Tuning (SFT), and an initial SFT cold start phase can hinder subsequent RL optimization. Although these observations are based on jigsaw puzzles and may vary across other visual tasks, this research contributes a valuable piece of jigsaw to the larger puzzle of collective understanding rule-based visual RL and its potential in multimodal learning. The code is available at: https://github.com/zifuwanggg/Jigsaw-R1.</p> + https://arxiv.org/abs/2505.23590 + Thu, 29 May 2025 16:01:22 +0000 - FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding - https://arxiv.org/abs/2505.17330 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amit Agarwal, Srikant Panda, Kulbhushan Pachauri</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> In this work, we propose Few Shot Domain Adapting Graph (FS-DAG), a scalable and efficient model architecture for visually rich document understanding (VRDU) in few-shot settings. FS-DAG leverages domain-specific and language/vision specific backbones within a modular framework to adapt to diverse document types with minimal data. The model is robust to practical challenges such as handling OCR errors, misspellings, and domain shifts, which are critical in real-world deployments. FS-DAG is highly performant with less than 90M parameters, making it well-suited for complex real-world applications for Information Extraction (IE) tasks where computational resources are limited. We demonstrate FS-DAG's capability through extensive experiments for information extraction task, showing significant improvements in convergence speed and performance compared to state-of-the-art methods. Additionally, this work highlights the ongoing progress in developing smaller, more efficient models that do not compromise on performance. Code : https://github.com/oracle-samples/fs-dag</p> - https://arxiv.org/abs/2505.17330 - Thu, 22 May 2025 22:53:58 +0000 + Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics + https://arxiv.org/abs/2506.00070 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyoung Kim, Sumin Park, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using Supervised Fine-Tuning (SFT). However, SFT datasets are often heuristically constructed and not explicitly optimized for improving robot control. Furthermore, SFT often leads to issues such as catastrophic forgetting and reduced generalization performance. To address these limitations, we introduce Robot-R1, a novel framework that leverages reinforcement learning to enhance embodied reasoning specifically for robot control. Robot-R1 learns to predict the next keypoint state required for task completion, conditioned on the current scene image and environment metadata derived from expert demonstrations. Inspired by the DeepSeek-R1 learning approach, Robot-R1 samples reasoning-based responses and reinforces those that lead to more accurate predictions. Our experiments show that models trained with Robot-R1 outperform SFT methods on embodied reasoning tasks. Despite having only 7B parameters, Robot-R1 even surpasses GPT-4o on reasoning tasks related to low-level action control, such as spatial and primitive movement reasoning.</p> + https://arxiv.org/abs/2506.00070 + Thu, 29 May 2025 16:41:12 +0000 - SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use - https://arxiv.org/abs/2505.17332 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17332.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hitesh Laxmichand Patel, Amit Agarwal, Arion Das, Bhargava Kumar, Srikant Panda, Priyaranjan Pattnayak, Taki Hasan Rafi, Tejaswini Kumar, Dong-Kyu Chae</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Enterprise customers are increasingly adopting Large Language Models (LLMs) for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions requires them to understand diverse cultural and linguistic contexts and generate safe and respectful responses. For enterprise applications, it is crucial to mitigate reputational risks, maintain trust, and ensure compliance by effectively identifying and handling unsafe or offensive language. To address this, we introduce SweEval, a benchmark simulating real-world scenarios with variations in tone (positive or negative) and context (formal or informal). The prompts explicitly instruct the model to include specific swear words while completing the task. This benchmark evaluates whether LLMs comply with or resist such inappropriate instructions and assesses their alignment with ethical frameworks, cultural nuances, and language comprehension capabilities. In order to advance research in building ethically aligned AI systems for enterprise use and beyond, we release the dataset and code: https://github.com/amitbcp/multilingual_profanity.</p> - https://arxiv.org/abs/2505.17332 - Thu, 22 May 2025 22:56:58 +0000 + VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models + https://arxiv.org/abs/2505.23656 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23656.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangdong Zhang, Jiaqi Liao, Shaofeng Zhang, Fanqing Meng, Xiangpeng Wan, Junchi Yan, Yu Cheng</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Recent advancements in text-to-video (T2V) diffusion models have enabled high-fidelity and realistic video synthesis. However, current T2V models often struggle to generate physically plausible content due to their limited inherent ability to accurately understand physics. We found that while the representations within T2V models possess some capacity for physics understanding, they lag significantly behind those from recent video self-supervised learning methods. To this end, we propose a novel framework called VideoREPA, which distills physics understanding capability from video understanding foundation models into T2V models by aligning token-level relations. This closes the physics understanding gap and enable more physics-plausible generation. Specifically, we introduce the Token Relation Distillation (TRD) loss, leveraging spatio-temporal alignment to provide soft guidance suitable for finetuning powerful pre-trained T2V models, a critical departure from prior representation alignment (REPA) methods. To our knowledge, VideoREPA is the first REPA method designed for finetuning T2V models and specifically for injecting physical knowledge. Empirical evaluations show that VideoREPA substantially enhances the physics commonsense of baseline method, CogVideoX, achieving significant improvement on relevant benchmarks and demonstrating a strong capacity for generating videos consistent with intuitive physics. More video results are available at https://videorepa.github.io/.</p> + https://arxiv.org/abs/2505.23656 + Thu, 29 May 2025 17:06:44 +0000 - Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention - https://arxiv.org/abs/2505.17412 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17412.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Wu, Youtian Lin, Feihu Zhang, Yifei Zeng, Yikang Yang, Yajie Bao, Jiachen Qian, Siyu Zhu, Philip Torr, Xun Cao, Yao Yao</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Generating high resolution 3D shapes using volumetric representations such as Signed Distance Functions presents substantial computational and memory challenges. We introduce Direct3D S2, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the Spatial Sparse Attention mechanism, which greatly enhances the efficiency of Diffusion Transformer computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, significantly reducing computational overhead and achieving a 3.9x speedup in the forward pass and a 9.6x speedup in the backward pass. Our framework also includes a variational autoencoder that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that Direct3D S2 not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables training at 1024 resolution using only 8 GPUs, a task typically requiring at least 32 GPUs for volumetric representations at 256 resolution, thus making gigascale 3D generation both practical and accessible. Project page: https://nju3dv.github.io/projects/Direct3D-S2/.</p> - https://arxiv.org/abs/2505.17412 - Fri, 23 May 2025 02:58:01 +0000 + Cora: Correspondence-aware image editing using few step diffusion + https://arxiv.org/abs/2505.23907 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23907.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhossein Almohammadi, Aryan Mikaeili, Sauradip Nag, Negar Hassanpour, Andrea Tagliasacchi, Ali Mahdavi-Amiri</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging. Existing few step editing approaches produce artifacts such as irrelevant texture or struggle to preserve key attributes of the source image (e.g., pose). We introduce Cora, a novel editing framework that addresses these limitations by introducing correspondence-aware noise correction and interpolated attention maps. Our method aligns textures and structures between the source and target images through semantic correspondence, enabling accurate texture transfer while generating new content when necessary. Cora offers control over the balance between content generation and preservation. Extensive experiments demonstrate that, quantitatively and qualitatively, Cora excels in maintaining structure, textures, and identity across diverse edits, including pose changes, object addition, and texture refinements. User studies confirm that Cora delivers superior results, outperforming alternatives.</p> + https://arxiv.org/abs/2505.23907 + Thu, 29 May 2025 18:00:56 +0000 - Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model - https://arxiv.org/abs/2505.17561 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17561.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kwanyoung Kim, Sanghyun Kim</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The choice of initial noise significantly affects the quality and prompt alignment of video diffusion models, where different noise seeds for the same prompt can lead to drastically different generations. While recent methods rely on externally designed priors such as frequency filters or inter-frame smoothing, they often overlook internal model signals that indicate which noise seeds are inherently preferable. To address this, we propose ANSE (Active Noise Selection for Generation), a model-aware framework that selects high-quality noise seeds by quantifying attention-based uncertainty. At its core is BANSA (Bayesian Active Noise Selection via Attention), an acquisition function that measures entropy disagreement across multiple stochastic attention samples to estimate model confidence and consistency. For efficient inference-time deployment, we introduce a Bernoulli-masked approximation of BANSA that enables score estimation using a single diffusion step and a subset of attention layers. Experiments on CogVideoX-2B and 5B demonstrate that ANSE improves video quality and temporal coherence with only an 8% and 13% increase in inference time, respectively, providing a principled and generalizable approach to noise selection in video diffusion. See our project page: https://anse-project.github.io/anse-project/</p> - https://arxiv.org/abs/2505.17561 - Fri, 23 May 2025 07:09:10 +0000 + Vision Language Models are Biased + https://arxiv.org/abs/2505.23941 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, Daeyoung Kim</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that help them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g, unable to recognize a fourth stripe has been added to a 3-stripe Adidas logo) scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains from animals, logos, chess, board games, optical illusions, to patterned grids. Insert text (e.g., "Adidas") describing the subject name into the counterfactual image further decreases VLM accuracy. The biases in VLMs are so strong that instructing them to double-check their results or rely exclusively on image details to answer improves counting accuracy by only +2 points, on average. Our work presents an interesting failure mode in VLMs and an automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.</p> + https://arxiv.org/abs/2505.23941 + Thu, 29 May 2025 18:47:58 +0000 - Distilling LLM Agent into Small Models with Retrieval and Code Tools - https://arxiv.org/abs/2505.17612 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17612.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minki Kang, Jongwon Jeong, Seanie Lee, Jaewoong Cho, Sung Ju Hwang</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused on distilling reasoning capabilities into smaller language models (sLMs) using chain-of-thought (CoT) traces from teacher LLMs. However, this approach struggles in scenarios requiring rare factual knowledge or precise computation, where sLMs often hallucinate due to limited capability. In this work, we propose Agent Distillation, a framework for transferring not only reasoning capability but full task-solving behavior from LLM-based agents into sLMs with retrieval and code tools. We improve agent distillation along two complementary axes: (1) we introduce a prompting method called first-thought prefix to enhance the quality of teacher-generated trajectories; and (2) we propose a self-consistent action generation for improving test-time robustness of small agents. We evaluate our method on eight reasoning tasks across factual and mathematical domains, covering both in-domain and out-of-domain generalization. Our results show that sLMs as small as 0.5B, 1.5B, 3B parameters can achieve performance competitive with next-tier larger 1.5B, 3B, 7B models fine-tuned using CoT distillation, demonstrating the potential of agent distillation for building practical, tool-using small agents. Our code is available at https://github.com/Nardien/agent-distillation.</p> - https://arxiv.org/abs/2505.17612 - Fri, 23 May 2025 08:20:15 +0000 + DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models + https://arxiv.org/abs/2505.24025 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenbin Pan, Wenbin He, Zhengzhong Tu, Liu Ren</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based fine-tuning frameworks, exemplified by methods like Group Relative Policy Optimization (GRPO). However, such reasoning abilities remain underexplored and notably absent in vision foundation models, including representation models like the DINO series. In this work, we propose DINO-R1, the first such attempt to incentivize visual in-context reasoning capabilities of vision foundation models using reinforcement learning. Specifically, DINO-R1 introduces Group Relative Query Optimization (GRQO), a novel reinforcement-style training strategy explicitly designed for query-based representation models, which computes query-level rewards based on group-normalized alignment quality. We also apply KL-regularization to stabilize the objectness distribution to reduce the training instability. This joint optimization enables dense and expressive supervision across queries while mitigating overfitting and distributional drift. Building upon Grounding-DINO, we train a series of DINO-R1 family models that integrate a visual prompt encoder and a visual-guided query selection mechanism. Extensive experiments on COCO, LVIS, and ODinW demonstrate that DINO-R1 significantly outperforms supervised fine-tuning baselines, achieving strong generalization in both open-vocabulary and closed-set visual prompting scenarios.</p> + https://arxiv.org/abs/2505.24025 + Thu, 29 May 2025 21:58:06 +0000 - Scaling Image and Video Generation via Test-Time Evolutionary Search - https://arxiv.org/abs/2505.17618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran He, Jiajun Liang, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Ling Pan</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising direction for improving generative model performance by allocating additional computation at inference time. While TTS has demonstrated significant success across multiple language tasks, there remains a notable gap in understanding the test-time scaling behaviors of image and video generative models (diffusion-based or flow-based models). Although recent works have initiated exploration into inference-time strategies for vision tasks, these approaches face critical limitations: being constrained to task-specific domains, exhibiting poor scalability, or falling into reward over-optimization that sacrifices sample diversity. In this paper, we propose Evolutionary Search (EvoSearch), a novel, generalist, and efficient TTS method that effectively enhances the scalability of both image and video generation across diffusion and flow models, without requiring additional training or model expansion. EvoSearch reformulates test-time scaling for diffusion and flow models as an evolutionary search problem, leveraging principles from biological evolution to efficiently explore and refine the denoising trajectory. By incorporating carefully designed selection and mutation mechanisms tailored to the stochastic differential equation denoising process, EvoSearch iteratively generates higher-quality offspring while preserving population diversity. Through extensive evaluation across both diffusion and flow architectures for image and video generation tasks, we demonstrate that our method consistently outperforms existing approaches, achieves higher diversity, and shows strong generalizability to unseen evaluation metrics. Our project is available at the website https://tinnerhrhe.github.io/evosearch.</p> - https://arxiv.org/abs/2505.17618 - Fri, 23 May 2025 08:25:46 +0000 + HardTests: Synthesizing High-Quality Test Cases for LLM Coding + https://arxiv.org/abs/2505.24098 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24098.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongmou He, Yee Man Choi, Kexun Zhang, Jiabao Ji, Junting Zhou, Dejia Xu, Ivan Bercovich, Aidan Zhang, Lei Li</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.</p> + https://arxiv.org/abs/2505.24098 + Fri, 30 May 2025 01:00:34 +0000 - QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning - https://arxiv.org/abs/2505.17667 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li, Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 81</p><p><b>Summary:</b> Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs to effectively process and reason on long-context inputs via RL remains a critical unsolved challenge. To bridge this gap, we first formalize the paradigm of long-context reasoning RL, and identify key challenges in suboptimal training efficiency and unstable optimization process. To address these issues, we propose QwenLong-L1, a framework that adapts short-context LRMs to long-context scenarios via progressive context scaling. Specifically, we utilize a warm-up supervised fine-tuning (SFT) stage to establish a robust initial policy, followed by a curriculum-guided phased RL technique to stabilize the policy evolution, and enhanced with a difficulty-aware retrospective sampling strategy to incentivize the policy exploration. Experiments on seven long-context document question-answering benchmarks demonstrate that QwenLong-L1-32B outperforms flagship LRMs like OpenAI-o3-mini and Qwen3-235B-A22B, achieving performance on par with Claude-3.7-Sonnet-Thinking, demonstrating leading performance among state-of-the-art LRMs. This work advances the development of practical long-context LRMs capable of robust reasoning across information-intensive environments.</p> - https://arxiv.org/abs/2505.17667 - Fri, 23 May 2025 09:31:55 +0000 + CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs + https://arxiv.org/abs/2505.24120 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ai Jian, Weijie Qiu, Xiaokun Wang, Peiyu Wang, Yunzhuo Hao, Jiangbo Pei, Yichen Wei, Yi Peng, Xuchen Song</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal understanding, yet their capabilities for scientific reasoning remains inadequately assessed. Current multimodal benchmarks predominantly evaluate generic image comprehension or text-driven reasoning, lacking authentic scientific contexts that require domain-specific knowledge integration with visual evidence analysis. To fill this gap, we present CSVQA, a diagnostic multimodal benchmark specifically designed for evaluating scientific reasoning through domain-grounded visual question answering.Our benchmark features 1,378 carefully constructed question-answer pairs spanning diverse STEM disciplines, each demanding domain knowledge, integration of visual evidence, and higher-order reasoning. Compared to prior multimodal benchmarks, CSVQA places greater emphasis on real-world scientific content and complex reasoning.We additionally propose a rigorous evaluation protocol to systematically assess whether model predictions are substantiated by valid intermediate reasoning steps based on curated explanations. Our comprehensive evaluation of 15 VLMs on this benchmark reveals notable performance disparities, as even the top-ranked proprietary model attains only 49.6\% accuracy.This empirical evidence underscores the pressing need for advancing scientific reasoning capabilities in VLMs. Our CSVQA is released at https://huggingface.co/datasets/Skywork/CSVQA.</p> + https://arxiv.org/abs/2505.24120 + Fri, 30 May 2025 01:34:25 +0000 - Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning - https://arxiv.org/abs/2505.17813 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17813.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Michael Hassid, Gabriel Synnaeve, Yossi Adi, Roy Schwartz</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant computational costs and inference time. In this work, we challenge the assumption that long thinking chains results in better reasoning capabilities. We first demonstrate that shorter reasoning chains within individual questions are significantly more likely to yield correct answers - up to 34.5% more accurate than the longest chain sampled for the same question. Based on these results, we suggest short-m@k, a novel reasoning LLM inference method. Our method executes k independent generations in parallel and halts computation once the first m thinking processes are done. The final answer is chosen using majority voting among these m chains. Basic short-1@k demonstrates similar or even superior performance over standard majority voting in low-compute settings - using up to 40% fewer thinking tokens. short-3@k, while slightly less efficient than short-1@k, consistently surpasses majority voting across all compute budgets, while still being substantially faster (up to 33% wall time reduction). Inspired by our results, we finetune an LLM using short, long, and randomly selected reasoning chains. We then observe that training on the shorter ones leads to better performance. Our findings suggest rethinking current methods of test-time compute in reasoning LLMs, emphasizing that longer "thinking" does not necessarily translate to improved performance and can, counter-intuitively, lead to degraded results.</p> - https://arxiv.org/abs/2505.17813 - Fri, 23 May 2025 12:29:06 +0000 + CLaSp: In-Context Layer Skip for Self-Speculative Decoding + https://arxiv.org/abs/2505.24196 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Longze Chen, Renke Shan, Huiming Wang, Lu Wang, Ziqiang Liu, Run Luo, Jiawei Wang, Hamid Alinejad-Rokny, Min Yang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing drafting approaches typically require additional modules to be trained, which can be challenging to implement and ensure compatibility across various LLMs. In this paper, we propose CLaSp, an in-context layer-skipping strategy for self-speculative decoding. Unlike prior methods, CLaSp does not require additional drafting modules or extra training. Instead, it employs a plug-and-play mechanism by skipping intermediate layers of the verify model to construct a compressed draft model. Specifically, we develop a dynamic programming algorithm that optimizes the layer-skipping process by leveraging the complete hidden states from the last verification stage as an objective. This enables CLaSp to dynamically adjust its layer-skipping strategy after each verification stage, without relying on pre-optimized sets of skipped layers. Experimental results across diverse downstream tasks demonstrate that CLaSp achieves a speedup of 1.3x ~ 1.7x on LLaMA3 series models without altering the original distribution of the generated text.</p> + https://arxiv.org/abs/2505.24196 + Fri, 30 May 2025 04:15:06 +0000 - MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback - https://arxiv.org/abs/2505.17873 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17873.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanhao Liu, Zonglin Yang, Jue Wang, Lidong Bing, Di Zhang, Dongzhan Zhou, Yuqiang Li, Houqiang Li, Erik Cambria, Wanli Ouyang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Hypothesis ranking is a crucial component of automated scientific discovery, particularly in natural sciences where wet-lab experiments are costly and throughput-limited. Existing approaches focus on pre-experiment ranking, relying solely on large language model's internal reasoning without incorporating empirical outcomes from experiments. We introduce the task of experiment-guided ranking, which aims to prioritize candidate hypotheses based on the results of previously tested ones. However, developing such strategies is challenging due to the impracticality of repeatedly conducting real experiments in natural science domains. To address this, we propose a simulator grounded in three domain-informed assumptions, modeling hypothesis performance as a function of similarity to a known ground truth hypothesis, perturbed by noise. We curate a dataset of 124 chemistry hypotheses with experimentally reported outcomes to validate the simulator. Building on this simulator, we develop a pseudo experiment-guided ranking method that clusters hypotheses by shared functional characteristics and prioritizes candidates based on insights derived from simulated experimental feedback. Experiments show that our method outperforms pre-experiment baselines and strong ablations.</p> - https://arxiv.org/abs/2505.17873 - Fri, 23 May 2025 13:24:50 +0000 + Large Language Models are Locally Linear Mappings + https://arxiv.org/abs/2505.24293 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24293.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James R. Golden</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We demonstrate that the inference operations of several open-weight large language models (LLMs) can be mapped to an exactly equivalent linear system for an input sequence without modifying the model weights or altering output predictions. Extending techniques from image diffusion models that exhibit local or piecewise linearity, we strategically alter the gradient computation with respect to a given input sequence for a next-token prediction such that the Jacobian of the model nearly exactly reproduces the forward prediction with a linear system. We demonstrate this approach across models (Llama 3, Gemma 3, Qwen 3, Phi 4, Mistral Ministral and OLMo 2, up to Llama 3.3 70B Q4) and show through the singular value decomposition of the detached Jacobian that these LLMs operate in extremely low-dimensional subspaces where many of the largest singular vectors decode to concepts related to the most-likely output token. This approach also allows us to examine the operation of each successive layer (and its attention and MLP components) as nearly-exact linear systems and observe the emergence of semantic concepts. Despite their expressive power and global nonlinearity, modern LLMs can be interpreted through nearly-exact locally linear decompositions that provide insights into their internal representations and reveal interpretable semantic structures in the next-token prediction process.</p> + https://arxiv.org/abs/2505.24293 + Fri, 30 May 2025 07:08:33 +0000 - Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model - https://arxiv.org/abs/2505.17894 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17894.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Khalil Hennara, Muhammad Hreden, Mohamed Motaism Hamed, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan</p><p><b>Upvotes:</b> 209</p><p><b>Summary:</b> We introduce Mutarjim, a compact yet powerful language model for bidirectional Arabic-English translation. While large-scale LLMs have shown impressive progress in natural language processing tasks, including machine translation, smaller models. Leveraging this insight, we developed Mutarjim based on Kuwain-1.5B , a language model tailored for both Arabic and English. Despite its modest size, Mutarjim outperforms much larger models on several established benchmarks, achieved through an optimized two-phase training approach and a carefully curated, high-quality training corpus.. Experimental results show that Mutarjim rivals models up to 20 times larger while significantly reducing computational costs and training requirements. We also introduce Tarjama-25, a new benchmark designed to overcome limitations in existing Arabic-English benchmarking datasets, such as domain narrowness, short sentence lengths, and English-source bias. Tarjama-25 comprises 5,000 expert-reviewed sentence pairs and spans a wide range of domains, offering a more comprehensive and balanced evaluation framework. Notably, Mutarjim achieves state-of-the-art performance on the English-to-Arabic task in Tarjama-25, surpassing even significantly larger and proprietary models like GPT-4o mini. We publicly release Tarjama-25 to support future research and advance the evaluation of Arabic-English translation systems.</p> - https://arxiv.org/abs/2505.17894 - Fri, 23 May 2025 13:42:21 +0000 + AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning + https://arxiv.org/abs/2505.24298 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24298.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Fu, Jiaxuan Gao, Xujie Shen, Chen Zhu, Zhiyu Mei, Chuyi He, Shusheng Xu, Guo Wei, Jun Mei, Jiashu Wang, Tongkai Yang, Binhang Yuan, Yi Wu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Reinforcement learning (RL) has become a trending paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous by alternating generation and training in a batch setting, where the rollouts in each training batch are generated by the same (or latest) model. This stabilizes RL training but suffers from severe system-level inefficiency. Generation must wait until the longest output in the batch is completed before model update, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.57times training speedup compared to the best synchronous systems with the same number of GPUs and matched or even improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.</p> + https://arxiv.org/abs/2505.24298 + Fri, 30 May 2025 07:18:25 +0000 - VeriThinker: Learning to Verify Makes Reasoning Model Efficient - https://arxiv.org/abs/2505.17941 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zigeng Chen, Xinyin Ma, Gongfan Fang, Ruonan Yu, Xinchao Wang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Large Reasoning Models (LRMs) excel at complex tasks using Chain-of-Thought (CoT) reasoning. However, their tendency to overthinking leads to unnecessarily lengthy reasoning chains, dramatically increasing inference costs. To mitigate this issue, we introduce VeriThinker, a novel approach for CoT compression. Unlike conventional methods that fine-tune LRMs directly on the original reasoning task using synthetic concise CoT data, we innovatively fine-tune the model solely through an auxiliary verification task. By training LRMs to accurately verify the correctness of CoT solutions, the LRMs inherently become more discerning about the necessity of subsequent self-reflection steps, thereby effectively suppressing overthinking. Extensive experiments validate that VeriThinker substantially reduces reasoning chain lengths while maintaining or even slightly improving accuracy. When applied to DeepSeek-R1-Distill-Qwen-7B, our approach reduces reasoning tokens on MATH500 from 3790 to 2125 while improving accuracy by 0.8% (94.0% to 94.8%), and on AIME25, tokens decrease from 14321 to 10287 with a 2.1% accuracy gain (38.7% to 40.8%). Additionally, our experiments demonstrate that VeriThinker can also be zero-shot generalized to speculative reasoning. Code is available at https://github.com/czg1225/VeriThinker</p> - https://arxiv.org/abs/2505.17941 - Fri, 23 May 2025 14:17:56 +0000 + EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering + https://arxiv.org/abs/2505.24417 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24417.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runnan Lu, Yuxuan Zhang, Jailing Liu, Haifa Wang, Yiren Song</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an unexplored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.</p> + https://arxiv.org/abs/2505.24417 + Fri, 30 May 2025 09:55:39 +0000 - Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL - https://arxiv.org/abs/2505.17952 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17952.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Che Liu, Haozhe Wang, Jiazhen Pan, Zhongwei Wan, Yong Dai, Fangzhen Lin, Wenjia Bai, Daniel Rueckert, Rossella Arcucci</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Improving performance on complex tasks and enabling interpretable decision making in large language models (LLMs), especially for clinical applications, requires effective reasoning. Yet this remains challenging without supervised fine-tuning (SFT) on costly chain-of-thought (CoT) data distilled from closed-source models (e.g., GPT-4o). In this work, we present AlphaMed, the first medical LLM to show that reasoning capability can emerge purely through reinforcement learning (RL), using minimalist rule-based rewards on public multiple-choice QA datasets, without relying on SFT or distilled CoT data. AlphaMed achieves state-of-the-art results on six medical QA benchmarks, outperforming models trained with conventional SFT+RL pipelines. On challenging benchmarks (e.g., MedXpert), AlphaMed even surpasses larger or closed-source models such as DeepSeek-V3-671B and Claude-3.5-Sonnet. To understand the factors behind this success, we conduct a comprehensive data-centric analysis guided by three questions: (i) Can minimalist rule-based RL incentivize reasoning without distilled CoT supervision? (ii) How do dataset quantity and diversity impact reasoning? (iii) How does question difficulty shape the emergence and generalization of reasoning? Our findings show that dataset informativeness is a key driver of reasoning performance, and that minimalist RL on informative, multiple-choice QA data is effective at inducing reasoning without CoT supervision. We also observe divergent trends across benchmarks, underscoring limitations in current evaluation and the need for more challenging, reasoning-oriented medical QA benchmarks.</p> - https://arxiv.org/abs/2505.17952 - Fri, 23 May 2025 14:27:37 +0000 + UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation + https://arxiv.org/abs/2505.24521 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24521.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang-Tian Sun, Xin Yu, Zehuan Huang, Yi-Hua Huang, Yuan-Chen Guo, Ziyi Yang, Yan-Pei Cao, Xiaojuan Qi</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generalization ability. However, most existing works focus on estimating geometric properties within the camera coordinate system of individual video frames, neglecting the inherent ability of diffusion models to determine inter-frame correspondence. In this work, we demonstrate that, through appropriate design and fine-tuning, the intrinsic consistency of video generation models can be effectively harnessed for consistent geometric estimation. Specifically, we 1) select geometric attributes in the global coordinate system that share the same correspondence with video frames as the prediction targets, 2) introduce a novel and efficient conditioning method by reusing positional encodings, and 3) enhance performance through joint training on multiple geometric attributes that share the same correspondence. Our results achieve superior performance in predicting global geometric attributes in videos and can be directly applied to reconstruction tasks. Even when trained solely on static video data, our approach exhibits the potential to generalize to dynamic video scenes.</p> + https://arxiv.org/abs/2505.24521 + Fri, 30 May 2025 12:31:59 +0000 - Diffusion Classifiers Understand Compositionality, but Conditions Apply - https://arxiv.org/abs/2505.17955 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.17955.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujin Jeong, Arnas Uselis, Seong Joon Oh, Anna Rohrbach</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image diffusion models excel at synthesizing complex scenes, suggesting inherent compositional capabilities. Building on this, zero-shot diffusion classifiers have been proposed to repurpose diffusion models for discriminative tasks. While prior work offered promising results in discriminative compositional scenarios, these results remain preliminary due to a small number of benchmarks and a relatively shallow analysis of conditions under which the models succeed. To address this, we present a comprehensive study of the discriminative capabilities of diffusion classifiers on a wide range of compositional tasks. Specifically, our study covers three diffusion models (SD 1.5, 2.0, and, for the first time, 3-m) spanning 10 datasets and over 30 tasks. Further, we shed light on the role that target dataset domains play in respective performance; to isolate the domain effects, we introduce a new diagnostic benchmark Self-Bench comprised of images created by diffusion models themselves. Finally, we explore the importance of timestep weighting and uncover a relationship between domain gap and timestep sensitivity, particularly for SD3-m. To sum up, diffusion classifiers understand compositionality, but conditions apply! Code and dataset are available at https://github.com/eugene6923/Diffusion-Classifiers-Compositionality.</p> - https://arxiv.org/abs/2505.17955 - Fri, 23 May 2025 14:29:52 +0000 + FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation + https://arxiv.org/abs/2505.24714 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24714.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized multimodal evaluation datasets. To advance the development of MLLMs in the finance domain, we introduce FinMME, encompassing more than 11,000 high-quality financial research samples across 18 financial domains and 6 asset classes, featuring 10 major chart types and 21 subtypes. We ensure data quality through 20 annotators and carefully designed validation mechanisms. Additionally, we develop FinScore, an evaluation system incorporating hallucination penalties and multi-dimensional capability assessment to provide an unbiased evaluation. Extensive experimental results demonstrate that even state-of-the-art models like GPT-4o exhibit unsatisfactory performance on FinMME, highlighting its challenging nature. The benchmark exhibits high robustness with prediction variations under different prompts remaining below 1%, demonstrating superior reliability compared to existing datasets. Our dataset and evaluation protocol are available at https://huggingface.co/datasets/luojunyu/FinMME and https://github.com/luo-junyu/FinMME.</p> + https://arxiv.org/abs/2505.24714 + Fri, 30 May 2025 15:36:19 +0000 - QwenLong-CPRS: Towards infty-LLMs with Dynamic Context Optimization - https://arxiv.org/abs/2505.18092 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18092.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhou Shen, Chenliang Li, Fanqi Wan, Shengyi Liao, Shaopeng Lai, Bo Zhang, Yingcheng Shi, Yuning Wu, Gang Fu, Zhansheng Li, Bin Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> This technical report presents QwenLong-CPRS, a context compression framework designed for explicit long-context optimization, addressing prohibitive computation overhead during the prefill stage and the "lost in the middle" performance degradation of large language models (LLMs) during long sequence processing. Implemented through a novel dynamic context optimization mechanism, QwenLong-CPRS enables multi-granularity context compression guided by natural language instructions, achieving both efficiency gains and improved performance. Evolved from the Qwen architecture series, QwenLong-CPRS introduces four key innovations: (1) Natural language-guided dynamic optimization, (2) Bidirectional reasoning layers for enhanced boundary awareness, (3) Token critic mechanisms with language modeling heads, and (4) Window-parallel inference. Comprehensive evaluations across five benchmarks (4K-2M word contexts) demonstrate QwenLong-CPRS's threefold effectiveness: (1) Consistent superiority over other context management methods like RAG and sparse attention in both accuracy and efficiency. (2) Architecture-agnostic integration with all flagship LLMs, including GPT-4o, Gemini2.0-pro, Claude3.7-sonnet, DeepSeek-v3, and Qwen2.5-max, achieves 21.59times context compression alongside 19.15-point average performance gains; (3) Deployed with Qwen2.5-32B-Instruct, QwenLong-CPRS surpasses leading proprietary LLMs by 4.85 and 10.88 points on Ruler-128K and InfiniteBench, establishing new SOTA performance.</p> - https://arxiv.org/abs/2505.18092 - Fri, 23 May 2025 16:47:00 +0000 + Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning + https://arxiv.org/abs/2505.24726 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24726.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shelly Bensal, Umar Jamil, Christopher Bryant, Melisa Russak, Kiran Kamble, Dmytro Mozolevskyi, Muayad Ali, Waseem AlShikh</p><p><b>Upvotes:</b> 171</p><p><b>Summary:</b> We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a model's ability to solve complex, verifiable tasks can be enhanced even when generating synthetic data is infeasible and only binary feedback is available. Our framework operates in two stages: first, upon failing a given task, the model generates a self-reflective commentary analyzing its previous attempt; second, the model is given another attempt at the task with the self-reflection in context. If the subsequent attempt succeeds, the tokens generated during the self-reflection phase are rewarded. Our experimental results show substantial performance gains across a variety of model architectures, as high as 34.7% improvement at math equation writing and 18.1% improvement at function calling. Notably, smaller fine-tuned models (1.5 billion to 7 billion parameters) outperform models in the same family that are 10 times larger. Our novel paradigm is thus an exciting pathway to more useful and reliable language models that can self-improve on challenging tasks with limited external feedback.</p> + https://arxiv.org/abs/2505.24726 + Fri, 30 May 2025 15:49:42 +0000 - TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations - https://arxiv.org/abs/2505.18125 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18125.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alan Arazi, Eilam Shapira, Roi Reichart</p><p><b>Upvotes:</b> 108</p><p><b>Summary:</b> While deep learning has achieved remarkable success across many domains, it has historically underperformed on tabular learning tasks, which remain dominated by gradient boosting decision trees (GBDTs). However, recent advancements are paving the way for Tabular Foundation Models, which can leverage real-world knowledge and generalize across diverse datasets, particularly when the data contains free-text. Although incorporating language model capabilities into tabular tasks has been explored, most existing methods utilize static, target-agnostic textual representations, limiting their effectiveness. We introduce TabSTAR: a Foundation Tabular Model with Semantically Target-Aware Representations. TabSTAR is designed to enable transfer learning on tabular data with textual features, with an architecture free of dataset-specific parameters. It unfreezes a pretrained text encoder and takes as input target tokens, which provide the model with the context needed to learn task-specific embeddings. TabSTAR achieves state-of-the-art performance for both medium- and large-sized datasets across known benchmarks of classification tasks with text features, and its pretraining phase exhibits scaling laws in the number of datasets, offering a pathway for further performance improvements.</p> - https://arxiv.org/abs/2505.18125 - Fri, 23 May 2025 17:34:28 +0000 + REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards + https://arxiv.org/abs/2505.24760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zafir Stojanovski, Oliver Stanley, Joe Sharratt, Richard Jones, Abdulhakeem Adefioye, Jean Kaddour, Andreas Köpf</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and various common games. Its key innovation is the ability to generate virtually infinite training data with adjustable complexity, unlike most previous reasoning datasets, which are typically fixed. This procedural generation approach allows for continuous evaluation across varying difficulty levels. Our experimental results demonstrate the efficacy of RG in both evaluating and reinforcement learning of reasoning models.</p> + https://arxiv.org/abs/2505.24760 + Fri, 30 May 2025 16:20:18 +0000 - One RL to See Them All: Visual Triple Unified Reinforcement Learning - https://arxiv.org/abs/2505.18129 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18129.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Ma, Linge Du, Xuyang Shen, Shaoxiang Chen, Pengfei Li, Qibing Ren, Lizhuang Ma, Yuchao Dai, Pengfei Liu, Junjie Yan</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Reinforcement learning (RL) has significantly advanced the reasoning capabilities of vision-language models (VLMs). However, the use of RL beyond reasoning tasks remains largely unexplored, especially for perceptionintensive tasks like object detection and grounding. We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables VLMs to jointly learn visual reasoning and perception tasks within a single training pipeline. V-Triune comprises triple complementary components: Sample-Level Data Formatting (to unify diverse task inputs), Verifier-Level Reward Computation (to deliver custom rewards via specialized verifiers) , and Source-Level Metric Monitoring (to diagnose problems at the data-source level). We further introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune. Our approach is instantiated within off-the-shelf RL training framework using open-source 7B and 32B backbone models. The resulting model, dubbed Orsta (One RL to See Them All), demonstrates consistent improvements across both reasoning and perception tasks. This broad capability is significantly shaped by its training on a diverse dataset, constructed around four representative visual reasoning tasks (Math, Puzzle, Chart, and Science) and four visual perception tasks (Grounding, Detection, Counting, and OCR). Subsequently, Orsta achieves substantial gains on MEGA-Bench Core, with improvements ranging from +2.1 to an impressive +14.1 across its various 7B and 32B model variants, with performance benefits extending to a wide range of downstream tasks. These results highlight the effectiveness and scalability of our unified RL approach for VLMs. The V-Triune system, along with the Orsta models, is publicly available at https://github.com/MiniMax-AI.</p> - https://arxiv.org/abs/2505.18129 - Fri, 23 May 2025 17:41:14 +0000 + EXP-Bench: Can AI Conduct AI Research Experiments? + https://arxiv.org/abs/2505.24785 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24785.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrick Tser Jern Kon, Jiachen Liu, Xinyi Zhu, Qiuyi Ding, Jingjia Peng, Jiarong Xing, Yibo Huang, Yiming Qiu, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, Matei Zaharia, Ang Chen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Automating AI research holds immense potential for accelerating scientific progress, yet current AI agents struggle with the complexities of rigorous, end-to-end experimentation. We introduce EXP-Bench, a novel benchmark designed to systematically evaluate AI agents on complete research experiments sourced from influential AI publications. Given a research question and incomplete starter code, EXP-Bench challenges AI agents to formulate hypotheses, design and implement experimental procedures, execute them, and analyze results. To enable the creation of such intricate and authentic tasks with high-fidelity, we design a semi-autonomous pipeline to extract and structure crucial experimental details from these research papers and their associated open-source code. With the pipeline, EXP-Bench curated 461 AI research tasks from 51 top-tier AI research papers. Evaluations of leading LLM-based agents, such as OpenHands and IterativeAgent on EXP-Bench demonstrate partial capabilities: while scores on individual experimental aspects such as design or implementation correctness occasionally reach 20-35%, the success rate for complete, executable experiments was a mere 0.5%. By identifying these bottlenecks and providing realistic step-by-step experiment procedures, EXP-Bench serves as a vital tool for future AI agents to improve their ability to conduct AI research experiments. EXP-Bench is open-sourced at https://github.com/Just-Curieous/Curie/tree/main/benchmark/exp_bench.</p> + https://arxiv.org/abs/2505.24785 + Fri, 30 May 2025 16:46:29 +0000 - Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence - https://arxiv.org/abs/2505.20325 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20325.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amirhosein Ghasemabadi, Keith G. Mills, Baochun Li, Di Niu</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs, primarily due to extensive reliance on external Process Reward Models (PRMs) or sampling methods like Best-of-N (BoN). This paper introduces Guided by Gut (GG), an efficient self-guided TTS framework that achieves PRM-level performance without costly external verifier models. Our method employs a lightweight tree search guided solely by intrinsic LLM signals, token-level confidence and step novelty. One critical innovation is improving the reliability of internal confidence estimates via a targeted reinforcement learning fine-tuning phase. Empirical evaluations on challenging mathematical reasoning benchmarks demonstrate that GG enables smaller models (e.g., 1.5B parameters) to achieve accuracy matching or surpassing significantly larger models (e.g., 32B-70B parameters), while reducing GPU memory usage by up to 10x. Compared to PRM-based methods, GG achieves comparable accuracy with 8x faster inference speeds and 4-5x lower memory usage. Additionally, GG reduces KV cache memory usage by approximately 50% compared to the BoN strategy, facilitating more efficient and practical deployment of TTS techniques.</p> - https://arxiv.org/abs/2505.20325 - Fri, 23 May 2025 18:19:09 +0000 + MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning + https://arxiv.org/abs/2505.24846 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences. Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment. Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error. While existing solutions, such as multi-objective learning with fine-grained annotations, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values. In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations. In the first stage, MiCRo introduces context-aware mixture modeling approach to capture diverse human preferences. In the second stage, MiCRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision. Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves downstream personalization.</p> + https://arxiv.org/abs/2505.24846 + Fri, 30 May 2025 17:44:28 +0000 - Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems - https://arxiv.org/abs/2505.18366 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hansa Meghwani, Amit Agarwal, Priyaranjan Pattnayak, Hitesh Laxmichand Patel, Srikant Panda</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge management, customer support, and retrieval-augmented generation agents. To address this challenge, we propose a scalable hard-negative mining framework tailored specifically for domain-specific enterprise data. Our approach dynamically selects semantically challenging but contextually irrelevant documents to enhance deployed re-ranking models. Our method integrates diverse embedding models, performs dimensionality reduction, and uniquely selects hard negatives, ensuring computational efficiency and semantic precision. Evaluation on our proprietary enterprise corpus (cloud services domain) demonstrates substantial improvements of 15\% in MRR@3 and 19\% in MRR@10 compared to state-of-the-art baselines and other negative sampling techniques. Further validation on public domain-specific datasets (FiQA, Climate Fever, TechQA) confirms our method's generalizability and readiness for real-world applications.</p> - https://arxiv.org/abs/2505.18366 - Fri, 23 May 2025 20:51:20 +0000 + MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs + https://arxiv.org/abs/2505.24858 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24858.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of faithful confidence calibration of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that faithfully reflect their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.</p> + https://arxiv.org/abs/2505.24858 + Fri, 30 May 2025 17:54:08 +0000 - OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data - https://arxiv.org/abs/2505.18445 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18445.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiren Song, Cheng Liu, Mike Zheng Shou</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Diffusion models have advanced image stylization significantly, yet two core challenges persist: (1) maintaining consistent stylization in complex scenes, particularly identity, composition, and fine details, and (2) preventing style degradation in image-to-image pipelines with style LoRAs. GPT-4o's exceptional stylization consistency highlights the performance gap between open-source methods and proprietary models. To bridge this gap, we propose OmniConsistency, a universal consistency plugin leveraging large-scale Diffusion Transformers (DiTs). OmniConsistency contributes: (1) an in-context consistency learning framework trained on aligned image pairs for robust generalization; (2) a two-stage progressive learning strategy decoupling style learning from consistency preservation to mitigate style degradation; and (3) a fully plug-and-play design compatible with arbitrary style LoRAs under the Flux framework. Extensive experiments show that OmniConsistency significantly enhances visual coherence and aesthetic quality, achieving performance comparable to commercial state-of-the-art model GPT-4o.</p> - https://arxiv.org/abs/2505.18445 - Sat, 24 May 2025 01:00:20 +0000 + ViStoryBench: Comprehensive Benchmark Suite for Story Visualization + https://arxiv.org/abs/2505.24862 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24862.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Zhewei Huang, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, Xuanyang Zhang, Xianfang Zeng, Gang Yu, Chi Zhang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Story visualization, which aims to generate a sequence of visually coherent images aligning with a given narrative and reference images, has seen significant progress with recent advancements in generative models. To further enhance the performance of story visualization frameworks in real-world scenarios, we introduce a comprehensive evaluation benchmark, ViStoryBench. We collect a diverse dataset encompassing various story types and artistic styles, ensuring models are evaluated across multiple dimensions such as different plots (e.g., comedy, horror) and visual aesthetics (e.g., anime, 3D renderings). ViStoryBench is carefully curated to balance narrative structures and visual elements, featuring stories with single and multiple protagonists to test models' ability to maintain character consistency. Additionally, it includes complex plots and intricate world-building to challenge models in generating accurate visuals. To ensure comprehensive comparisons, our benchmark incorporates a wide range of evaluation metrics assessing critical aspects. This structured and multifaceted framework enables researchers to thoroughly identify both the strengths and weaknesses of different models, fostering targeted improvements.</p> + https://arxiv.org/abs/2505.24862 + Fri, 30 May 2025 17:58:21 +0000 - Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models - https://arxiv.org/abs/2505.18536 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18536.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyuan Sun, Jiaqi Wu, Bo Xia, Yifu Luo, Yifei Zhao, Kai Qin, Xufei Lv, Tiantian Zhang, Yongzhe Chang, Xueqian Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Standing in 2025, at a critical juncture in the pursuit of Artificial General Intelligence (AGI), reinforcement fine-tuning (RFT) has demonstrated significant potential in enhancing the reasoning capability of large language models (LLMs) and has led to the development of cutting-edge AI models such as OpenAI-o1 and DeepSeek-R1. Moreover, the efficient application of RFT to enhance the reasoning capability of multimodal large language models (MLLMs) has attracted widespread attention from the community. In this position paper, we argue that reinforcement fine-tuning powers the reasoning capability of multimodal large language models. To begin with, we provide a detailed introduction to the fundamental background knowledge that researchers interested in this field should be familiar with. Furthermore, we meticulously summarize the improvements of RFT in powering reasoning capability of MLLMs into five key points: diverse modalities, diverse tasks and domains, better training algorithms, abundant benchmarks and thriving engineering frameworks. Finally, we propose five promising directions for future research that the community might consider. We hope that this position paper will provide valuable insights to the community at this pivotal stage in the advancement toward AGI. Summary of works done on RFT for MLLMs is available at https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs.</p> - https://arxiv.org/abs/2505.18536 - Sat, 24 May 2025 06:01:48 +0000 + AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time + https://arxiv.org/abs/2505.24863 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang</p><p><b>Upvotes:</b> 89</p><p><b>Summary:</b> This paper presents AlphaOne (alpha1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. alpha1 first introduces alpha moment, which represents the scaled thinking phase with a universal parameter alpha. Within this scaled pre-alpha moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the alpha moment, alpha1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate alpha1's superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/</p> + https://arxiv.org/abs/2505.24863 + Fri, 30 May 2025 17:58:36 +0000 - B-score: Detecting biases in large language models using response history - https://arxiv.org/abs/2505.18545 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> An Vo, Mohammad Reza Taesiri, Daeyoung Kim, Anh Totti Nguyen</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers when allowed to observe their prior answers to the same question in a multi-turn conversation. To understand which types of questions invite more biased answers, we test LLMs on our proposed set of questions that span 9 topics and belong to three types: (1) Subjective; (2) Random; and (3) Objective. Interestingly, LLMs are able to "de-bias" themselves in a multi-turn conversation in response to questions that seek an Random, unbiased answer. Furthermore, we propose B-score, a novel metric that is effective in detecting biases to Subjective, Random, Easy, and Hard questions. On MMLU, HLE, and CSQA, leveraging B-score substantially improves the verification accuracy of LLM answers (i.e, accepting LLM correct answers and rejecting incorrect ones) compared to using verbalized confidence scores or the frequency of single-turn answers alone. Code and data are available at: https://b-score.github.io.</p> - https://arxiv.org/abs/2505.18545 - Sat, 24 May 2025 06:23:52 +0000 + ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models + https://arxiv.org/abs/2505.24864 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24864.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong</p><p><b>Upvotes:</b> 115</p><p><b>Summary:</b> Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's reasoning capabilities or merely amplifies high-reward outputs already latent in the base model's distribution, and whether continually scaling up RL compute reliably leads to improved reasoning performance. In this work, we challenge prevailing assumptions by demonstrating that prolonged RL (ProRL) training can uncover novel reasoning strategies that are inaccessible to base models, even under extensive sampling. We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy resetting, and a diverse suite of tasks. Our empirical analysis reveals that RL-trained models consistently outperform base models across a wide range of pass@k evaluations, including scenarios where base models fail entirely regardless of the number of attempts. We further show that reasoning boundary improvements correlates strongly with task competence of base model and training duration, suggesting that RL can explore and populate new regions of solution space over time. These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models and establish a foundation for future work on long-horizon RL for reasoning. We release model weights to support further research: https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B</p> + https://arxiv.org/abs/2505.24864 + Fri, 30 May 2025 17:59:01 +0000 - Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment - https://arxiv.org/abs/2505.18600 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime. We address this scalability bottleneck with Chain-of-Zoom (CoZ), a model-agnostic framework that factorizes SISR into an autoregressive chain of intermediate scale-states with multi-scale-aware prompts. CoZ repeatedly re-uses a backbone SR model, decomposing the conditional probability into tractable sub-problems to achieve extreme resolutions without additional training. Because visual cues diminish at high magnifications, we augment each zoom step with multi-scale-aware text prompts generated by a vision-language model (VLM). The prompt extractor itself is fine-tuned using Generalized Reward Policy Optimization (GRPO) with a critic VLM, aligning text guidance towards human preference. Experiments show that a standard 4x diffusion SR model wrapped in CoZ attains beyond 256x enlargement with high perceptual quality and fidelity. Project Page: https://bryanswkim.github.io/chain-of-zoom/ .</p> - https://arxiv.org/abs/2505.18600 - Sat, 24 May 2025 08:50:08 +0000 + Time Blindness: Why Video-Language Models Can't See What Humans Can? + https://arxiv.org/abs/2505.24867 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ujjwal Upadhyay, Mukul Ranjan, Zhiqiang Shen, Mohamed Elhoseiny</p><p><b>Upvotes:</b> 75</p><p><b>Summary:</b> Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. However, when spatial information is obscured, these models struggle to capture purely temporal patterns. We introduce SpookyBench, a benchmark where information is encoded solely in temporal sequences of noise-like frames, mirroring natural phenomena from biological signaling to covert communication. Interestingly, while humans can recognize shapes, text, and patterns in these sequences with over 98% accuracy, state-of-the-art VLMs achieve 0% accuracy. This performance gap highlights a critical limitation: an over-reliance on frame-level spatial features and an inability to extract meaning from temporal cues. Furthermore, when trained in data sets with low spatial signal-to-noise ratios (SNR), temporal understanding of models degrades more rapidly than human perception, especially in tasks requiring fine-grained temporal reasoning. Overcoming this limitation will require novel architectures or training paradigms that decouple spatial dependencies from temporal processing. Our systematic analysis shows that this issue persists across model scales and architectures. We release SpookyBench to catalyze research in temporal pattern recognition and bridge the gap between human and machine video understanding. Dataset and code has been made available on our project website: https://timeblindness.github.io/.</p> + https://arxiv.org/abs/2505.24867 + Fri, 30 May 2025 17:59:12 +0000 - Flex-Judge: Think Once, Judge Anywhere - https://arxiv.org/abs/2505.18601 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18601.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jongwoo Ko, Sungnyun Kim, Sungwoo Cho, Se-Young Yun</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Human-generated reward signals are critical for aligning generative models with human preferences, guiding both training and inference-time evaluations. While large language models (LLMs) employed as proxy evaluators, i.e., LLM-as-a-Judge, significantly reduce the costs associated with manual annotations, they typically require extensive modality-specific training data and fail to generalize well across diverse multimodal tasks. In this paper, we propose Flex-Judge, a reasoning-guided multimodal judge model that leverages minimal textual reasoning data to robustly generalize across multiple modalities and evaluation formats. Our core intuition is that structured textual reasoning explanations inherently encode generalizable decision-making patterns, enabling an effective transfer to multimodal judgments, e.g., with images or videos. Empirical results demonstrate that Flex-Judge, despite being trained on significantly fewer text data, achieves competitive or superior performance compared to state-of-the-art commercial APIs and extensively trained multimodal evaluators. Notably, Flex-Judge presents broad impact in modalities like molecule, where comprehensive evaluation benchmarks are scarce, underscoring its practical value in resource-constrained domains. Our framework highlights reasoning-based text supervision as a powerful, cost-effective alternative to traditional annotation-intensive approaches, substantially advancing scalable multimodal model-as-a-judge.</p> - https://arxiv.org/abs/2505.18601 - Sat, 24 May 2025 08:50:53 +0000 + MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning + https://arxiv.org/abs/2505.24871 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24871.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiqing Liang, Jielin Qiu, Wenhao Ding, Zuxin Liu, James Tompkin, Mengdi Xu, Mengzhou Xia, Zhengzhong Tu, Laixi Shi, Jiacheng Zhu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiable answers. Applying RLVR to Multimodal LLMs (MLLMs) presents significant opportunities but is complicated by the broader, heterogeneous nature of vision-language tasks that demand nuanced visual, logical, and spatial capabilities. As such, training MLLMs using RLVR on multiple datasets could be beneficial but creates challenges with conflicting objectives from interaction among diverse datasets, highlighting the need for optimal dataset mixture strategies to improve generalization and reasoning. We introduce a systematic post-training framework for Multimodal LLM RLVR, featuring a rigorous data mixture problem formulation and benchmark implementation. Specifically, (1) We developed a multimodal RLVR framework for multi-dataset post-training by curating a dataset that contains different verifiable vision-language problems and enabling multi-domain online RL learning with different verifiable rewards; (2) We proposed a data mixture strategy that learns to predict the RL fine-tuning outcome from the data mixture distribution, and consequently optimizes the best mixture. Comprehensive experiments showcase that multi-domain RLVR training, when combined with mixture prediction strategies, can significantly boost MLLM general reasoning capacities. Our best mixture improves the post-trained model's accuracy on out-of-distribution benchmarks by an average of 5.24% compared to the same model post-trained with uniform data mixture, and by a total of 20.74% compared to the pre-finetuning baseline.</p> + https://arxiv.org/abs/2505.24871 + Fri, 30 May 2025 17:59:38 +0000 - Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps - https://arxiv.org/abs/2505.18675 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicheng Feng, Song Wang, Shuyi Ouyang, Lingdong Kong, Zikai Song, Jianke Zhu, Huan Wang, Xinchao Wang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding and spatial reasoning abilities of MLLMs. ReasonMap encompasses high-resolution transit maps from 30 cities across 13 countries and includes 1,008 question-answer pairs spanning two question types and three templates. Furthermore, we design a two-level evaluation pipeline that properly assesses answer correctness and quality. Comprehensive evaluations of 15 popular MLLMs, including both base and reasoning variants, reveal a counterintuitive pattern: among open-source models, base models outperform reasoning ones, while the opposite trend is observed in closed-source models. Additionally, performance generally degrades when visual inputs are masked, indicating that while MLLMs can leverage prior knowledge to answer some questions, fine-grained visual reasoning tasks still require genuine visual perception for strong performance. Our benchmark study offers new insights into visual reasoning and contributes to investigating the gap between open-source and closed-source models.</p> - https://arxiv.org/abs/2505.18675 - Sat, 24 May 2025 12:33:52 +0000 + Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents + https://arxiv.org/abs/2505.24878 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.24878.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yaxin Luo, Zhaoyi Li, Jiacheng Liu, Jiacheng Cui, Xiaohan Zhao, Zhiqiang Shen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in static perception tasks, their ability to handle interactive, multi-step reasoning challenges like CAPTCHAs is largely untested. To address this gap, we introduce Open CaptchaWorld, the first web-based benchmark and platform specifically designed to evaluate the visual reasoning and interaction capabilities of MLLM-powered agents through diverse and dynamic CAPTCHA puzzles. Our benchmark spans 20 modern CAPTCHA types, totaling 225 CAPTCHAs, annotated with a new metric we propose: CAPTCHA Reasoning Depth, which quantifies the number of cognitive and motor steps required to solve each puzzle. Experimental results show that humans consistently achieve near-perfect scores, state-of-the-art MLLM agents struggle significantly, with success rates at most 40.0% by Browser-Use Openai-o3, far below human-level performance, 93.3%. This highlights Open CaptchaWorld as a vital benchmark for diagnosing the limits of current multimodal agents and guiding the development of more robust multimodal reasoning systems. Code and Data are available at this https URL.</p> + https://arxiv.org/abs/2505.24878 + Fri, 30 May 2025 17:59:55 +0000 - Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation - https://arxiv.org/abs/2505.18875 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18875.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Yang, Haocheng Xi, Yilong Zhao, Muyang Li, Jintao Zhang, Han Cai, Yujun Lin, Xiuyu Li, Chenfeng Xu, Kelly Peng, Jianfei Chen, Song Han, Kurt Keutzer, Ion Stoica</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens, sparse attention reduces computational costs and offers a promising acceleration approach. However, we identify that existing methods fail to approach optimal generation quality under the same computation budget for two reasons: (1) Inaccurate critical token identification: current methods cluster tokens based on position rather than semantics, leading to imprecise aggregated representations. (2) Excessive computation waste: critical tokens are scattered among non-critical ones, leading to wasted computation on GPUs, which are optimized for processing contiguous tokens. In this paper, we propose SVG2, a training-free framework that maximizes identification accuracy and minimizes computation waste, achieving a Pareto frontier trade-off between generation quality and efficiency. The core of SVG2 is semantic-aware permutation, which clusters and reorders tokens based on semantic similarity using k-means. This approach ensures both a precise cluster representation, improving identification accuracy, and a densified layout of critical tokens, enabling efficient computation without padding. Additionally, SVG2 integrates top-p dynamic budget control and customized kernel implementations, achieving up to 2.30x and 1.89x speedup while maintaining a PSNR of up to 30 and 26 on HunyuanVideo and Wan 2.1, respectively.</p> - https://arxiv.org/abs/2505.18875 - Sat, 24 May 2025 21:30:29 +0000 + Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces + https://arxiv.org/abs/2506.00123 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gen Luo, Ganlin Yang, Ziyang Gong, Guanzhou Chen, Haonan Duan, Erfei Cui, Ronglei Tong, Zhi Hou, Tianyi Zhang, Zhe Chen, Shenglong Ye, Lewei Lu, Jingbo Wang, Wenhai Wang, Jifeng Dai, Yu Qiao, Rongrong Ji, Xizhou Zhu</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding abilities, but also integrate visual-spatial reasoning and physical interaction capabilities. Nevertheless,existing methods struggle to unify these capabilities due to their fundamental differences.In this paper, we present the Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world. VeBrain reformulates robotic control into common text-based MLLM tasks in the 2D visual space, thus unifying the objectives and mapping spaces of different tasks. Then, a novel robotic adapter is proposed to convert textual control signals from MLLMs to motion policies of real robots. From the data perspective, we further introduce VeBrain-600k, a high-quality instruction dataset encompassing various capabilities of VeBrain. In VeBrain-600k, we take hundreds of hours to collect, curate and annotate the data, and adopt multimodal chain-of-thought(CoT) to mix the different capabilities into a single conversation. Extensive experiments on 13 multimodal benchmarks and 5 spatial intelligence benchmarks demonstrate the superior performance of VeBrain to existing MLLMs like Qwen2.5-VL. When deployed to legged robots and robotic arms, VeBrain shows strong adaptability, flexibility, and compositional capabilities compared to existing methods. For example, compared to Qwen2.5-VL, VeBrain not only achieves substantial gains on MMVet by +5.6%, but also excels in legged robot tasks with +50% average gains.</p> + https://arxiv.org/abs/2506.00123 + Fri, 30 May 2025 18:00:34 +0000 - Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time - https://arxiv.org/abs/2505.18926 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxuan Xu, Hong Huang, Chuhang Zou, Manolis Savva, Yunchao Wei, Wuyang Chen</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We propose a neural physics system for real-time, interactive fluid simulations. Traditional physics-based methods, while accurate, are computationally intensive and suffer from latency issues. Recent machine-learning methods reduce computational costs while preserving fidelity; yet most still fail to satisfy the latency constraints for real-time use and lack support for interactive applications. To bridge this gap, we introduce a novel hybrid method that integrates numerical simulation, neural physics, and generative control. Our neural physics jointly pursues low-latency simulation and high physical fidelity by employing a fallback safeguard to classical numerical solvers. Furthermore, we develop a diffusion-based controller that is trained using a reverse modeling strategy to generate external dynamic force fields for fluid manipulation. Our system demonstrates robust performance across diverse 2D/3D scenarios, material types, and obstacle interactions, achieving real-time simulations at high frame rates (11~29% latency) while enabling fluid control guided by user-friendly freehand sketches. We present a significant step towards practical, controllable, and physically plausible fluid simulations for real-time interactive applications. We promise to release both models and data upon acceptance.</p> - https://arxiv.org/abs/2505.18926 - Sun, 25 May 2025 01:27:18 +0000 + Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes + https://arxiv.org/abs/2506.00227 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00227.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anthony Gosselin, Ge Ya Luo, Luis Lara, Florian Golemo, Derek Nowrouzezahrai, Liam Paull, Alexia Jolicoeur-Martineau, Christopher Pal</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Video diffusion techniques have advanced significantly in recent years; however, they struggle to generate realistic imagery of car crashes due to the scarcity of accident events in most driving datasets. Improving traffic safety requires realistic and controllable accident simulations. To tackle the problem, we propose Ctrl-Crash, a controllable car crash video generation model that conditions on signals such as bounding boxes, crash types, and an initial image frame. Our approach enables counterfactual scenario generation where minor variations in input can lead to dramatically different crash outcomes. To support fine-grained control at inference time, we leverage classifier-free guidance with independently tunable scales for each conditioning signal. Ctrl-Crash achieves state-of-the-art performance across quantitative video quality metrics (e.g., FVD and JEDi) and qualitative measurements based on a human-evaluation of physical realism and video quality compared to prior diffusion-based methods.</p> + https://arxiv.org/abs/2506.00227 + Fri, 30 May 2025 21:04:38 +0000 - MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems - https://arxiv.org/abs/2505.18943 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.18943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, Yixuan Li</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Human social interactions depend on the ability to infer others' unspoken intentions, emotions, and beliefs-a cognitive skill grounded in the psychological concept of Theory of Mind (ToM). While large language models (LLMs) excel in semantic understanding tasks, they struggle with the ambiguity and contextual nuance inherent in human communication. To bridge this gap, we introduce MetaMind, a multi-agent framework inspired by psychological theories of metacognition, designed to emulate human-like social reasoning. MetaMind decomposes social understanding into three collaborative stages: (1) a Theory-of-Mind Agent generates hypotheses user mental states (e.g., intent, emotion), (2) a Domain Agent refines these hypotheses using cultural norms and ethical constraints, and (3) a Response Agent generates contextually appropriate responses while validating alignment with inferred intent. Our framework achieves state-of-the-art performance across three challenging benchmarks, with 35.7% improvement in real-world social scenarios and 6.2% gain in ToM reasoning. Notably, it enables LLMs to match human-level performance on key ToM tasks for the first time. Ablation studies confirm the necessity of all components, which showcase the framework's ability to balance contextual plausibility, social appropriateness, and user adaptation. This work advances AI systems toward human-like social intelligence, with applications in empathetic dialogue and culturally sensitive interactions. Code is available at https://github.com/XMZhangAI/MetaMind.</p> - https://arxiv.org/abs/2505.18943 - Sun, 25 May 2025 02:32:57 +0000 + LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks + https://arxiv.org/abs/2506.00411 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00411.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang, Zhijie Deng</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (VLA) models and hierarchical architectures offer potential in embodied tasks, the former often falter in planning, and the latter can suffer from coordination issues, both hampering performance. We introduce a new unified VLA framework for long-horizon tasks, dubbed LoHoVLA, to overcome these limitations. LoHoVLA leverages a large pretrained vision language model (VLM) as the backbone to jointly generate language and action tokens for sub-task generation and robot action prediction, respectively. This shared representation promotes better generalization across tasks. Additionally, LoHoVLA embraces a hierarchical closed-loop control mechanism to mitigate errors originating from both high-level planning and low-level control. To train LoHoVLA, we introduce LoHoSet, a dataset built on the Ravens simulator, containing 20 long-horizon tasks, each with 1,000 expert demonstrations composed of visual observations, linguistic goals, sub-tasks, and robot actions. Experimental results show that LoHoVLA significantly surpasses both hierarchical and standard VLA approaches on long-horizon embodied tasks in the Ravens simulator. These findings underscore the promise of unified architectures for advancing generalizable embodied intelligence.</p> + https://arxiv.org/abs/2506.00411 + Sat, 31 May 2025 06:01:03 +0000 - VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization - https://arxiv.org/abs/2505.19000 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunxin Li, Xinyu Chen, Zitao Li, Zhenyu Liu, Longyue Wang, Wenhan Luo, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy Optimization (GRPO), are limited by data preparation bottlenecks (e.g., noise or high cost) and exhibit unstable improvements in the quality of long chain-of-thoughts (CoTs) and downstream performance.To address these limitations, we propose VerIPO, a Verifier-guided Iterative Policy Optimization method designed to gradually improve video LLMs' capacity for generating deep, long-term reasoning chains. The core component is Rollout-Aware Verifier, positioned between the GRPO and Direct Preference Optimization (DPO) training phases to form the GRPO-Verifier-DPO training loop. This verifier leverages small LLMs as a judge to assess the reasoning logic of rollouts, enabling the construction of high-quality contrastive data, including reflective and contextually consistent CoTs. These curated preference samples drive the efficient DPO stage (7x faster than GRPO), leading to marked improvements in reasoning chain quality, especially in terms of length and contextual consistency. This training loop benefits from GRPO's expansive search and DPO's targeted optimization. Experimental results demonstrate: 1) Significantly faster and more effective optimization compared to standard GRPO variants, yielding superior performance; 2) Our trained models exceed the direct inference of large-scale instruction-tuned Video-LLMs, producing long and contextually consistent CoTs on diverse video reasoning tasks; and 3) Our model with one iteration outperforms powerful LMMs (e.g., Kimi-VL) and long reasoning models (e.g., Video-R1), highlighting its effectiveness and stability.</p> - https://arxiv.org/abs/2505.19000 - Sun, 25 May 2025 06:41:28 +0000 + ARIA: Training Language Agents with Intention-Driven Reward Aggregation + https://arxiv.org/abs/2506.00539 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00539.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruihan Yang, Yikai Zhang, Aili Chen, Xintao Wang, Siyu Yuan, Jiangjie Chen, Deqing Yang, Yanghua Xiao</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the action space can be formulated as a joint distribution over tokens, resulting in an exponentially large action space. Sampling actions in such a space can lead to extreme reward sparsity, which brings large reward variance, hindering effective reinforcement learning (RL). To address this, we propose ARIA, a method that Aggregates Rewards in Intention space to enable efficient and effective language Agents training. ARIA aims to project natural language actions from the high-dimensional joint token distribution space into a low-dimensional intention space, where semantically similar actions are clustered and assigned shared rewards. This intention-aware reward aggregation reduces reward variance by densifying reward signals, fostering better policy optimization. Extensive experiments demonstrate that ARIA not only significantly reduces policy gradient variance, but also delivers substantial performance gains of an average of 9.95% across four downstream tasks, consistently outperforming offline and online RL baselines.</p> + https://arxiv.org/abs/2506.00539 + Sat, 31 May 2025 12:54:49 +0000 - Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs - https://arxiv.org/abs/2505.19075 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaemin Kim, Hangeol Chang, Hyunmin Hwang, Choonghan Kim, Jong Chul Ye</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substantial computational resources and may compromise their generalization. While Parameter-Efficient Fine-Tuning (PEFT) methods offer a more resource-conscious alternative, they typically requires retraining for each LLM backbone due to architectural dependencies. To address these challenges, here we propose Universal Reasoner (UniR) - a single, lightweight, composable, and plug-and-play reasoning module that can be used with any frozen LLM to endow it with specialized reasoning capabilities. Specifically, UniR decomposes the reward into a standalone reasoning module that is trained independently using predefined rewards, effectively translating trajectory-level signals into token-level guidance. Once trained, UniR can be combined with any frozen LLM at inference time by simply adding its output logits to those of the LLM backbone. This additive structure naturally enables modular composition: multiple UniR modules trained for different tasks can be jointly applied by summing their logits, enabling complex reasoning via composition. Experimental results on mathematical reasoning and machine translation tasks show that UniR significantly outperforms existing baseline fine-tuning methods using the Llama3.2 model. Furthermore, UniR demonstrates strong weak-to-strong generalization: reasoning modules trained on smaller models effectively guide much larger LLMs. This makes UniR a cost-efficient, adaptable, and robust solution for enhancing reasoning in LLMs without compromising their core capabilities. Code is open-sourced at https://github.com/hangeol/UniR</p> - https://arxiv.org/abs/2505.19075 - Sun, 25 May 2025 10:19:10 +0000 + Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs + https://arxiv.org/abs/2506.00577 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufa Zhou, Shaobo Wang, Xingyu Dong, Xiangqi Jin, Yifang Chen, Yue Min, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively generalize to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real-world applications such as market design, resource allocation, and policy analysis. We introduce Recon (Reasoning like an ECONomist), a 7B-parameter open-source LLM post-trained on a hand-curated dataset of 2,100 high-quality economic reasoning problems. Comprehensive evaluation on economic reasoning benchmarks and multi-agent games reveals clear improvements in structured reasoning and economic rationality. These results underscore the promise of domain-aligned post-training for enhancing reasoning and agent alignment, shedding light on the roles of SFT and RL in shaping model behavior. Code is available at https://github.com/MasterZhou1/Recon .</p> + https://arxiv.org/abs/2506.00577 + Sat, 31 May 2025 14:22:40 +0000 - Jodi: Unification of Visual Generation and Understanding via Joint Modeling - https://arxiv.org/abs/2505.19084 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19084.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifeng Xu, Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Visual generation and understanding are two deeply interconnected aspects of human intelligence, yet they have been traditionally treated as separate tasks in machine learning. In this paper, we propose Jodi, a diffusion framework that unifies visual generation and understanding by jointly modeling the image domain and multiple label domains. Specifically, Jodi is built upon a linear diffusion transformer along with a role switch mechanism, which enables it to perform three particular types of tasks: (1) joint generation, where the model simultaneously generates images and multiple labels; (2) controllable generation, where images are generated conditioned on any combination of labels; and (3) image perception, where multiple labels can be predicted at once from a given image. Furthermore, we present the Joint-1.6M dataset, which contains 200,000 high-quality images collected from public sources, automatic labels for 7 visual domains, and LLM-generated captions. Extensive experiments demonstrate that Jodi excels in both generation and understanding tasks and exhibits strong extensibility to a wider range of visual domains. Code is available at https://github.com/VIPL-GENUN/Jodi.</p> - https://arxiv.org/abs/2505.19084 - Sun, 25 May 2025 10:40:52 +0000 + PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models + https://arxiv.org/abs/2506.00910 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongjae Kang, Dong Bok Lee, Hyungjoon Jang, Dongseop Kim, Sung Ju Hwang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Knowledge distillation (KD) is a widely used framework for training compact, task-specific models by leveraging the knowledge of teacher models. However, its application to active learning (AL), which aims to minimize annotation costs through iterative sample selection, remains underexplored. This gap stems from the fact that KD typically assumes access to sufficient labeled data, whereas AL operates in data-scarce scenarios where task-specific teacher models are often unavailable. In this paper, we introduce ActiveKD, a framework that integrates AL with KD by leveraging the zero- and few-shot capabilities of large vision-language models (VLMs). A key aspect of ActiveKD is the structured prediction bias of VLMs -- i.e., their predictions form clusters in the probability space. We regard this structure as an inductive bias of the teacher model, capturing generalizable output patterns beneficial to student learning. To exploit this bias, we propose Probabilistic CoreSet (PCoreSet), a selection strategy that maximizes coverage in the probability space rather than the feature space. PCoreSet strategically selects categorically diverse unlabeled samples, facilitating more efficient transfer of teacher knowledge under limited annotation budgets. Evaluations on 11 datasets show that PCoreSet consistently outperforms existing selection methods within the ActiveKD framework, advancing research at the intersection of AL and KD.</p> + https://arxiv.org/abs/2506.00910 + Sun, 01 Jun 2025 08:54:37 +0000 - Shifting AI Efficiency From Model-Centric to Data-Centric Compression - https://arxiv.org/abs/2505.19147 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19147.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuyang Liu, Zichen Wen, Shaobo Wang, Junjie Chen, Zhishan Tao, Yubo Wang, Xiangqi Jin, Chang Zou, Yiyu Wang, Chenfei Liao, Xu Zheng, Honggang Chen, Weijia Li, Xuming Hu, Conghui He, Linfeng Zhang</p><p><b>Upvotes:</b> 139</p><p><b>Summary:</b> The rapid advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on model-centric scaling through increasing parameter counts from millions to hundreds of billions to drive performance gains. However, as we approach hardware limits on model size, the dominant computational bottleneck has fundamentally shifted to the quadratic cost of self-attention over long token sequences, now driven by ultra-long text contexts, high-resolution images, and extended videos. In this position paper, we argue that the focus of research for efficient AI is shifting from model-centric compression to data-centric compression. We position token compression as the new frontier, which improves AI efficiency via reducing the number of tokens during model training or inference. Through comprehensive analysis, we first examine recent developments in long-context AI across various domains and establish a unified mathematical framework for existing model efficiency strategies, demonstrating why token compression represents a crucial paradigm shift in addressing long-context overhead. Subsequently, we systematically review the research landscape of token compression, analyzing its fundamental benefits and identifying its compelling advantages across diverse scenarios. Furthermore, we provide an in-depth analysis of current challenges in token compression research and outline promising future directions. Ultimately, our work aims to offer a fresh perspective on AI efficiency, synthesize existing research, and catalyze innovative developments to address the challenges that increasing context lengths pose to the AI community's advancement.</p> - https://arxiv.org/abs/2505.19147 - Sun, 25 May 2025 13:51:17 +0000 + IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection + https://arxiv.org/abs/2506.00979 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wayne Zhang, Changjiang Jiang, Zhonghao Zhang, Chenyang Si, Fengchang Yu, Wei Peng</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The rapid advancement of Artificial Intelligence Generated Content (AIGC) in visual domains has resulted in highly realistic synthetic images and videos, driven by sophisticated generative frameworks such as diffusion-based architectures. While these breakthroughs open substantial opportunities, they simultaneously raise critical concerns about content authenticity and integrity. Many current AIGC detection methods operate as black-box binary classifiers, which offer limited interpretability, and no approach supports detecting both images and videos in a unified framework. This dual limitation compromises model transparency, reduces trustworthiness, and hinders practical deployment. To address these challenges, we introduce IVY-FAKE , a novel, unified, and large-scale dataset specifically designed for explainable multimodal AIGC detection. Unlike prior benchmarks, which suffer from fragmented modality coverage and sparse annotations, IVY-FAKE contains over 150,000 richly annotated training samples (images and videos) and 18,700 evaluation examples, each accompanied by detailed natural-language reasoning beyond simple binary labels. Building on this, we propose Ivy Explainable Detector (IVY-XDETECTOR), a unified AIGC detection and explainable architecture that jointly performs explainable detection for both image and video content. Our unified vision-language model achieves state-of-the-art performance across multiple image and video detection benchmarks, highlighting the significant advancements enabled by our dataset and modeling framework. Our data is publicly available at https://huggingface.co/datasets/AI-Safeguard/Ivy-Fake.</p> + https://arxiv.org/abs/2506.00979 + Sun, 01 Jun 2025 12:20:22 +0000 - MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search - https://arxiv.org/abs/2505.19209 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zonglin Yang, Wanhao Liu, Ben Gao, Yujie Liu, Wei Li, Tong Xie, Lidong Bing, Wanli Ouyang, Erik Cambria, Dongzhan Zhou</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Large language models (LLMs) have shown promise in automating scientific hypothesis generation, yet existing approaches primarily yield coarse-grained hypotheses lacking critical methodological and experimental details. We introduce and formally define the novel task of fine-grained scientific hypothesis discovery, which entails generating detailed, experimentally actionable hypotheses from coarse initial research directions. We frame this as a combinatorial optimization problem and investigate the upper limits of LLMs' capacity to solve it when maximally leveraged. Specifically, we explore four foundational questions: (1) how to best harness an LLM's internal heuristics to formulate the fine-grained hypothesis it itself would judge as the most promising among all the possible hypotheses it might generate, based on its own internal scoring-thus defining a latent reward landscape over the hypothesis space; (2) whether such LLM-judged better hypotheses exhibit stronger alignment with ground-truth hypotheses; (3) whether shaping the reward landscape using an ensemble of diverse LLMs of similar capacity yields better outcomes than defining it with repeated instances of the strongest LLM among them; and (4) whether an ensemble of identical LLMs provides a more reliable reward landscape than a single LLM. To address these questions, we propose a hierarchical search method that incrementally proposes and integrates details into the hypothesis, progressing from general concepts to specific experimental configurations. We show that this hierarchical process smooths the reward landscape and enables more effective optimization. Empirical evaluations on a new benchmark of expert-annotated fine-grained hypotheses from recent chemistry literature show that our method consistently outperforms strong baselines.</p> - https://arxiv.org/abs/2505.19209 - Sun, 25 May 2025 16:13:46 +0000 + Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models + https://arxiv.org/abs/2506.00996 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.00996.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kinam Kim, Junha Hyung, Jaegul Choo</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional generation often rely on external encoders or architectural modifications, which demand large datasets and are typically restricted to spatially aligned conditioning, limiting flexibility and scalability. In this work, we introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient and versatile approach for adapting pretrained video diffusion models to diverse conditional generation tasks. Our key idea is to concatenate condition and target frames along the temporal axis and insert intermediate buffer frames with progressively increasing noise levels. These buffer frames enable smooth transitions, aligning the fine-tuning process with the pretrained model's temporal dynamics. TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples. We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B. Extensive experiments show that TIC-FT outperforms existing baselines in both condition fidelity and visual quality, while remaining highly efficient in both training and inference. For additional results, visit https://kinam0252.github.io/TIC-FT/</p> + https://arxiv.org/abs/2506.00996 + Sun, 01 Jun 2025 12:57:43 +0000 - PATS: Process-Level Adaptive Thinking Mode Switching - https://arxiv.org/abs/2505.19250 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19250.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Wang, Junxiao Liu, Shimao Zhang, Jiajun Chen, Shujian Huang</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty. This neglect of variation in task and reasoning process complexity leads to an imbalance between performance and efficiency. Existing methods attempt to implement training-free fast-slow thinking system switching to handle problems of varying difficulty, but are limited by coarse-grained solution-level strategy adjustments. To address this issue, we propose a novel reasoning paradigm: Process-Level Adaptive Thinking Mode Switching (PATS), which enables LLMs to dynamically adjust their reasoning strategy based on the difficulty of each step, optimizing the balance between accuracy and computational efficiency. Our approach integrates Process Reward Models (PRMs) with Beam Search, incorporating progressive mode switching and bad-step penalty mechanisms. Experiments on diverse mathematical benchmarks demonstrate that our methodology achieves high accuracy while maintaining moderate token usage. This study emphasizes the significance of process-level, difficulty-aware reasoning strategy adaptation, offering valuable insights into efficient inference for LLMs.</p> - https://arxiv.org/abs/2505.19250 - Sun, 25 May 2025 17:58:50 +0000 + Taming LLMs by Scaling Learning Rates with Gradient Grouping + https://arxiv.org/abs/2506.01049 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01049.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variations, they still struggle with efficient and effective parameter-wise learning rate estimation, resulting in training instability, slow convergence, and poor compatibility with parameter-efficient fine-tuning (PEFT) techniques. This work introduces Scaling with Gradient Grouping (SGG), an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling. SGG first groups gradient statistics in each layer into clusters and then applies cluster-specific scaling to calibrate learning rates for each parameter, thus imposing collective group-wise constraints while maintaining precise per-parameter adaptation. Experiments on diverse (M)LLM benchmarks show that SGG integrates seamlessly with existing optimizers, and offers consistent gains and faster convergence over baselines, with various model sizes. Its stability across varying batch sizes and learning rates establishes SGG as a robust choice for LLM optimization.</p> + https://arxiv.org/abs/2506.01049 + Sun, 01 Jun 2025 15:30:37 +0000 - DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research - https://arxiv.org/abs/2505.19253 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19253.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> João Coelho, Jingjie Ning, Jingyuan He, Kangrui Mao, Abhijay Paladugu, Pranav Setlur, Jiahe Jin, Jamie Callan, João Magalhães, Bruno Martins, Chenyan Xiong</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks rely on dynamic commercial search APIs, which pose reproducibility and transparency challenges in addition to their cost. To address these limitations, we introduce DeepResearchGym, an open-source sandbox that combines a reproducible search API with a rigorous evaluation protocol for benchmarking deep research systems. The API indexes large-scale public web corpora, namely ClueWeb22 and FineWeb, using a state-of-the-art dense retriever and approximate nearest neighbor search via DiskANN. It achieves lower latency than popular commercial APIs while ensuring stable document rankings across runs, and is freely available for research use. To evaluate deep research systems' outputs, we extend the Researchy Questions benchmark with automatic metrics through LLM-as-a-judge assessments to measure alignment with users' information needs, retrieval faithfulness, and report quality. Experimental results show that systems integrated with DeepResearchGym achieve performance comparable to those using commercial APIs, with performance rankings remaining consistent across evaluation metrics. A human evaluation study further confirms that our automatic protocol aligns with human preferences, validating the framework's ability to help support controlled assessment of deep research systems. Our code and API documentation are available at https://www.deepresearchgym.ai.</p> - https://arxiv.org/abs/2505.19253 - Sun, 25 May 2025 18:16:13 +0000 + FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation + https://arxiv.org/abs/2506.01144 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01144.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ariel Shaulov, Itay Hazan, Lior Wolf, Hila Chefer</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external conditioning signals to enforce temporal consistency. In this work, we explore whether a meaningful temporal representation can be extracted directly from the predictions of a pre-trained model without any additional training or auxiliary inputs. We introduce FlowMo, a novel training-free guidance method that enhances motion coherence using only the model's own predictions in each diffusion step. FlowMo first derives an appearance-debiased temporal representation by measuring the distance between latents corresponding to consecutive frames. This highlights the implicit temporal structure predicted by the model. It then estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling. Extensive experiments across multiple text-to-video models demonstrate that FlowMo significantly improves motion coherence without sacrificing visual quality or prompt alignment, offering an effective plug-and-play solution for enhancing the temporal fidelity of pre-trained video diffusion models.</p> + https://arxiv.org/abs/2506.01144 + Sun, 01 Jun 2025 19:55:33 +0000 - Alchemist: Turning Public Text-to-Image Data into Generative Gold - https://arxiv.org/abs/2505.19297 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19297.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Valerii Startsev, Alexander Ustyuzhanin, Alexey Kirillov, Dmitry Baranchuk, Sergey Kastryulin</p><p><b>Upvotes:</b> 73</p><p><b>Summary:</b> Pre-training equips text-to-image (T2I) models with broad world knowledge, but this alone is often insufficient to achieve high aesthetic quality and alignment. Consequently, supervised fine-tuning (SFT) is crucial for further refinement. However, its effectiveness highly depends on the quality of the fine-tuning dataset. Existing public SFT datasets frequently target narrow domains (e.g., anime or specific art styles), and the creation of high-quality, general-purpose SFT datasets remains a significant challenge. Current curation methods are often costly and struggle to identify truly impactful samples. This challenge is further complicated by the scarcity of public general-purpose datasets, as leading models often rely on large, proprietary, and poorly documented internal data, hindering broader research progress. This paper introduces a novel methodology for creating general-purpose SFT datasets by leveraging a pre-trained generative model as an estimator of high-impact training samples. We apply this methodology to construct and release Alchemist, a compact (3,350 samples) yet highly effective SFT dataset. Experiments demonstrate that Alchemist substantially improves the generative quality of five public T2I models while preserving diversity and style. Additionally, we release the fine-tuned models' weights to the public.</p> - https://arxiv.org/abs/2505.19297 - Sun, 25 May 2025 20:08:20 +0000 + Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models + https://arxiv.org/abs/2506.01320 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Taehoon Yoon, Yunhong Min, Kyeongmin Yeo, Minhyuk Sung</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We introduce Psi-Sampler, an SMC-based framework incorporating pCNL-based initial particle sampling for effective inference-time reward alignment with a score-based generative model. Inference-time reward alignment with score-based generative models has recently gained significant traction, following a broader paradigm shift from pre-training to post-training optimization. At the core of this trend is the application of Sequential Monte Carlo (SMC) to the denoising process. However, existing methods typically initialize particles from the Gaussian prior, which inadequately captures reward-relevant regions and results in reduced sampling efficiency. We demonstrate that initializing from the reward-aware posterior significantly improves alignment performance. To enable posterior sampling in high-dimensional latent spaces, we introduce the preconditioned Crank-Nicolson Langevin (pCNL) algorithm, which combines dimension-robust proposals with gradient-informed dynamics. This approach enables efficient and scalable posterior sampling and consistently improves performance across various reward alignment tasks, including layout-to-image generation, quantity-aware generation, and aesthetic-preference generation, as demonstrated in our experiments.</p> + https://arxiv.org/abs/2506.01320 + Mon, 02 Jun 2025 05:02:33 +0000 - Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers - https://arxiv.org/abs/2505.19439 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19439.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rihui Xin, Han Liu, Zecheng Wang, Yupeng Zhang, Dianbo Sui, Xiaolin Hu, Bingning Wang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Large Language Models have achieved remarkable success in natural language processing tasks, with Reinforcement Learning playing a key role in adapting them to specific applications. However, obtaining ground truth answers for training LLMs in mathematical problem-solving is often challenging, costly, and sometimes unfeasible. This research delves into the utilization of format and length as surrogate signals to train LLMs for mathematical problem-solving, bypassing the need for traditional ground truth answers.Our study shows that a reward function centered on format correctness alone can yield performance improvements comparable to the standard GRPO algorithm in early phases. Recognizing the limitations of format-only rewards in the later phases, we incorporate length-based rewards. The resulting GRPO approach, leveraging format-length surrogate signals, not only matches but surpasses the performance of the standard GRPO algorithm relying on ground truth answers in certain scenarios, achieving 40.0\% accuracy on AIME2024 with a 7B base model. Through systematic exploration and experimentation, this research not only offers a practical solution for training LLMs to solve mathematical problems and reducing the dependence on extensive ground truth data collection, but also reveals the essence of why our label-free approach succeeds: base model is like an excellent student who has already mastered mathematical and logical reasoning skills, but performs poorly on the test paper, it simply needs to develop good answering habits to achieve outstanding results in exams , in other words, to unlock the capabilities it already possesses.</p> - https://arxiv.org/abs/2505.19439 - Mon, 26 May 2025 02:56:22 +0000 + Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models + https://arxiv.org/abs/2506.01413 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01413.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulei Qin, Gang Li, Zongyi Li, Zihan Xu, Yuchen Shi, Zhekai Lin, Xiao Cui, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1.5B LLM achieves 11.74% gains with performance comparable to a 8B LLM. Codes and data are available at https://github.com/yuleiqin/RAIF.</p> + https://arxiv.org/abs/2506.01413 + Mon, 02 Jun 2025 08:11:44 +0000 - BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs - https://arxiv.org/abs/2505.19457 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guilong Lu, Xuntao Guo, Rongjunchen Zhang, Wenqiao Zhu, Ji Liu</p><p><b>Upvotes:</b> 61</p><p><b>Summary:</b> Large language models excel in general tasks, yet assessing their reliability in logic-heavy, precision-critical domains like finance, law, and healthcare remains challenging. To address this, we introduce BizFinBench, the first benchmark specifically designed to evaluate LLMs in real-world financial applications. BizFinBench consists of 6,781 well-annotated queries in Chinese, spanning five dimensions: numerical calculation, reasoning, information extraction, prediction recognition, and knowledge-based question answering, grouped into nine fine-grained categories. The benchmark includes both objective and subjective metrics. We also introduce IteraJudge, a novel LLM evaluation method that reduces bias when LLMs serve as evaluators in objective metrics. We benchmark 25 models, including both proprietary and open-source systems. Extensive experiments show that no model dominates across all tasks. Our evaluation reveals distinct capability patterns: (1) In Numerical Calculation, Claude-3.5-Sonnet (63.18) and DeepSeek-R1 (64.04) lead, while smaller models like Qwen2.5-VL-3B (15.92) lag significantly; (2) In Reasoning, proprietary models dominate (ChatGPT-o3: 83.58, Gemini-2.0-Flash: 81.15), with open-source models trailing by up to 19.49 points; (3) In Information Extraction, the performance spread is the largest, with DeepSeek-R1 scoring 71.46, while Qwen3-1.7B scores 11.23; (4) In Prediction Recognition, performance variance is minimal, with top models scoring between 39.16 and 50.00. We find that while current LLMs handle routine finance queries competently, they struggle with complex scenarios requiring cross-concept reasoning. BizFinBench offers a rigorous, business-aligned benchmark for future research. The code and dataset are available at https://github.com/HiThink-Research/BizFinBench.</p> - https://arxiv.org/abs/2505.19457 - Mon, 26 May 2025 03:23:02 +0000 + EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models + https://arxiv.org/abs/2506.01667 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01667.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Shu, Bin Ren, Zhitong Xiong, Danda Pani Paudel, Luc Van Gool, Begum Demir, Nicu Sebe, Paolo Rota</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Large Multimodal Models (LMMs) have demonstrated strong performance in various vision-language tasks. However, they often struggle to comprehensively understand Earth Observation (EO) data, which is critical for monitoring the environment and the effects of human activity on it. In this work, we present EarthMind, a novel vision-language framework for multi-granular and multi-sensor EO data understanding. EarthMind features two core components: (1) Spatial Attention Prompting (SAP), which reallocates attention within the LLM to enhance pixel-level understanding; and (2) Cross-modal Fusion, which aligns heterogeneous modalities into a shared space and adaptively reweighs tokens based on their information density for effective fusion. To facilitate multi-sensor fusion evaluation, we propose EarthMind-Bench, a comprehensive benchmark with over 2,000 human-annotated multi-sensor image-question pairs, covering a wide range of perception and reasoning tasks. Extensive experiments demonstrate the effectiveness of EarthMind. It achieves state-of-the-art performance on EarthMind-Bench, surpassing GPT-4o despite being only 4B in scale. Moreover, EarthMind outperforms existing methods on multiple public EO benchmarks, showcasing its potential to handle both multi-granular and multi-sensor challenges in a unified framework.</p> + https://arxiv.org/abs/2506.01667 + Mon, 02 Jun 2025 13:36:05 +0000 - GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning - https://arxiv.org/abs/2505.20355 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20355.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yeonjoon Jung, Daehyun Ahn, Hyungjun Kim, Taesu Kim, Eunhyeok Park</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Low-Rank Adaptation (LoRA) is a popular method for parameter-efficient fine-tuning (PEFT) of generative models, valued for its simplicity and effectiveness. Despite recent enhancements, LoRA still suffers from a fundamental limitation: overfitting when the bottleneck is widened. It performs best at ranks 32-64, yet its accuracy stagnates or declines at higher ranks, still falling short of full fine-tuning (FFT) performance. We identify the root cause as LoRA's structural bottleneck, which introduces gradient entanglement to the unrelated input channels and distorts gradient propagation. To address this, we introduce a novel structure, Granular Low-Rank Adaptation (GraLoRA) that partitions weight matrices into sub-blocks, each with its own low-rank adapter. With negligible computational or storage cost, GraLoRA overcomes LoRA's limitations, effectively increases the representational capacity, and more closely approximates FFT behavior. Experiments on code generation and commonsense reasoning benchmarks show that GraLoRA consistently outperforms LoRA and other baselines, achieving up to +8.5% absolute gain in Pass@1 on HumanEval+. These improvements hold across model sizes and rank settings, making GraLoRA a scalable and robust solution for PEFT. Code, data, and scripts are available at https://github.com/SqueezeBits/GraLoRA.git</p> - https://arxiv.org/abs/2505.20355 - Mon, 26 May 2025 06:48:20 +0000 + MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs + https://arxiv.org/abs/2506.01674 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yipeng Du, Tiehan Fan, Kepan Nan, Rui Xie, Penghao Zhou, Xiang Li, Jian Yang, Zhenheng Yang, Ying Tai</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Despite advancements in Multimodal Large Language Models (MLLMs), their proficiency in fine-grained video motion understanding remains critically limited. They often lack inter-frame differencing and tend to average or ignore subtle visual cues. Furthermore, while visual prompting has shown potential in static images, its application to video's temporal complexities, particularly for fine-grained motion understanding, remains largely unexplored. We investigate whether inherent capability can be unlocked and boost MLLMs' motion perception and enable distinct visual signatures tailored to decouple object and camera motion cues. In this study, we introduce MotionSight, a novel zero-shot method pioneering object-centric visual spotlight and motion blur as visual prompts to effectively improve fine-grained motion understanding without training. To convert this into valuable data assets, we curated MotionVid-QA, the first large-scale dataset for fine-grained video motion understanding, with hierarchical annotations including SFT and preference data, {\Theta}(40K) video clips and {\Theta}(87K) QAs. Experiments show MotionSight achieves state-of-the-art open-source performance and competitiveness with commercial models. In particular, for fine-grained motion understanding we present a novel zero-shot technique and a large-scale, high-quality dataset. All the code and annotations will be publicly available.</p> + https://arxiv.org/abs/2506.01674 + Mon, 02 Jun 2025 13:44:56 +0000 - Learning to Reason without External Rewards - https://arxiv.org/abs/2505.19590 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data. We propose Intuitor, an RLIF method that uses a model's own confidence, termed self-certainty, as its sole reward signal. Intuitor replaces external rewards in Group Relative Policy Optimization (GRPO) with self-certainty scores, enabling fully unsupervised learning. Experiments demonstrate that Intuitor matches GRPO's performance on mathematical benchmarks while achieving superior generalization to out-of-domain tasks like code generation, without requiring gold solutions or test cases. Our findings show that intrinsic model signals can drive effective learning across domains, offering a scalable alternative to RLVR for autonomous AI systems where verifiable rewards are unavailable. Code is available at https://github.com/sunblaze-ucb/Intuitor</p> - https://arxiv.org/abs/2505.19590 - Mon, 26 May 2025 07:01:06 +0000 + SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning + https://arxiv.org/abs/2506.01713 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01713.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang, Dongfei Cui, Qinjian Zhao, Hui Shen, Jing Xiong, Yi Xin, Yifan Jiang, Yangfan He, Mi Zhang, Shen Yan</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges, we propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning (RL) framework explicitly designed to enhance multimodal LLM reasoning. In the first stage, we construct a high-quality, reflection-focused dataset under the guidance of an advanced MLLM, which generates reflections based on initial responses to help the policy model learn both reasoning and self-reflection. In the second stage, we introduce a novel reward mechanism within the GRPO framework that encourages concise and cognitively meaningful reflection while avoiding redundancy. Extensive experiments across multiple multimodal reasoning benchmarks, including MathVista, MathVision, MathVerse, and MMMU-Pro, using Qwen-2.5-VL-7B and Qwen-2.5-VL-32B demonstrate that SRPO significantly outperforms state-of-the-art models, achieving notable improvements in both reasoning accuracy and reflection quality.</p> + https://arxiv.org/abs/2506.01713 + Mon, 02 Jun 2025 14:21:44 +0000 - SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond - https://arxiv.org/abs/2505.19641 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19641.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junteng Liu, Yuanxiang Fan, Zhuo Jiang, Han Ding, Yongyi Hu, Chi Zhang, Yiqi Shi, Shitong Weng, Aili Chen, Shiqi Chen, Yunan Huang, Mozhi Zhang, Pengyu Zhao, Junjie Yan, Junxian He</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Recent advances such as OpenAI-o1 and DeepSeek R1 have demonstrated the potential of Reinforcement Learning (RL) to enhance reasoning abilities in Large Language Models (LLMs). While open-source replication efforts have primarily focused on mathematical and coding domains, methods and resources for developing general reasoning capabilities remain underexplored. This gap is partly due to the challenge of collecting diverse and verifiable reasoning data suitable for RL. We hypothesize that logical reasoning is critical for developing general reasoning capabilities, as logic forms a fundamental building block of reasoning. In this work, we present SynLogic, a data synthesis framework and dataset that generates diverse logical reasoning data at scale, encompassing 35 diverse logical reasoning tasks. The SynLogic approach enables controlled synthesis of data with adjustable difficulty and quantity. Importantly, all examples can be verified by simple rules, making them ideally suited for RL with verifiable rewards. In our experiments, we validate the effectiveness of RL training on the SynLogic dataset based on 7B and 32B models. SynLogic leads to state-of-the-art logical reasoning performance among open-source datasets, surpassing DeepSeek-R1-Distill-Qwen-32B by 6 points on BBEH. Furthermore, mixing SynLogic data with mathematical and coding tasks improves the training efficiency of these domains and significantly enhances reasoning generalization. Notably, our mixed training model outperforms DeepSeek-R1-Zero-Qwen-32B across multiple benchmarks. These findings position SynLogic as a valuable resource for advancing the broader reasoning capabilities of LLMs. We open-source both the data synthesis pipeline and the SynLogic dataset at https://github.com/MiniMax-AI/SynLogic.</p> - https://arxiv.org/abs/2505.19641 - Mon, 26 May 2025 07:59:36 +0000 + Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability + https://arxiv.org/abs/2506.01789 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Genta Indra Winata, David Anugraha, Emmy Liu, Alham Fikri Aji, Shou-Yi Hung, Aditya Parashar, Patrick Amadeus Irawan, Ruochen Zhang, Zheng-Xin Yong, Jan Christian Blaise Cruz, Niklas Muennighoff, Seungone Kim, Hanyang Zhao, Sudipta Kar, Kezia Erina Suryoraharjo, M. Farid Adilazuarda, En-Shiun Annie Lee, Ayu Purwarianti, Derry Tanti Wijaya, Monojit Choudhury</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality, diversity, or rigorous quality control, and these shortcomings are often overlooked during peer review. Submissions also frequently omit essential details about dataset construction and properties. While existing tools such as datasheets aim to promote transparency, they are largely descriptive and do not provide standardized, measurable methods for evaluating data quality. Similarly, metadata requirements at conferences promote accountability but are inconsistently enforced. To address these limitations, this position paper advocates for the integration of systematic, rubric-based evaluation metrics into the dataset review process-particularly as submission volumes continue to grow. We also explore scalable, cost-effective methods for synthetic data generation, including dedicated tools and LLM-as-a-judge approaches, to support more efficient evaluation. As a call to action, we introduce DataRubrics, a structured framework for assessing the quality of both human- and model-generated datasets. Leveraging recent advances in LLM-based evaluation, DataRubrics offers a reproducible, scalable, and actionable solution for dataset quality assessment, enabling both authors and reviewers to uphold higher standards in data-centric research. We also release code to support reproducibility of LLM-based evaluations at https://github.com/datarubrics/datarubrics.</p> + https://arxiv.org/abs/2506.01789 + Mon, 02 Jun 2025 15:31:52 +0000 - Discrete Markov Bridge - https://arxiv.org/abs/2505.19752 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19752.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengli Li, Yuxuan Wang, Song-Chun Zhu, Ying Nian Wu, Zilong Zheng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Discrete diffusion has recently emerged as a promising paradigm in discrete data modeling. However, existing methods typically rely on a fixed rate transition matrix during training, which not only limits the expressiveness of latent representations, a fundamental strength of variational methods, but also constrains the overall design space. To address these limitations, we propose Discrete Markov Bridge, a novel framework specifically designed for discrete representation learning. Our approach is built upon two key components: Matrix Learning and Score Learning. We conduct a rigorous theoretical analysis, establishing formal performance guarantees for Matrix Learning and proving the convergence of the overall framework. Furthermore, we analyze the space complexity of our method, addressing practical constraints identified in prior studies. Extensive empirical evaluations validate the effectiveness of the proposed Discrete Markov Bridge, which achieves an Evidence Lower Bound (ELBO) of 1.38 on the Text8 dataset, outperforming established baselines. Moreover, the proposed model demonstrates competitive performance on the CIFAR-10 dataset, achieving results comparable to those obtained by image-specific generation approaches.</p> - https://arxiv.org/abs/2505.19752 - Mon, 26 May 2025 09:32:12 +0000 + SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics + https://arxiv.org/abs/2506.01844 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mustafa Shukor, Dana Aubakirova, Francesco Capuano, Pepijn Kooijmans, Steven Palma, Adil Zouitine, Michel Aractingi, Caroline Pascal, Martino Russi, Andres Marafioti, Simon Alibert, Matthieu Cord, Thomas Wolf, Remi Cadene</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data.</p> + https://arxiv.org/abs/2506.01844 + Mon, 02 Jun 2025 16:30:19 +0000 - Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective - https://arxiv.org/abs/2505.19815 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19815.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junnan Liu, Hongwei Liu, Linchen Xiao, Shudong Liu, Taolin Zhang, Zihan Ma, Songyang Zhang, Kai Chen</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's parameters, we identify parallels between LLM reasoning and various meta-learning paradigms. We formalize the training process for reasoning tasks as a meta-learning setup, with each question treated as an individual task, and reasoning trajectories serving as the inner loop optimization for adapting model parameters. Once trained on a diverse set of questions, the LLM develops fundamental reasoning capabilities that can generalize to previously unseen questions. Extensive empirical evaluations substantiate the strong connection between LLM reasoning and meta-learning, exploring several issues of significant interest from a meta-learning standpoint. Our work not only enhances the understanding of LLM reasoning but also provides practical insights for improving these models through established meta-learning techniques.</p> - https://arxiv.org/abs/2505.19815 - Mon, 26 May 2025 10:52:17 +0000 + ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding + https://arxiv.org/abs/2506.01853 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01853.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junliang Ye, Zhengyi Wang, Ruowen Zhao, Shenghao Xie, Jun Zhu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficient and accurate shape representation and reconstruction. Building upon the 3D-aware discrete tokens, we innovatively construct a large-scale continuous training dataset named 3D-Alpaca, encompassing generation, comprehension, and editing, thus providing rich resources for future research and training. Finally, by performing instruction-based training of the Qwen-2.5-vl-7B-Instruct model on the 3D-Alpaca dataset. Our work provides an effective attempt at extending multimodal models with basic 3D capabilities, which contributes to future research in 3D-native AI. Project page: https://github.com/JAMESYJL/ShapeLLM-Omni</p> + https://arxiv.org/abs/2506.01853 + Mon, 02 Jun 2025 16:40:50 +0000 - ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows - https://arxiv.org/abs/2505.19897 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19897.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiushi Sun, Zhoumianze Liu, Chang Ma, Zichen Ding, Fangzhi Xu, Zhangyue Yin, Haiteng Zhao, Zhenyu Wu, Kanzhi Cheng, Zhaoyang Liu, Jianing Wang, Qintong Li, Xiangru Tang, Tianbao Xie, Xiachong Feng, Xiang Li, Ben Kao, Wenhai Wang, Biqing Qi, Lingpeng Kong, Zhiyong Wu</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdisciplinary research. Recently, various LLM-based agents have been developed to assist scientific discovery progress across multiple aspects and domains. Among these, computer-using agents, capable of interacting with operating systems as humans do, are paving the way to automated scientific problem-solving and addressing routines in researchers' workflows. Recognizing the transformative potential of these agents, we introduce ScienceBoard, which encompasses two complementary contributions: (i) a realistic, multi-domain environment featuring dynamic and visually rich scientific workflows with integrated professional software, where agents can autonomously interact via different interfaces to accelerate complex research tasks and experiments; and (ii) a challenging benchmark of 169 high-quality, rigorously validated real-world tasks curated by humans, spanning scientific-discovery workflows in domains such as biochemistry, astronomy, and geoinformatics. Extensive evaluations of agents with state-of-the-art backbones (e.g., GPT-4o, Claude 3.7, UI-TARS) show that, despite some promising results, they still fall short of reliably assisting scientists in complex workflows, achieving only a 15% overall success rate. In-depth analysis further provides valuable insights for addressing current agent limitations and more effective design principles, paving the way to build more capable agents for scientific discovery. Our code, environment, and benchmark are at https://qiushisun.github.io/ScienceBoard-Home/.</p> - https://arxiv.org/abs/2505.19897 - Mon, 26 May 2025 12:27:27 +0000 + Unified Scaling Laws for Compressed Representations + https://arxiv.org/abs/2506.01863 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01863.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, the rise in computational cost for AI has motivated model compression techniques, notably quantization and sparsification, which have emerged to mitigate the steep computational demands associated with large-scale training and inference. This paper investigates the interplay between scaling laws and compression formats, exploring whether a unified scaling framework can accurately predict model performance when training occurs over various compressed representations, such as sparse, scalar-quantized, sparse-quantized or even vector-quantized formats. Our key contributions include validating a general scaling law formulation and showing that it is applicable both individually but also composably across compression types. Based on this, our main finding is demonstrating both theoretically and empirically that there exists a simple "capacity" metric -- based on the representation's ability to fit random Gaussian data -- which can robustly predict parameter efficiency across multiple compressed representations. On the practical side, we extend our formulation to directly compare the accuracy potential of different compressed formats, and to derive better algorithms for training over sparse-quantized formats.</p> + https://arxiv.org/abs/2506.01863 + Mon, 02 Jun 2025 16:52:51 +0000 - Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles - https://arxiv.org/abs/2505.19914 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.19914.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Large Language Models (LLMs), such as OpenAI's o1 and DeepSeek's R1, excel at advanced reasoning tasks like math and coding via Reinforcement Learning with Verifiable Rewards (RLVR), but still struggle with puzzles solvable by humans without domain knowledge. We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills. It includes 36 tasks across seven categories, each with 1) a generator that produces unlimited examples with controllable difficulty and 2) a rule-based verifier for automatic evaluation. This generator-verifier design supports scalable, multi-task RL training, fine-grained analysis, and seamless RLVR integration. We further propose Enigmata-Eval, a rigorous benchmark, and develop optimized multi-task RLVR strategies. Our trained model, Qwen2.5-32B-Enigmata, consistently surpasses o3-mini-high and o1 on the puzzle reasoning benchmarks like Enigmata-Eval, ARC-AGI (32.8%), and ARC-AGI 2 (0.6%). It also generalizes well to out-of-domain puzzle benchmarks and mathematical reasoning, with little multi-tasking trade-off. When trained on larger models like Seed1.5-Thinking (20B activated parameters and 200B total parameters), puzzle data from Enigmata further boosts SoTA performance on advanced math and STEM reasoning tasks such as AIME (2024-2025), BeyondAIME and GPQA (Diamond), showing nice generalization benefits of Enigmata. This work offers a unified, controllable framework for advancing logical reasoning in LLMs. Resources of this work can be found at https://seed-enigmata.github.io.</p> - https://arxiv.org/abs/2505.19914 - Mon, 26 May 2025 12:40:31 +0000 + SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis + https://arxiv.org/abs/2506.02096 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijian Wu, Jinjie Ni, Xiangyan Liu, Zichen Liu, Hang Yan, Michael Qizhe Shieh</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, we investigate how synthesized RL data can further improve RLVR. To this end, we propose SynthRL-a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training. SynthRL comprises three key stages: (1) selecting seed questions with appropriate distribution, (2) augmenting them into more challenging variants while preserving the original answers, and (3) a guaranteed verification stage that ensures near-perfect correctness and difficulty enhancement. Our empirical experiments demonstrate SynthRL's scalability and effectiveness. When applied to the MMK12 dataset, SynthRL synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples. Models trained with our synthesized data achieve consistent gains across five out-of-domain visual math reasoning benchmarks, with a significant improvement over baseline models trained on seed data alone. Notably, detailed analysis reveals that the gains are more pronounced on the most challenging evaluation samples, highlighting SynthRL's effectiveness in eliciting deeper and more complex reasoning patterns.</p> + https://arxiv.org/abs/2506.02096 + Mon, 02 Jun 2025 17:45:16 +0000 - REARANK: Reasoning Re-ranking Agent via Reinforcement Learning - https://arxiv.org/abs/2505.20046 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20046.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Le Zhang, Bo Wang, Xipeng Qiu, Siva Reddy, Aishwarya Agrawal</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular information retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in-domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results underscore the effectiveness of our approach and highlight how reinforcement learning can enhance LLM reasoning capabilities in reranking.</p> - https://arxiv.org/abs/2505.20046 - Mon, 26 May 2025 14:31:48 +0000 + Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning + https://arxiv.org/abs/2506.01939 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01939.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xionghui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin</p><p><b>Upvotes:</b> 133</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well understood. In this work, we undertake a pioneering exploration of RLVR through the novel perspective of token entropy patterns, comprehensively analyzing how different tokens influence reasoning performance. By examining token entropy patterns in Chain-of-Thought (CoT) reasoning, we observe that only a small fraction of tokens exhibit high entropy, and these tokens act as critical forks that steer the model toward diverse reasoning pathways. Furthermore, studying how entropy patterns evolve during RLVR training reveals that RLVR largely adheres to the base model's entropy patterns, primarily adjusting the entropy of high-entropy tokens. These findings highlight the significance of high-entropy tokens (i.e., forking tokens) to RLVR. We ultimately improve RLVR by restricting policy gradient updates to forking tokens and uncover a finding even beyond the 80/20 rule: utilizing only 20% of the tokens while maintaining performance comparable to full-gradient updates on the Qwen3-8B base model and significantly surpassing full-gradient updates on the Qwen3-32B (+11.04 on AIME'25 and +7.71 on AIME'24) and Qwen3-14B (+4.79 on AIME'25 and +5.21 on AIME'24) base models, highlighting a strong scaling trend. In contrast, training exclusively on the 80% lowest-entropy tokens leads to a marked decline in performance. These findings indicate that the efficacy of RLVR primarily arises from optimizing the high-entropy tokens that decide reasoning directions. Collectively, our results highlight the potential to understand RLVR through a token-entropy perspective and optimize RLVR by leveraging high-entropy minority tokens to further improve LLM reasoning.</p> + https://arxiv.org/abs/2506.01939 + Mon, 02 Jun 2025 17:54:39 +0000 - Multi-Domain Explainability of Preferences - https://arxiv.org/abs/2505.20088 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20088.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nitay Calderon, Liat Ein-Dor, Roi Reichart</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly understood. In this work, we propose a fully automated method for generating local and global concept-based explanations of preferences across multiple domains. Our method utilizes an LLM to identify concepts that distinguish between chosen and rejected responses, and to represent them with concept-based vectors. To model the relationships between concepts and preferences, we propose a white-box Hierarchical Multi-Domain Regression model that captures both domain-general and domain-specific effects. To evaluate our method, we curate a dataset spanning eight challenging and diverse domains and explain twelve mechanisms. Our method achieves strong preference prediction performance, outperforming baselines while also being explainable. Additionally, we assess explanations in two application-driven settings. First, guiding LLM outputs with concepts from LaaJ explanations yields responses that those judges consistently prefer. Second, prompting LaaJs with concepts explaining humans improves their preference predictions. Together, our work establishes a new paradigm for explainability in the era of LLMs.</p> - https://arxiv.org/abs/2505.20088 - Mon, 26 May 2025 15:01:56 +0000 + Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control + https://arxiv.org/abs/2506.01943 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.01943.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Fu, Xintao Wang, Xian Liu, Jianhong Bai, Runsen Xu, Pengfei Wan, Di Zhang, Dahua Lin</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Recent advances in video diffusion models have demonstrated strong potential for generating robotic decision-making data, with trajectory conditions further enabling fine-grained control. However, existing trajectory-based methods primarily focus on individual object motion and struggle to capture multi-object interaction crucial in complex robotic manipulation. This limitation arises from multi-feature entanglement in overlapping regions, which leads to degraded visual fidelity. To address this, we present RoboMaster, a novel framework that models inter-object dynamics through a collaborative trajectory formulation. Unlike prior methods that decompose objects, our core is to decompose the interaction process into three sub-stages: pre-interaction, interaction, and post-interaction. Each stage is modeled using the feature of the dominant object, specifically the robotic arm in the pre- and post-interaction phases and the manipulated object during interaction, thereby mitigating the drawback of multi-object feature fusion present during interaction in prior work. To further ensure subject semantic consistency throughout the video, we incorporate appearance- and shape-aware latent representations for objects. Extensive experiments on the challenging Bridge V2 dataset, as well as in-the-wild evaluation, demonstrate that our method outperforms existing approaches, establishing new state-of-the-art performance in trajectory-controlled video generation for robotic manipulation.</p> + https://arxiv.org/abs/2506.01943 + Mon, 02 Jun 2025 17:57:06 +0000 - StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs - https://arxiv.org/abs/2505.20139 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jialin Yang, Dongfu Jiang, Lipeng He, Sherman Siu, Yuxuan Zhang, Disen Liao, Zhuofeng Li, Huaye Zeng, Yiming Jia, Haozhe Wang, Benjamin Schneider, Chi Ruan, Wentao Ma, Zhiheng Lyu, Yifei Wang, Yi Lu, Quy Duc Do, Ziyan Jiang, Ping Nie, Wenhu Chen</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce StructEval, a comprehensive benchmark for evaluating LLMs' capabilities in producing both non-renderable (JSON, YAML, CSV) and renderable (HTML, React, SVG) structured formats. Unlike prior benchmarks, StructEval systematically evaluates structural fidelity across diverse formats through two paradigms: 1) generation tasks, producing structured output from natural language prompts, and 2) conversion tasks, translating between structured formats. Our benchmark encompasses 18 formats and 44 types of task, with novel metrics for format adherence and structural correctness. Results reveal significant performance gaps, even state-of-the-art models like o1-mini achieve only 75.58 average score, with open-source alternatives lagging approximately 10 points behind. We find generation tasks more challenging than conversion tasks, and producing correct visual content more difficult than generating text-only structures.</p> - https://arxiv.org/abs/2505.20139 - Mon, 26 May 2025 15:40:42 +0000 + VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments + https://arxiv.org/abs/2506.02387 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02387.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zelai Xu, Zhexuan Xu, Xiangmin Yi, Huining Yuan, Xinlei Chen, Yi Wu, Chao Yu, Yu Wang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often involve multiple agents interacting within rich visual and linguistic contexts, posing challenges with both multimodal observations and strategic interactions. To bridge this gap, we introduce Visual Strategic Bench (VS-Bench), a multimodal benchmark that evaluates VLMs for strategic reasoning and decision-making in multi-agent environments. VS-Bench comprises eight vision-grounded environments spanning cooperative, competitive, and mixed-motive interactions, designed to assess agents' ability to predict others' future moves and optimize for long-term objectives. We consider two complementary evaluation dimensions, including offline evaluation of strategic reasoning by next-action prediction accuracy and online evaluation of decision-making by normalized episode return. Extensive experiments of fourteen leading VLMs reveal a significant gap between current models and optimal performance, with the best models attaining 47.8% prediction accuracy and 24.3% normalized return. We further conduct in-depth analyses on multimodal observations, test-time scaling, social behaviors, and failure cases of VLM agents. By standardizing the evaluation and highlighting the limitations of existing models, we envision VS-Bench as a foundation for future research on strategic multimodal agents. Code and data are available at https://vs-bench.github.io.</p> + https://arxiv.org/abs/2506.02387 + Tue, 03 Jun 2025 02:57:38 +0000 - Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration - https://arxiv.org/abs/2505.20256 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20256.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Zhong, Muzhi Zhu, Zongze Du, Zheng Huang, Canyu Zhao, Mingyu Liu, Wen Wang, Hao Chen, Chunhua Shen</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution inputs. We tackle this trade-off with a two-system architecture: a Global Reasoning System selects informative keyframes and rewrites the task at low spatial cost, while a Detail Understanding System performs pixel-level grounding on the selected high-resolution snippets. Because ``optimal'' keyframe selection and reformulation are ambiguous and hard to supervise, we formulate them as a reinforcement learning (RL) problem and present Omni-R1, an end-to-end RL framework built on Group Relative Policy Optimization. Omni-R1 trains the Global Reasoning System through hierarchical rewards obtained via online collaboration with the Detail Understanding System, requiring only one epoch of RL on small task splits. Experiments on two challenging benchmarks, namely Referring Audio-Visual Segmentation (RefAVS) and Reasoning Video Object Segmentation (REVOS), show that Omni-R1 not only surpasses strong supervised baselines but also outperforms specialized state-of-the-art models, while substantially improving out-of-domain generalization and mitigating multimodal hallucination. Our results demonstrate the first successful application of RL to large-scale omnimodal reasoning and highlight a scalable path toward universally foundation models.</p> - https://arxiv.org/abs/2505.20256 - Mon, 26 May 2025 17:34:06 +0000 + OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation + https://arxiv.org/abs/2506.02397 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02397.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengjia Zhang, Junjie Wu, Jiawei Chen, Changwang Zhang, Xingyu Lou, Wangchunshu Zhou, Sheng Zhou, Can Wang, Jun Wang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Recent advanced large reasoning models (LRMs) leverage extended chain-of-thought (CoT) reasoning to solve complex tasks, achieving state-of-the-art performance. Despite their success, we identify a critical issue: a substantial portion of simple tasks solved by LRMs can also be addressed by non-reasoning LLMs using significantly fewer tokens, indicating the complex reasoning may not always be necessary. To address this, we systematically analyze the reasoning trajectories of LRMs and present a method utilizing identified paradigms and LLM-Judge to classify these trajectories as either Redundant Reasoning or Essential Reasoning. And we introduce OThink-R1, a method that prunes redundant reasoning steps while preserving logical validity. OThink-R1 dynamically employs the non-thinking mode (fast-thinking) for straightforward problems while engaging in deliberate thinking (slow-thinking) for complex problems. Experiments across mathematical and question-answering tasks demonstrate that OThink-R1 reduces reasoning redundancy by almost 23\% on average without compromising accuracy, offering practical guidelines for efficient reasoning models. The code is available at https://github.com/AgenticIR-Lab/OThink-R1.</p> + https://arxiv.org/abs/2506.02397 + Tue, 03 Jun 2025 03:31:30 +0000 - ARM: Adaptive Reasoning Model - https://arxiv.org/abs/2505.20258 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20258.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siye Wu, Jian Xie, Yikai Zhang, Aili Chen, Kai Zhang, Yu Su, Yanghua Xiao</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> While large reasoning models demonstrate strong performance on complex tasks, they lack the ability to adjust reasoning token usage based on task difficulty. This often leads to the "overthinking" problem -- excessive and unnecessary reasoning -- which, although potentially mitigated by human intervention to control the token budget, still fundamentally contradicts the goal of achieving fully autonomous AI. In this work, we propose Adaptive Reasoning Model (ARM), a reasoning model capable of adaptively selecting appropriate reasoning formats based on the task at hand. These formats include three efficient ones -- Direct Answer, Short CoT, and Code -- as well as a more elaborate format, Long CoT. To train ARM, we introduce Ada-GRPO, an adaptation of Group Relative Policy Optimization (GRPO), which addresses the format collapse issue in traditional GRPO. Ada-GRPO enables ARM to achieve high token efficiency, reducing tokens by an average of 30%, and up to 70%, while maintaining performance comparable to the model that relies solely on Long CoT. Furthermore, not only does it improve inference efficiency through reduced token generation, but it also brings a 2x speedup in training. In addition to the default Adaptive Mode, ARM supports two additional reasoning modes: 1) Instruction-Guided Mode, which allows users to explicitly specify the reasoning format via special tokens -- ideal when the appropriate format is known for a batch of tasks. 2) Consensus-Guided Mode, which aggregates the outputs of the three efficient formats and resorts to Long CoT in case of disagreement, prioritizing performance with higher token usage.</p> - https://arxiv.org/abs/2505.20258 - Mon, 26 May 2025 17:38:50 +0000 + LumosFlow: Motion-Guided Long Video Generation + https://arxiv.org/abs/2506.02497 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02497.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Chen, Hangjie Yuan, Yichen Qian, Jingyun Liang, Jiazheng Xing, Pengwei Liu, Weihua Chen, Fan Wang, Bing Su</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Long video generation has gained increasing attention due to its widespread applications in fields such as entertainment and simulation. Despite advances, synthesizing temporally coherent and visually compelling long sequences remains a formidable challenge. Conventional approaches often synthesize long videos by sequentially generating and concatenating short clips, or generating key frames and then interpolate the intermediate frames in a hierarchical manner. However, both of them still remain significant challenges, leading to issues such as temporal repetition or unnatural transitions. In this paper, we revisit the hierarchical long video generation pipeline and introduce LumosFlow, a framework introduce motion guidance explicitly. Specifically, we first employ the Large Motion Text-to-Video Diffusion Model (LMTV-DM) to generate key frames with larger motion intervals, thereby ensuring content diversity in the generated long videos. Given the complexity of interpolating contextual transitions between key frames, we further decompose the intermediate frame interpolation into motion generation and post-hoc refinement. For each pair of key frames, the Latent Optical Flow Diffusion Model (LOF-DM) synthesizes complex and large-motion optical flows, while MotionControlNet subsequently refines the warped results to enhance quality and guide intermediate frame generation. Compared with traditional video frame interpolation, we achieve 15x interpolation, ensuring reasonable and continuous motion between adjacent frames. Experiments show that our method can generate long videos with consistent motion and appearance. Code and models will be made publicly available upon acceptance. Our project page: https://jiahaochen1.github.io/LumosFlow/</p> + https://arxiv.org/abs/2506.02497 + Tue, 03 Jun 2025 06:25:00 +0000 - Lifelong Safety Alignment for Language Models - https://arxiv.org/abs/2505.20259 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Wang, Zeyu Qin, Yifei Zhao, Chao Du, Min Lin, Xueqian Wang, Tianyu Pang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise during deployment. To address this, we propose a lifelong safety alignment framework that enables LLMs to continuously adapt to new and evolving jailbreaking strategies. Our framework introduces a competitive setup between two components: a Meta-Attacker, trained to actively discover novel jailbreaking strategies, and a Defender, trained to resist them. To effectively warm up the Meta-Attacker, we first leverage the GPT-4o API to extract key insights from a large collection of jailbreak-related research papers. Through iterative training, the first iteration Meta-Attacker achieves a 73% attack success rate (ASR) on RR and a 57% transfer ASR on LAT using only single-turn attacks. Meanwhile, the Defender progressively improves its robustness and ultimately reduces the Meta-Attacker's success rate to just 7%, enabling safer and more reliable deployment of LLMs in open-ended environments. The code is available at https://github.com/sail-sg/LifelongSafetyAlignment.</p> - https://arxiv.org/abs/2505.20259 - Mon, 26 May 2025 17:40:40 +0000 + RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers + https://arxiv.org/abs/2506.02528 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yan Gong, Yiren Song, Yicheng Li, Chenglin Li, Yin Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-reference methods typically focus on style or appearance adjustments and struggle with non-rigid transformations. To address these limitations, we propose leveraging source-target image pairs to extract and transfer content-aware editing intent to novel query images. To this end, we introduce RelationAdapter, a lightweight module that enables Diffusion Transformer (DiT) based models to effectively capture and apply visual transformations from minimal examples. We also introduce Relation252K, a comprehensive dataset comprising 218 diverse editing tasks, to evaluate model generalization and adaptability in visual prompt-driven scenarios. Experiments on Relation252K show that RelationAdapter significantly improves the model's ability to understand and transfer editing intent, leading to notable gains in generation quality and overall editing performance.</p> + https://arxiv.org/abs/2506.02528 + Tue, 03 Jun 2025 07:06:35 +0000 - ImgEdit: A Unified Image Editing Dataset and Benchmark - https://arxiv.org/abs/2505.20275 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20275.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Ye, Xianyi He, Zongjian Li, Bin Lin, Shenghai Yuan, Zhiyuan Yan, Bohan Hou, Li Yuan</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce ImgEdit, a large-scale, high-quality image-editing dataset comprising 1.2 million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks. To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict post-processing. ImgEdit surpasses existing datasets in both task novelty and data quality. Using ImgEdit, we train ImgEdit-E1, an editing model using Vision Language Model to process the reference image and editing prompt, which outperforms existing open-source models on multiple tasks, highlighting the value of ImgEdit and model design. For comprehensive evaluation, we introduce ImgEdit-Bench, a benchmark designed to evaluate image editing performance in terms of instruction adherence, editing quality, and detail preservation. It includes a basic testsuite, a challenging single-turn suite, and a dedicated multi-turn suite. We evaluate both open-source and proprietary models, as well as ImgEdit-E1, providing deep analysis and actionable insights into the current behavior of image-editing models. The source data are publicly available on https://github.com/PKU-YuanGroup/ImgEdit.</p> - https://arxiv.org/abs/2505.20275 - Mon, 26 May 2025 17:53:33 +0000 + FlexPainter: Flexible and Multi-View Consistent Texture Generation + https://arxiv.org/abs/2506.02620 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongyu Yan, Leyi Wu, Jiantao Lin, Luozhou Wang, Tianshuo Xu, Zhifei Chen, Zhen Yang, Lie Xu, Shunsi Zhang, Yingcong Chen</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt modalities may prevent creators from producing desired results. Furthermore, inconsistencies between generated multi-view images often lead to poor texture generation quality. To address these issues, we introduce FlexPainter, a novel texture generation pipeline that enables flexible multi-modal conditional guidance and achieves highly consistent texture generation. A shared conditional embedding space is constructed to perform flexible aggregation between different input modalities. Utilizing such embedding space, we present an image-based CFG method to decompose structural and style information, achieving reference image-based stylization. Leveraging the 3D knowledge within the image diffusion prior, we first generate multi-view images simultaneously using a grid representation to enhance global understanding. Meanwhile, we propose a view synchronization and adaptive weighting module during diffusion sampling to further ensure local consistency. Finally, a 3D-aware texture completion model combined with a texture enhancement model is used to generate seamless, high-resolution texture maps. Comprehensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods in both flexibility and generation quality.</p> + https://arxiv.org/abs/2506.02620 + Tue, 03 Jun 2025 08:36:03 +0000 - MotionPro: A Precise Motion Controller for Image-to-Video Generation - https://arxiv.org/abs/2505.20287 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20287.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhongwei Zhang, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Wu Liu, Ting Yao, Tao Mei</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Animating images with interactive motion control has garnered popularity for image-to-video (I2V) generation. Modern approaches typically rely on large Gaussian kernels to extend motion trajectories as condition without explicitly defining movement region, leading to coarse motion control and failing to disentangle object and camera moving. To alleviate these, we present MotionPro, a precise motion controller that novelly leverages region-wise trajectory and motion mask to regulate fine-grained motion synthesis and identify target motion category (i.e., object or camera moving), respectively. Technically, MotionPro first estimates the flow maps on each training video via a tracking model, and then samples the region-wise trajectories to simulate inference scenario. Instead of extending flow through large Gaussian kernels, our region-wise trajectory approach enables more precise control by directly utilizing trajectories within local regions, thereby effectively characterizing fine-grained movements. A motion mask is simultaneously derived from the predicted flow maps to capture the holistic motion dynamics of the movement regions. To pursue natural motion control, MotionPro further strengthens video denoising by incorporating both region-wise trajectories and motion mask through feature modulation. More remarkably, we meticulously construct a benchmark, i.e., MC-Bench, with 1.1K user-annotated image-trajectory pairs, for the evaluation of both fine-grained and object-level I2V motion control. Extensive experiments conducted on WebVid-10M and MC-Bench demonstrate the effectiveness of MotionPro. Please refer to our project page for more results: https://zhw-zhang.github.io/MotionPro-page/.</p> - https://arxiv.org/abs/2505.20287 - Mon, 26 May 2025 17:59:03 +0000 + Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights + https://arxiv.org/abs/2506.02865 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02865.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mathieu Andreux, Breno Baldas Skuk, Hamza Benchekroun, Emilien Biré, Antoine Bonnet, Riaz Bordie, Matthias Brunel, Pierre-Louis Cedoz, Antoine Chassang, Mickaël Chen, Alexandra D. Constantinou, Antoine d'Andigné, Hubert de La Jonquière, Aurélien Delfosse, Ludovic Denoyer, Alexis Deprez, Augustin Derupti, Michael Eickenberg, Mathïs Federico, Charles Kantor, Xavier Koegler, Yann Labbé, Matthew C. H. Lee, Erwan Le Jumeau de Kergaradec, Amir Mahla, Avshalom Manevich, Adrien Maret, Charles Masson, Rafaël Maurin, Arturo Mena, Philippe Modard, Axel Moyal, Axel Nguyen Kerbel, Julien Revelle, Mats L. Richter, María Santos, Laurent Sifre, Maxime Theillard, Marc Thibault, Louis Thiry, Léo Tronchon, Nicolas Usunier, Tony Wu</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight collection of VLMs specialized in web navigation and information extraction. Holo1 was trained on carefully curated data sources, including open-access web content, synthetic examples, and self-produced agentic data. Holo1 tops generalist User Interface (UI) benchmarks as well as our new web UI localization benchmark, WebClick. When powered by Holo1, Surfer-H achieves a 92.2% state-of-the-art performance on WebVoyager, striking a Pareto-optimal balance between accuracy and cost-efficiency. To accelerate research advancement in agentic systems, we are open-sourcing both our WebClick evaluation dataset and the Holo1 model weights.</p> + https://arxiv.org/abs/2506.02865 + Tue, 03 Jun 2025 13:29:03 +0000 - OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation - https://arxiv.org/abs/2505.20292 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenghai Yuan, Xianyi He, Yufan Deng, Yang Ye, Jinfa Huang, Bin Lin, Chongyang Ma, Jiebo Luo, Li Yuan</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus, consisting of (i) OpenS2V-Eval, a fine-grained benchmark, and (ii) OpenS2V-5M, a million-scale dataset. In contrast to existing S2V benchmarks inherited from VBench that focus on global and coarse-grained assessment of generated videos, OpenS2V-Eval focuses on the model's ability to generate subject-consistent videos with natural subject appearance and identity fidelity. For these purposes, OpenS2V-Eval introduces 180 prompts from seven major categories of S2V, which incorporate both real and synthetic test data. Furthermore, to accurately align human preferences with S2V benchmarks, we propose three automatic metrics, NexusScore, NaturalScore and GmeScore, to separately quantify subject consistency, naturalness, and text relevance in generated videos. Building on this, we conduct a comprehensive evaluation of 16 representative S2V models, highlighting their strengths and weaknesses across different content. Moreover, we create the first open-source large-scale S2V generation dataset OpenS2V-5M, which consists of five million high-quality 720P subject-text-video triples. Specifically, we ensure subject-information diversity in our dataset by (1) segmenting subjects and building pairing information via cross-video associations and (2) prompting GPT-Image-1 on raw frames to synthesize multi-view representations. Through OpenS2V-Nexus, we deliver a robust infrastructure to accelerate future S2V generation research.</p> - https://arxiv.org/abs/2505.20292 - Mon, 26 May 2025 17:59:46 +0000 + A Controllable Examination for Long-Context Language Models + https://arxiv.org/abs/2506.02921 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.02921.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yijun Yang, Zeyu Huang, Wenhao Zhu, Zihan Qiu, Fei Yuan, Jeff Z. Pan, Ivan Titov</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Existing frameworks for evaluating long-context language models (LCLM) can be broadly categorized into real-world and synthetic tasks. Despite their utility, both approaches are accompanied by certain intrinsic limitations. Real-world tasks are too complex to interpret or characterize and are susceptible to data contamination. In contrast, synthetic tasks often adopt the needle-in-the-haystack (NIAH) format, wherein a lack of coherence between the "needle" and the "haystack" compromises their validity as proxies for realistic applications. In response to these challenges, we posit that an ideal long-context evaluation framework should be characterized by three essential features: seamless context, controllable setting, and sound evaluation. This study introduces LongBioBench, a novel benchmark that utilizes artificially generated biographies as a controlled environment for assessing LCLMs across dimensions of understanding, reasoning, and trustworthiness. Our experimental evaluation, which includes 18 LCLMs in total, demonstrates that most models still exhibit deficiencies in semantic understanding and elementary reasoning over retrieved results and are less trustworthy as context length increases. Our further analysis indicates some design choices employed by existing synthetic benchmarks, such as contextual non-coherence, numerical needles, and the absence of distractors, rendering them vulnerable to test the model long-context capabilities. Moreover, we also reveal that long-context continual pretraining primarily adjusts RoPE embedding to accommodate extended context lengths. To sum up, compared to previous synthetic benchmarks, LongBioBench achieves a better trade-off between mirroring authentic language tasks and maintaining controllability, and is highly interpretable and configurable.</p> + https://arxiv.org/abs/2506.02921 + Tue, 03 Jun 2025 14:23:06 +0000 - SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents - https://arxiv.org/abs/2505.20411 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.20411.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, Boris Yangel</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that reflects real-world SWE scenarios, where agents must interact with development environments, execute code and adapt behavior based on the outcomes of their actions. Existing datasets are either limited to one-shot code generation or comprise small, manually curated collections of interactive tasks, lacking both scale and diversity. Second, the lack of fresh interactive SWE tasks affects evaluation of rapidly improving models, as static benchmarks quickly become outdated due to contamination issues. To address these limitations, we introduce a novel, automated, and scalable pipeline to continuously extract real-world interactive SWE tasks from diverse GitHub repositories. Using this pipeline, we construct SWE-rebench, a public dataset comprising over 21,000 interactive Python-based SWE tasks, suitable for reinforcement learning of SWE agents at scale. Additionally, we use continuous supply of fresh tasks collected using SWE-rebench methodology to build a contamination-free benchmark for agentic software engineering. We compare results of various LLMs on this benchmark to results on SWE-bench Verified and show that performance of some language models might be inflated due to contamination issues.</p> - https://arxiv.org/abs/2505.20411 - Mon, 26 May 2025 18:01:00 +0000 + Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers + https://arxiv.org/abs/2506.03065 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03065.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengtao Chen, Xianfang Zeng, Maosen Zhao, Peng Ye, Mingzhu Shen, Wei Cheng, Gang Yu, Tao Chen</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency. Through detailed analysis of attention maps in Video Diffusion Transformer (vDiT), we identify three recurring sparsity patterns: diagonal, multi-diagonal, and vertical-stripe structures. And even 3-6\% attention heads can be skipped. Crucially, these patterns exhibit strong layer-depth and head-position correlations but show limited dependence on the input content. Leveraging these findings, we propose Sparse-vDiT, a sparsity acceleration framework for vDiT comprising: 1) Pattern-optimized sparse kernels that replace dense attention with computationally efficient implementations for each identified sparsity pattern. 2) An offline sparse diffusion search algorithm that selects the optimal sparse computation strategy per layer and head via hardware-aware cost modeling. After determining the optimal configuration, we fuse heads within the same layer that share the same attention strategy, enhancing inference efficiency. Integrated into state-of-the-art vDiT models (CogVideoX1.5, HunyuanVideo, and Wan2.1), Sparse-vDiT achieves 2.09times, 2.38times, and 1.67times theoretical FLOP reduction, and actual inference speedups of 1.76times, 1.85times, and 1.58times, respectively, while maintaining high visual fidelity, with PSNR values reaching 24.13, 27.09, and 22.59. Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.</p> + https://arxiv.org/abs/2506.03065 + Tue, 03 Jun 2025 16:42:37 +0000 - SageAttention2++: A More Efficient Implementation of SageAttention2 - https://arxiv.org/abs/2505.21136 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Xiaoming Xu, Jia Wei, Haofeng Huang, Pengle Zhang, Chendong Xiang, Jun Zhu, Jianfei Chen</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> The efficiency of attention is critical because its time complexity grows quadratically with sequence length. SageAttention2 addresses this by utilizing quantization to accelerate matrix multiplications (Matmul) in attention. To further accelerate SageAttention2, we propose to utilize the faster instruction of FP8 Matmul accumulated in FP16. The instruction is 2x faster than the FP8 Matmul used in SageAttention2. Our experiments show that SageAttention2++ achieves a 3.9x speedup over FlashAttention while maintaining the same attention accuracy as SageAttention2. This means SageAttention2++ effectively accelerates various models, including those for language, image, and video generation, with negligible end-to-end metrics loss. The code will be available at https://github.com/thu-ml/SageAttention.</p> - https://arxiv.org/abs/2505.21136 - Tue, 27 May 2025 12:50:36 +0000 + StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs + https://arxiv.org/abs/2506.03077 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03077.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qijun Luo, Mengqi Li, Lei Zhao, Xiao Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Training language models on long sequence data is a demanding requirement for enhancing the model's capability on complex tasks, e.g., long-chain reasoning. However, as the sequence length scales up, the memory cost for storing activation values becomes huge during the Backpropagation (BP) process, even with the application of gradient checkpointing technique. To tackle this challenge, we propose a memory-efficient and exact BP method called StreamBP, which performs a linear decomposition of the chain rule along the sequence dimension in a layer-wise manner, significantly reducing the memory cost of activation values and logits. The proposed method is applicable to common objectives such as SFT, GRPO, and DPO. From an implementation perspective, StreamBP achieves less computational FLOPs and faster BP speed by leveraging the causal structure of the language model. Compared to gradient checkpointing, StreamBP scales up the maximum sequence length of BP by 2.8-5.5 times larger, while using comparable or even less BP time. Note that StreamBP's sequence length scaling ability can be directly transferred to batch size scaling for accelerating training. We further develop a communication-efficient distributed StreamBP to effectively support multi-GPU training and broaden its applicability. Our code can be easily integrated into the training pipeline of any transformer models and is available at https://github.com/Ledzy/StreamBP.</p> + https://arxiv.org/abs/2506.03077 + Tue, 03 Jun 2025 16:54:15 +0000 - Exploring the Latent Capacity of LLMs for One-Step Text Generation - https://arxiv.org/abs/2505.21189 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gleb Mezentsev, Ivan Oseledets</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one specially trained input embedding. In this work, we explore whether such reconstruction is possible without autoregression. We show that frozen LLMs can generate hundreds of accurate tokens in just one forward pass, when provided with only two learned embeddings. This reveals a surprising and underexplored capability of LLMs - multi-token generation without iterative decoding. We investigate the behaviour of these embeddings and provide insight into the type of information they encode. We also empirically show that although these representations are not unique for a given text, they form connected and local regions in embedding space - a property that suggests the potential of learning a dedicated encoder into that space.</p> - https://arxiv.org/abs/2505.21189 - Tue, 27 May 2025 13:39:24 +0000 + DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation + https://arxiv.org/abs/2506.03123 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyao Lv, Chenyang Si, Tianlin Pan, Zhaoxi Chen, Kwan-Yee K. Wong, Yu Qiao, Ziwei Liu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Diffusion Models have achieved remarkable results in video synthesis but require iterative denoising steps, leading to substantial computational overhead. Consistency Models have made significant progress in accelerating diffusion models. However, directly applying them to video diffusion models often results in severe degradation of temporal consistency and appearance details. In this paper, by analyzing the training dynamics of Consistency Models, we identify a key conflicting learning dynamics during the distillation process: there is a significant discrepancy in the optimization gradients and loss contributions across different timesteps. This discrepancy prevents the distilled student model from achieving an optimal state, leading to compromised temporal consistency and degraded appearance details. To address this issue, we propose a parameter-efficient Dual-Expert Consistency Model~(DCM), where a semantic expert focuses on learning semantic layout and motion, while a detail expert specializes in fine detail refinement. Furthermore, we introduce Temporal Coherence Loss to improve motion consistency for the semantic expert and apply GAN and Feature Matching Loss to enhance the synthesis quality of the detail expert.Our approach achieves state-of-the-art visual quality with significantly reduced sampling steps, demonstrating the effectiveness of expert specialization in video diffusion model distillation. Our code and models are available at https://github.com/Vchitect/DCM{https://github.com/Vchitect/DCM}.</p> + https://arxiv.org/abs/2506.03123 + Tue, 03 Jun 2025 17:55:04 +0000 - rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset - https://arxiv.org/abs/2505.21297 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21297.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifei Liu, Li Lyna Zhang, Yi Zhu, Bingcheng Dong, Xudong Zhou, Ning Shang, Fan Yang, Mao Yang</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> Advancing code reasoning in large language models (LLMs) is fundamentally limited by the scarcity of high-difficulty datasets, especially those with verifiable input-output test cases necessary for rigorous solution validation at scale. We introduce rStar-Coder, which significantly improves LLM code reasoning capabilities by constructing a large-scale, verified dataset of 418K competition-level code problems, 580K long-reasoning solutions along with rich test cases of varying difficulty. This is achieved through three core contributions: (1) we curate competitive programming code problems and oracle solutions to synthesize new, solvable problems; (2) we introduce a reliable input-output test case synthesis pipeline that decouples the generation into a three-step input generation method and a mutual verification mechanism for effective output labeling; (3) we augment problems with high-quality, test-case-verified long-reasoning solutions. Extensive experiments on Qwen models (1.5B-14B) across various code reasoning benchmarks demonstrate the superiority of rStar-Coder dataset, achieving leading performance comparable to frontier reasoning LLMs with much smaller model sizes. On LiveCodeBench, rStar-Coder improves Qwen2.5-7B from 17.4% to an impressive 57.3%, and Qwen2.5-14B from 23.3% to 62.5%, surpassing o3-mini (low) by3.1%. On the more challenging USA Computing Olympiad, our 7B model achieves an average pass@1 accuracy of 16.15%, outperforming the frontier-level QWQ-32B. Code and the dataset will be released at https://github.com/microsoft/rStar.</p> - https://arxiv.org/abs/2505.21297 - Tue, 27 May 2025 15:00:57 +0000 + AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation + https://arxiv.org/abs/2506.03126 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03126.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lu Qiu, Yizhuo Li, Yuying Ge, Yixiao Ge, Ying Shan, Xihui Liu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recent advances in AI-generated content (AIGC) have significantly accelerated animation production. To produce engaging animations, it is essential to generate coherent multi-shot video clips with narrative scripts and character references. However, existing public datasets primarily focus on real-world scenarios with global descriptions, and lack reference images for consistent character guidance. To bridge this gap, we present AnimeShooter, a reference-guided multi-shot animation dataset. AnimeShooter features comprehensive hierarchical annotations and strong visual consistency across shots through an automated pipeline. Story-level annotations provide an overview of the narrative, including the storyline, key scenes, and main character profiles with reference images, while shot-level annotations decompose the story into consecutive shots, each annotated with scene, characters, and both narrative and descriptive visual captions. Additionally, a dedicated subset, AnimeShooter-audio, offers synchronized audio tracks for each shot, along with audio descriptions and sound sources. To demonstrate the effectiveness of AnimeShooter and establish a baseline for the reference-guided multi-shot video generation task, we introduce AnimeShooterGen, which leverages Multimodal Large Language Models (MLLMs) and video diffusion models. The reference image and previously generated shots are first processed by MLLM to produce representations aware of both reference and context, which are then used as the condition for the diffusion model to decode the subsequent shot. Experimental results show that the model trained on AnimeShooter achieves superior cross-shot visual consistency and adherence to reference visual guidance, which highlight the value of our dataset for coherent animated video generation.</p> + https://arxiv.org/abs/2506.03126 + Tue, 03 Jun 2025 17:55:18 +0000 - MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs - https://arxiv.org/abs/2505.21327 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiakang Yuan, Tianshuo Peng, Yilei Jiang, Yiting Lu, Renrui Zhang, Kaituo Feng, Chaoyou Fu, Tao Chen, Lei Bai, Bo Zhang, Xiangyu Yue</p><p><b>Upvotes:</b> 80</p><p><b>Summary:</b> Logical reasoning is a fundamental aspect of human intelligence and an essential capability for multimodal large language models (MLLMs). Despite the significant advancement in multimodal reasoning, existing benchmarks fail to comprehensively evaluate their reasoning abilities due to the lack of explicit categorization for logical reasoning types and an unclear understanding of reasoning. To address these issues, we introduce MME-Reasoning, a comprehensive benchmark designed to evaluate the reasoning ability of MLLMs, which covers all three types of reasoning (i.e., inductive, deductive, and abductive) in its questions. We carefully curate the data to ensure that each question effectively evaluates reasoning ability rather than perceptual skills or knowledge breadth, and extend the evaluation protocols to cover the evaluation of diverse questions. Our evaluation reveals substantial limitations of state-of-the-art MLLMs when subjected to holistic assessments of logical reasoning capabilities. Even the most advanced MLLMs show limited performance in comprehensive logical reasoning, with notable performance imbalances across reasoning types. In addition, we conducted an in-depth analysis of approaches such as ``thinking mode'' and Rule-based RL, which are commonly believed to enhance reasoning abilities. These findings highlight the critical limitations and performance imbalances of current MLLMs in diverse logical reasoning scenarios, providing comprehensive and systematic insights into the understanding and evaluation of reasoning capabilities.</p> - https://arxiv.org/abs/2505.21327 - Tue, 27 May 2025 15:23:23 +0000 + Native-Resolution Image Synthesis + https://arxiv.org/abs/2506.03131 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03131.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zidong Wang, Lei Bai, Xiangyu Yue, Wanli Ouyang, Yiyuan Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of conventional fixed-resolution, square-image methods by natively handling variable-length visual tokens, a core challenge for traditional techniques. To this end, we introduce the Native-resolution diffusion Transformer (NiT), an architecture designed to explicitly model varying resolutions and aspect ratios within its denoising process. Free from the constraints of fixed formats, NiT learns intrinsic visual distributions from images spanning a broad range of resolutions and aspect ratios. Notably, a single NiT model simultaneously achieves the state-of-the-art performance on both ImageNet-256x256 and 512x512 benchmarks. Surprisingly, akin to the robust zero-shot capabilities seen in advanced large language models, NiT, trained solely on ImageNet, demonstrates excellent zero-shot generalization performance. It successfully generates high-fidelity images at previously unseen high resolutions (e.g., 1536 x 1536) and diverse aspect ratios (e.g., 16:9, 3:1, 4:3), as shown in Figure 1. These findings indicate the significant potential of native-resolution modeling as a bridge between visual generative modeling and advanced LLM methodologies.</p> + https://arxiv.org/abs/2506.03131 + Tue, 03 Jun 2025 17:57:33 +0000 - MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios - https://arxiv.org/abs/2505.21333 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21333.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Shi, Huanqian Wang, Wulin Xie, Huanyao Zhang, Lijie Zhao, Yi-Fan Zhang, Xinfeng Li, Chaoyou Fu, Zhuoer Wen, Wenting Liu, Zhuoran Zhang, Xinlong Chen, Bohan Zeng, Sihan Yang, Yuanxing Zhang, Pengfei Wan, Haotian Wang, Wenjing Yang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce the MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1,464 videos with varying resolutions, aspect ratios, and durations, along with 2,000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2.5 Pro) achieves an accuracy of only 73.7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.</p> - https://arxiv.org/abs/2505.21333 - Tue, 27 May 2025 15:27:46 +0000 + OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models + https://arxiv.org/abs/2506.03135 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03135.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengdi Jia, Zekun Qi, Shaochen Zhang, Wenyao Zhang, Xinqiang Yu, Jiawei He, He Wang, Li Yi</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> Spatial reasoning is a key aspect of cognitive psychology and remains a major bottleneck for current vision-language models (VLMs). While extensive research has aimed to evaluate or improve VLMs' understanding of basic spatial relations, such as distinguishing left from right, near from far, and object counting, these tasks represent only the most fundamental level of spatial reasoning. In this work, we introduce OmniSpatial, a comprehensive and challenging benchmark for spatial reasoning, grounded in cognitive psychology. OmniSpatial covers four major categories: dynamic reasoning, complex spatial logic, spatial interaction, and perspective-taking, with 50 fine-grained subcategories. Through Internet data crawling and careful manual annotation, we construct over 1.5K question-answer pairs. Extensive experiments show that both open- and closed-source VLMs, as well as existing reasoning and spatial understanding models, exhibit significant limitations in comprehensive spatial understanding. We further analyze failure cases and propose potential directions for future research.</p> + https://arxiv.org/abs/2506.03135 + Tue, 03 Jun 2025 17:58:29 +0000 - HoliTom: Holistic Token Merging for Fast Video Large Language Models - https://arxiv.org/abs/2505.21334 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the LLM (inner-LLM pruning), such as FastV, incur intrinsic computational overhead in shallow layers. In contrast, methods performing token pruning before the LLM (outer-LLM pruning) primarily address spatial redundancy within individual frames or limited temporal windows, neglecting the crucial global temporal dynamics and correlations across longer video sequences. This leads to sub-optimal spatio-temporal reduction and does not leverage video compressibility fully. Crucially, the synergistic potential and mutual influence of combining these strategies remain unexplored. To further reduce redundancy, we introduce HoliTom, a novel training-free holistic token merging framework. HoliTom employs outer-LLM pruning through global redundancy-aware temporal segmentation, followed by spatial-temporal merging to reduce visual tokens by over 90%, significantly alleviating the LLM's computational burden. Complementing this, we introduce a robust inner-LLM token similarity-based merging approach, designed for superior performance and compatibility with outer-LLM pruning. Evaluations demonstrate our method's promising efficiency-performance trade-off on LLaVA-OneVision-7B, reducing computational costs to 6.9% of FLOPs while maintaining 99.1% of the original performance. Furthermore, we achieve a 2.28x reduction in Time-To-First-Token (TTFT) and a 1.32x acceleration in decoding throughput, highlighting the practical benefits of our integrated pruning approach for efficient video LLMs inference.</p> - https://arxiv.org/abs/2505.21334 - Tue, 27 May 2025 15:28:45 +0000 + Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning + https://arxiv.org/abs/2506.03136 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinjie Wang, Ling Yang, Ye Tian, Ke Shen, Mengdi Wang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This approach enables flexible and scalable training and allows the unit tester to learn directly from the coder's mistakes. Our derived ReasonFlux-Coder-7B and 14B models improve code generation accuracy by 5.3% and Best-of-N accuracy by 9.0% after optimization on Qwen2.5-Instruct models, outperforming similarly sized Qwen-Coder, DeepSeek-Coder, and Seed-Coder. They naturally extend to downstream tasks such as test-time scaling and agentic coding-achieving a 8.1% improvement over the base model. For the long-CoT model, our ReasonFlux-Coder-4B consistently outperforms Qwen3-4B while achieving 64.8% inference efficiency in unit test generation. Notably, we also find that our model can serve as an effective reward model for reinforcement learning on base models. Project: https://github.com/Gen-Verse/CURE</p> + https://arxiv.org/abs/2506.03136 + Tue, 03 Jun 2025 17:58:42 +0000 - Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning? - https://arxiv.org/abs/2505.21374 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21374.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, Ying Shan</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Recent advances in CoT reasoning and RL post-training have been reported to enhance video reasoning capabilities of MLLMs. This progress naturally raises a question: can these models perform complex video reasoning in a manner comparable to human experts? However, existing video benchmarks primarily evaluate visual perception and grounding abilities, with questions that can be answered based on explicit prompts or isolated visual cues. Such benchmarks do not fully capture the intricacies of real-world reasoning, where humans must actively search for, integrate, and analyze multiple clues before reaching a conclusion. To address this issue, we present Video-Holmes, a benchmark inspired by the reasoning process of Sherlock Holmes, designed to evaluate the complex video reasoning capabilities of MLLMs. Video-Holmes consists of 1,837 questions derived from 270 manually annotated suspense short films, which spans seven carefully designed tasks. Each task is constructed by first identifying key events and causal relationships within films, and then designing questions that require models to actively locate and connect multiple relevant visual clues scattered across different video segments. Our comprehensive evaluation of state-of-the-art MLLMs reveals that, while these models generally excel at visual perception, they encounter substantial difficulties with integrating information and often miss critical clues. For example, the best-performing model, Gemini-2.5-Pro, achieves an accuracy of only 45%, with most models scoring below 40%. We aim that Video-Holmes can serve as a "Holmes-test" for multimodal reasoning, motivating models to reason more like humans and emphasizing the ongoing challenges in this field. The benchmark is released in https://github.com/TencentARC/Video-Holmes.</p> - https://arxiv.org/abs/2505.21374 - Tue, 27 May 2025 16:05:01 +0000 + GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents + https://arxiv.org/abs/2506.03143 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qianhui Wu, Kanzhi Cheng, Rui Yang, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao, Reuben Tan, Si Qin, Lars Liden, Qingwei Lin, Huan Zhang, Tong Zhang, Jianbing Zhang, Dongmei Zhang, Jianfeng Gao</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual content and the textual plans. Most existing work formulates this as a text-based coordinate generation task. However, these approaches suffer from several limitations: weak spatial-semantic alignment, inability to handle ambiguous supervision targets, and a mismatch between the dense nature of screen coordinates and the coarse, patch-level granularity of visual features extracted by models like Vision Transformers. In this paper, we propose GUI-Actor, a VLM-based method for coordinate-free GUI grounding. At its core, GUI-Actor introduces an attention-based action head that learns to align a dedicated <ACTOR> token with all relevant visual patch tokens, enabling the model to propose one or more action regions in a single forward pass. In line with this, we further design a grounding verifier to evaluate and select the most plausible action region from the candidates proposed for action execution. Extensive experiments show that GUI-Actor outperforms prior state-of-the-art methods on multiple GUI action grounding benchmarks, with improved generalization to unseen screen resolutions and layouts. Notably, GUI-Actor-7B even surpasses UI-TARS-72B (38.1) on ScreenSpot-Pro, achieving scores of 40.7 with Qwen2-VL and 44.6 with Qwen2.5-VL as backbones. Furthermore, by incorporating the verifier, we find that fine-tuning only the newly introduced action head (~100M parameters for 7B model) while keeping the VLM backbone frozen is sufficient to achieve performance comparable to previous state-of-the-art models, highlighting that GUI-Actor can endow the underlying VLM with effective grounding capabilities without compromising its general-purpose strengths.</p> + https://arxiv.org/abs/2506.03143 + Tue, 03 Jun 2025 17:59:08 +0000 - R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing - https://arxiv.org/abs/2505.21600 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21600.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Fu, Yi Ge, Yichen You, Enshu Liu, Zhihang Yuan, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled Small Language Models (SLMs) significantly enhance efficiency, their performance suffers as they fail to follow LLMs' reasoning paths. Luckily, we reveal that only a small fraction of tokens genuinely diverge reasoning paths between LLMs and SLMs. Most generated tokens are either identical or exhibit neutral differences, such as minor variations in abbreviations or expressions. Leveraging this insight, we introduce **Roads to Rome (R2R)**, a neural token routing method that selectively utilizes LLMs only for these critical, path-divergent tokens, while leaving the majority of token generation to the SLM. We also develop an automatic data generation pipeline that identifies divergent tokens and generates token-level routing labels to train the lightweight router. We apply R2R to combine R1-1.5B and R1-32B models from the DeepSeek family, and evaluate on challenging math, coding, and QA benchmarks. With an average activated parameter size of 5.6B, R2R surpasses the average accuracy of R1-7B by 1.6x, outperforming even the R1-14B model. Compared to R1-32B, it delivers a 2.8x wall-clock speedup with comparable performance, advancing the Pareto frontier of test-time scaling efficiency. Our code is available at https://github.com/thu-nics/R2R.</p> - https://arxiv.org/abs/2505.21600 - Tue, 27 May 2025 16:57:20 +0000 + UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation + https://arxiv.org/abs/2506.03147 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03147.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Lin, Zongjian Li, Xinhua Cheng, Yuwei Niu, Yang Ye, Xianyi He, Shenghai Yuan, Wangbo Yu, Shaodong Wang, Yunyang Ge, Yatian Pang, Li Yuan</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> Although existing unified models deliver strong performance on vision-language understanding and text-to-image generation, their models are limited in exploring image perception and manipulation tasks, which are urgently desired by users for wide applications. Recently, OpenAI released their powerful GPT-4o-Image model for comprehensive image perception and manipulation, achieving expressive capability and attracting community interests. By observing the performance of GPT-4o-Image in our carefully constructed experiments, we infer that GPT-4o-Image leverages features extracted by semantic encoders instead of VAE, while VAEs are considered essential components in many image manipulation models. Motivated by such inspiring observations, we present a unified generative framework named UniWorld based on semantic features provided by powerful visual-language models and contrastive semantic encoders. As a result, we build a strong unified model using only 1% amount of BAGEL's data, which consistently outperforms BAGEL on image editing benchmarks. UniWorld also maintains competitive image understanding and generation capabilities, achieving strong performance across multiple image perception tasks. We fully open-source our models, including model weights, training and evaluation scripts, and datasets.</p> + https://arxiv.org/abs/2506.03147 + Tue, 03 Jun 2025 17:59:33 +0000 - Frame In-N-Out: Unbounded Controllable Image-to-Video Generation - https://arxiv.org/abs/2505.21491 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boyang Wang, Xuweiyi Chen, Matheus Gadelha, Zezhou Cheng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out. Specifically, starting from image-to-video generation, users can control the objects in the image to naturally leave the scene or provide breaking new identity references to enter the scene, guided by user-specified motion trajectory. To support this task, we introduce a new dataset curated semi-automatically, a comprehensive evaluation protocol targeting this setting, and an efficient identity-preserving motion-controllable video Diffusion Transformer architecture. Our evaluation shows that our proposed approach significantly outperforms existing baselines.</p> - https://arxiv.org/abs/2505.21491 - Tue, 27 May 2025 17:56:07 +0000 + IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation + https://arxiv.org/abs/2506.03150 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark, Ming-Hsuan Yang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appearance across frames. To address this limitation, we propose IllumiCraft, an end-to-end diffusion framework accepting three complementary inputs: (1) high-dynamic-range (HDR) video maps for detailed lighting control; (2) synthetically relit frames with randomized illumination changes (optionally paired with a static background reference image) to provide appearance cues; and (3) 3D point tracks that capture precise 3D geometry information. By integrating the lighting, appearance, and geometry cues within a unified diffusion architecture, IllumiCraft generates temporally coherent videos aligned with user-defined prompts. It supports background-conditioned and text-conditioned video relighting and provides better fidelity than existing controllable video generation methods. Project Page: https://yuanze-lin.me/IllumiCraft_page</p> + https://arxiv.org/abs/2506.03150 + Tue, 03 Jun 2025 17:59:52 +0000 - Reinforcing General Reasoning without Verifiers - https://arxiv.org/abs/2505.21493 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21493.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangxin Zhou, Zichen Liu, Anya Sims, Haonan Wang, Tianyu Pang, Chongxuan Li, Liang Wang, Min Lin, Chao Du</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> The recent paradigm shift towards training large language models (LLMs) using DeepSeek-R1-Zero-style reinforcement learning (RL) on verifiable rewards has led to impressive advancements in code and mathematical reasoning. However, this methodology is limited to tasks where rule-based answer verification is possible and does not naturally extend to real-world domains such as chemistry, healthcare, engineering, law, biology, business, and economics. Current practical workarounds use an additional LLM as a model-based verifier; however, this introduces issues such as reliance on a strong verifier LLM, susceptibility to reward hacking, and the practical burden of maintaining the verifier model in memory during training. To address this and extend DeepSeek-R1-Zero-style training to general reasoning domains, we propose a verifier-free method (VeriFree) that bypasses answer verification and instead uses RL to directly maximize the probability of generating the reference answer. We compare VeriFree with verifier-based methods and demonstrate that, in addition to its significant practical benefits and reduced compute requirements, VeriFree matches and even surpasses verifier-based methods on extensive evaluations across MMLU-Pro, GPQA, SuperGPQA, and math-related benchmarks. Moreover, we provide insights into this method from multiple perspectives: as an elegant integration of training both the policy and implicit verifier in a unified model, and as a variational optimization approach. Code is available at https://github.com/sail-sg/VeriFree.</p> - https://arxiv.org/abs/2505.21493 - Tue, 27 May 2025 17:56:27 +0000 + Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem + https://arxiv.org/abs/2506.03295 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yubo Wang, Ping Nie, Kai Zou, Lijun Wu, Wenhu Chen</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> We have witnessed that strong LLMs like Qwen-Math, MiMo, and Phi-4 possess immense reasoning potential inherited from the pre-training stage. With reinforcement learning (RL), these models can improve dramatically on reasoning tasks. Recent studies have shown that even RL on a single problem can unleash these models' reasoning capabilities. However, RL is not only expensive but also unstable. Even one-shot RL requires hundreds of GPU hours. This raises a critical question: Is there a more efficient way to unleash the reasoning potential of these powerful base LLMs? In this work, we demonstrate that Critique Fine-Tuning (CFT) on only one problem can effectively unleash the reasoning potential of LLMs. Our method constructs critique data by collecting diverse model-generated solutions to a single problem and using teacher LLMs to provide detailed critiques. We fine-tune Qwen and Llama family models, ranging from 1.5B to 14B parameters, on the CFT data and observe significant performance gains across diverse reasoning tasks. For example, with just 5 GPU hours of training, Qwen-Math-7B-CFT show an average improvement of 15% on six math benchmarks and 16% on three logic reasoning benchmarks. These results are comparable to or even surpass the results from RL with 20x less compute. Ablation studies reveal the robustness of one-shot CFT across different prompt problems. These results highlight one-shot CFT as a simple, general, and compute-efficient approach to unleashing the reasoning capabilities of modern LLMs.</p> + https://arxiv.org/abs/2506.03295 + Tue, 03 Jun 2025 18:35:52 +0000 - UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents - https://arxiv.org/abs/2505.21496 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21496.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Xiao, Guozhi Wang, Yuxiang Chai, Zimu Lu, Weifeng Lin, Hao He, Lue Fan, Liuyang Bian, Rui Hu, Liang Liu, Shuai Ren, Yafei Wen, Xiaoxin Chen, Aojun Zhou, Hongsheng Li</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> In this paper, we introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents: verification of trajectory outcome is challenging and high-quality training data are not scalable. These challenges are addressed by a reward model and a self-improving pipeline, respectively. The reward model, UI-Genie-RM, features an image-text interleaved architecture that efficiently pro- cesses historical context and unifies action-level and task-level rewards. To sup- port the training of UI-Genie-RM, we develop deliberately-designed data genera- tion strategies including rule-based verification, controlled trajectory corruption, and hard negative mining. To address the second challenge, a self-improvement pipeline progressively expands solvable complex GUI tasks by enhancing both the agent and reward models through reward-guided exploration and outcome verification in dynamic environments. For training the model, we generate UI- Genie-RM-517k and UI-Genie-Agent-16k, establishing the first reward-specific dataset for GUI agents while demonstrating high-quality synthetic trajectory gen- eration without manual annotation. Experimental results show that UI-Genie achieves state-of-the-art performance across multiple GUI agent benchmarks with three generations of data-model self-improvement. We open-source our complete framework implementation and generated datasets to facilitate further research in https://github.com/Euphoria16/UI-Genie.</p> - https://arxiv.org/abs/2505.21496 - Tue, 27 May 2025 17:58:06 +0000 + DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models + https://arxiv.org/abs/2506.03517 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyi Wu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ashkan Mirzaei, Igor Gilitschenski, Sergey Tulyakov, Aliaksandr Siarohin</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from independent noise. However, this approach prohibits fine-grained comparisons, and we point out that it biases the annotators towards low-motion clips as they often contain fewer visual artifacts. In this work, we introduce DenseDPO, a method that addresses these shortcomings by making three contributions. First, we create each video pair for DPO by denoising corrupted copies of a ground truth video. This results in aligned pairs with similar motion structures while differing in local details, effectively neutralizing the motion bias. Second, we leverage the resulting temporal alignment to label preferences on short segments rather than entire clips, yielding a denser and more precise learning signal. With only one-third of the labeled data, DenseDPO greatly improves motion generation over vanilla DPO, while matching it in text alignment, visual quality, and temporal consistency. Finally, we show that DenseDPO unlocks automatic preference annotation using off-the-shelf Vision Language Models (VLMs): GPT accurately predicts segment-level preferences similar to task-specifically fine-tuned video reward models, and DenseDPO trained on these labels achieves performance close to using human labels.</p> + https://arxiv.org/abs/2506.03517 + Wed, 04 Jun 2025 03:06:08 +0000 - Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers - https://arxiv.org/abs/2505.21497 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21497.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Pang, Kevin Qinghong Lin, Xiangru Jian, Xi He, Philip Torr</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> Academic poster generation is a crucial yet challenging task in scientific communication, requiring the compression of long-context interleaved documents into a single, visually coherent page. To address this challenge, we introduce the first benchmark and metric suite for poster generation, which pairs recent conference papers with author-designed posters and evaluates outputs on (i)Visual Quality-semantic alignment with human posters, (ii)Textual Coherence-language fluency, (iii)Holistic Assessment-six fine-grained aesthetic and informational criteria scored by a VLM-as-judge, and notably (iv)PaperQuiz-the poster's ability to convey core paper content as measured by VLMs answering generated quizzes. Building on this benchmark, we propose PosterAgent, a top-down, visual-in-the-loop multi-agent pipeline: the (a)Parser distills the paper into a structured asset library; the (b)Planner aligns text-visual pairs into a binary-tree layout that preserves reading order and spatial balance; and the (c)Painter-Commenter loop refines each panel by executing rendering code and using VLM feedback to eliminate overflow and ensure alignment. In our comprehensive evaluation, we find that GPT-4o outputs-though visually appealing at first glance-often exhibit noisy text and poor PaperQuiz scores, and we find that reader engagement is the primary aesthetic bottleneck, as human-designed posters rely largely on visual semantics to convey meaning. Our fully open-source variants (e.g. based on the Qwen-2.5 series) outperform existing 4o-driven multi-agent systems across nearly all metrics, while using 87% fewer tokens. It transforms a 22-page paper into a finalized yet editable .pptx poster - all for just $0.005. These findings chart clear directions for the next generation of fully automated poster-generation models. The code and datasets are available at https://github.com/Paper2Poster/Paper2Poster.</p> - https://arxiv.org/abs/2505.21497 - Tue, 27 May 2025 17:58:49 +0000 + MiMo-VL Technical Report + https://arxiv.org/abs/2506.03569 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03569.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaomi LLM-Core Team, Zihao Yue, Zhenru Lin, Yifan Song, Weikun Wang, Shuhuai Ren, Shuhao Gu, Shicheng Li, Peidian Li, Liang Zhao, Lei Li, Kainan Bao, Hao Tian, Hailin Zhang, Gang Wang, Dawei Zhu, Cici, Chenhong He, Bowen Ye, Bowen Shen, Zihan Zhang, Zihan Jiang, Zhixian Zheng, Zhichao Song, Zhenbo Luo, Yue Yu, Yudong Wang, Yuanyuan Tian, Yu Tu, Yihan Yan, Yi Huang, Xu Wang, Xinzhe Xu, Xingchen Song, Xing Zhang, Xing Yong, Xin Zhang, Xiangwei Deng, Wenyu Yang, Wenhan Ma, Weiwei Lv, Weiji Zhuang, Wei Liu, Sirui Deng, Shuo Liu, Shimao Chen, Shihua Yu, Shaohui Liu, Shande Wang, Rui Ma, Qiantong Wang, Peng Wang, Nuo Chen, Menghang Zhu, Kangyang Zhou, Kang Zhou, Kai Fang, Jun Shi, Jinhao Dong, Jiebao Xiao, Jiaming Xu, Huaqiu Liu, Hongshen Xu, Heng Qu, Haochen Zhao, Hanglong Lv, Guoan Wang, Duo Zhang, Dong Zhang, Di Zhang, Chong Ma, Chang Liu, Can Cai, Bingquan Xia</p><p><b>Upvotes:</b> 67</p><p><b>Summary:</b> We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integrating diverse reward signals. We identify the importance of incorporating high-quality reasoning data with long Chain-of-Thought into pre-training stages, and the benefits of mixed RL despite challenges in simultaneous multi-domain optimization. We also contribute a comprehensive evaluation suite covering 50+ tasks to promote reproducibility and advance the field. The model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-VL.</p> + https://arxiv.org/abs/2506.03569 + Wed, 04 Jun 2025 04:32:54 +0000 - How does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective - https://arxiv.org/abs/2505.21505 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21505.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shimao Zhang, Zhejian Lai, Xiang Liu, Shuaijie She, Xiao Liu, Yeyun Gong, Shujian Huang, Jiajun Chen</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Multilingual Alignment is an effective and representative paradigm to enhance LLMs' multilingual capabilities, which transfers the capabilities from the high-resource languages to the low-resource languages. Meanwhile, some researches on language-specific neurons reveal that there are language-specific neurons that are selectively activated in LLMs when processing different languages. This provides a new perspective to analyze and understand LLMs' mechanisms more specifically in multilingual scenarios. In this work, we propose a new finer-grained neuron identification algorithm, which detects language neurons~(including language-specific neurons and language-related neurons) and language-agnostic neurons. Furthermore, based on the distributional characteristics of different types of neurons, we divide the LLMs' internal process for multilingual inference into four parts: (1) multilingual understanding, (2) shared semantic space reasoning, (3) multilingual output space transformation, and (4) vocabulary space outputting. Additionally, we systematically analyze the models before and after alignment with a focus on different types of neurons. We also analyze the phenomenon of ''Spontaneous Multilingual Alignment''. Overall, our work conducts a comprehensive investigation based on different types of neurons, providing empirical results and valuable insights for better understanding multilingual alignment and multilingual capabilities of LLMs.</p> - https://arxiv.org/abs/2505.21505 - Tue, 27 May 2025 17:59:52 +0000 + Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation + https://arxiv.org/abs/2506.03621 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaehun Shin, Jooyoung Choi, Johan Barthelemy, Jungbeom Lee, Sungroh Yoon</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> We present Subject Fidelity Optimization (SFO), a novel comparative learning framework for zero-shot subject-driven generation that enhances subject fidelity. Beyond supervised fine-tuning methods that rely only on positive targets and use the diffusion loss as in the pre-training stage, SFO introduces synthetic negative targets and explicitly guides the model to favor positives over negatives through pairwise comparison. For negative targets, we propose Condition-Degradation Negative Sampling (CDNS), which automatically generates distinctive and informative negatives by intentionally degrading visual and textual cues without expensive human annotations. Moreover, we reweight the diffusion timesteps to focus finetuning on intermediate steps where subject details emerge. Extensive experiments demonstrate that SFO with CDNS significantly outperforms baselines in terms of both subject fidelity and text alignment on a subject-driven generation benchmark. Project page: https://subjectfidelityoptimization.github.io/</p> + https://arxiv.org/abs/2506.03621 + Wed, 04 Jun 2025 06:59:25 +0000 - RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination - https://arxiv.org/abs/2505.21925 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.21925.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chong Zeng, Yue Dong, Pieter Peers, Hongzhi Wu, Xin Tong</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We present RenderFormer, a neural rendering pipeline that directly renders an image from a triangle-based representation of a scene with full global illumination effects and that does not require per-scene training or fine-tuning. Instead of taking a physics-centric approach to rendering, we formulate rendering as a sequence-to-sequence transformation where a sequence of tokens representing triangles with reflectance properties is converted to a sequence of output tokens representing small patches of pixels. RenderFormer follows a two stage pipeline: a view-independent stage that models triangle-to-triangle light transport, and a view-dependent stage that transforms a token representing a bundle of rays to the corresponding pixel values guided by the triangle-sequence from the view-independent stage. Both stages are based on the transformer architecture and are learned with minimal prior constraints. We demonstrate and evaluate RenderFormer on scenes with varying complexity in shape and light transport.</p> - https://arxiv.org/abs/2505.21925 - Wed, 28 May 2025 03:20:46 +0000 + VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation + https://arxiv.org/abs/2506.03930 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.03930.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuansheng Ni, Ping Nie, Kai Zou, Xiang Yue, Wenhu Chen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded supervision and offer limited support for iterative code correction, resulting in fragile and unreliable plot generation. We present VisCode-200K, a large-scale instruction tuning dataset for Python-based visualization and self-correction. It contains over 200K examples from two sources: (1) validated plotting code from open-source repositories, paired with natural language instructions and rendered plots; and (2) 45K multi-turn correction dialogues from Code-Feedback, enabling models to revise faulty code using runtime feedback. We fine-tune Qwen2.5-Coder-Instruct on VisCode-200K to create VisCoder, and evaluate it on PandasPlotBench. VisCoder significantly outperforms strong open-source baselines and approaches the performance of proprietary models like GPT-4o-mini. We further adopt a self-debug evaluation protocol to assess iterative repair, demonstrating the benefits of feedback-driven learning for executable, visually accurate code generation.</p> + https://arxiv.org/abs/2506.03930 + Wed, 04 Jun 2025 13:24:44 +0000 - Let's Predict Sentence by Sentence - https://arxiv.org/abs/2505.22202 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyeonbin Hwang, Byeongguk Jeon, Seungone Kim, Jiyeon Kim, Hoyeon Chang, Sohee Yang, Seungpil Won, Dohaeng Lee, Youbin Ahn, Minjoon Seo</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to reason over structured semantic units rather than raw token sequences? In this work, we investigate whether pretrained LMs can be lifted into such abstract reasoning spaces by building on their learned representations. We present a framework that adapts a pretrained token-level LM to operate in sentence space by autoregressively predicting continuous embeddings of next sentences. We explore two embedding paradigms inspired by classical representation learning: 1) semantic embeddings, learned via autoencoding to preserve surface meaning; and 2) contextual embeddings, trained via next-sentence prediction to encode anticipatory structure. We evaluate both under two inference regimes: Discretized, which decodes each predicted embedding into text before re-encoding; and Continuous, which reasons entirely in embedding space for improved efficiency. Across four domains - mathematics, logic, commonsense, and planning - contextual embeddings under continuous inference show competitive performance with Chain-of-Thought (CoT) while reducing inference-time FLOPs on average by half. We also present early signs of scalability and modular adaptation. Finally, to visualize latent trajectories, we introduce SentenceLens, a diagnostic tool that decodes intermediate model states into interpretable sentences. Together, our results indicate that pretrained LMs can effectively transition to abstract, structured reasoning within latent embedding spaces.</p> - https://arxiv.org/abs/2505.22202 - Wed, 28 May 2025 10:28:35 +0000 + AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment + https://arxiv.org/abs/2506.04089 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04089.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anastasiia Ivanova, Eva Bakaeva, Zoya Volovikova, Alexey K. Kovalev, Aleksandr I. Panov</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> As a part of an embodied agent, Large Language Models (LLMs) are typically used for behavior planning given natural language instructions from the user. However, dealing with ambiguous instructions in real-world environments remains a challenge for LLMs. Various methods for task ambiguity detection have been proposed. However, it is difficult to compare them because they are tested on different datasets and there is no universal benchmark. For this reason, we propose AmbiK (Ambiguous Tasks in Kitchen Environment), the fully textual dataset of ambiguous instructions addressed to a robot in a kitchen environment. AmbiK was collected with the assistance of LLMs and is human-validated. It comprises 1000 pairs of ambiguous tasks and their unambiguous counterparts, categorized by ambiguity type (Human Preferences, Common Sense Knowledge, Safety), with environment descriptions, clarifying questions and answers, user intents, and task plans, for a total of 2000 tasks. We hope that AmbiK will enable researchers to perform a unified comparison of ambiguity detection methods. AmbiK is available at https://github.com/cog-model/AmbiK-dataset.</p> + https://arxiv.org/abs/2506.04089 + Wed, 04 Jun 2025 15:47:07 +0000 - Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models - https://arxiv.org/abs/2505.22232 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mehdi Ali, Manuel Brack, Max Lübbering, Elias Wendt, Abbas Goher Khan, Richard Rutmann, Alex Jude, Maurice Kraus, Alexander Arno Weber, Felix Stollenwerk, David Kaczér, Florian Mai, Lucie Flek, Rafet Sifa, Nicolas Flores-Herr, Joachim Köhler, Patrick Schramowski, Michael Fromm, Kristian Kersting</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> High-quality multilingual training data is essential for effectively pretraining large language models (LLMs). Yet, the availability of suitable open-source multilingual datasets remains limited. Existing state-of-the-art datasets mostly rely on heuristic filtering methods, restricting both their cross-lingual transferability and scalability. Here, we introduce JQL, a systematic approach that efficiently curates diverse and high-quality multilingual data at scale while significantly reducing computational demands. JQL distills LLMs' annotation capabilities into lightweight annotators based on pretrained multilingual embeddings. These models exhibit robust multilingual and cross-lingual performance, even for languages and scripts unseen during training. Evaluated empirically across 35 languages, the resulting annotation pipeline substantially outperforms current heuristic filtering methods like Fineweb2. JQL notably enhances downstream model training quality and increases data retention rates. Our research provides practical insights and valuable resources for multilingual data curation, raising the standards of multilingual dataset development.</p> - https://arxiv.org/abs/2505.22232 - Wed, 28 May 2025 11:06:54 +0000 + MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos + https://arxiv.org/abs/2506.04141 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kejian Zhu, Zhuoran Jin, Hongbang Yuan, Jiachun Li, Shangqing Tu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on understanding tasks, which only require models to match frames mentioned in the question (hereafter referred to as "question frame") and perceive a few adjacent frames. To address this gap, we propose MMR-V: A Benchmark for Multimodal Deep Reasoning in Videos. The benchmark is characterized by the following features. (1) Long-range, multi-frame reasoning: Models are required to infer and analyze evidence frames that may be far from the question frame. (2) Beyond perception: Questions cannot be answered through direct perception alone but require reasoning over hidden information. (3) Reliability: All tasks are manually annotated, referencing extensive real-world user understanding to align with common perceptions. (4) Confusability: Carefully designed distractor annotation strategies to reduce model shortcuts. MMR-V consists of 317 videos and 1,257 tasks. Our experiments reveal that current models still struggle with multi-modal reasoning; even the best-performing model, o4-mini, achieves only 52.5% accuracy. Additionally, current reasoning enhancement strategies (Chain-of-Thought and scaling test-time compute) bring limited gains. Further analysis indicates that the CoT demanded for multi-modal reasoning differs from it in textual reasoning, which partly explains the limited performance gains. We hope that MMR-V can inspire further research into enhancing multi-modal reasoning capabilities.</p> + https://arxiv.org/abs/2506.04141 + Wed, 04 Jun 2025 16:33:41 +0000 - Train Sparse Autoencoders Efficiently by Utilizing Features Correlation - https://arxiv.org/abs/2505.22255 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22255.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Sparse Autoencoders (SAEs) have demonstrated significant promise in interpreting the hidden states of language models by decomposing them into interpretable latent directions. However, training SAEs at scale remains challenging, especially when large dictionary sizes are used. While decoders can leverage sparse-aware kernels for efficiency, encoders still require computationally intensive linear operations with large output dimensions. To address this, we propose KronSAE, a novel architecture that factorizes the latent representation via Kronecker product decomposition, drastically reducing memory and computational overhead. Furthermore, we introduce mAND, a differentiable activation function approximating the binary AND operation, which improves interpretability and performance in our factorized framework.</p> - https://arxiv.org/abs/2505.22255 - Wed, 28 May 2025 11:41:11 +0000 + Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis + https://arxiv.org/abs/2506.04142 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04142.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kejian Zhu, Shangqing Tu, Zhuoran Jin, Lei Hou, Juanzi Li, Jun Zhao</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> The development of large language models (LLMs) depends on trustworthy evaluation. However, most current evaluations rely on public benchmarks, which are prone to data contamination issues that significantly compromise fairness. Previous researches have focused on constructing dynamic benchmarks to address contamination. However, continuously building new benchmarks is costly and cyclical. In this work, we aim to tackle contamination by analyzing the mechanisms of contaminated models themselves. Through our experiments, we discover that the overestimation of contaminated models is likely due to parameters acquiring shortcut solutions in training. We further propose a novel method for identifying shortcut neurons through comparative and causal analysis. Building on this, we introduce an evaluation method called shortcut neuron patching to suppress shortcut neurons. Experiments validate the effectiveness of our approach in mitigating contamination. Additionally, our evaluation results exhibit a strong linear correlation with MixEval, a recently released trustworthy benchmark, achieving a Spearman coefficient (rho) exceeding 0.95. This high correlation indicates that our method closely reveals true capabilities of the models and is trustworthy. We conduct further experiments to demonstrate the generalizability of our method across various benchmarks and hyperparameter settings. Code: https://github.com/GaryStack/Trustworthy-Evaluation</p> + https://arxiv.org/abs/2506.04142 + Wed, 04 Jun 2025 16:33:44 +0000 - Skywork Open Reasoner 1 Technical Report - https://arxiv.org/abs/2505.22312 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22312.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jujie He, Jiacai Liu, Chris Yuhao Liu, Rui Yan, Chaojie Wang, Peng Cheng, Xiaoyu Zhang, Fuxiang Zhang, Jiacheng Xu, Wei Shen, Siyuan Li, Liang Zeng, Tianwen Wei, Cheng Cheng, Bo An, Yang Liu, Yahui Zhou</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs). In this work, we present Skywork-OR1, an effective and scalable RL implementation for long Chain-of-Thought (CoT) models. Building on the DeepSeek-R1-Distill model series, our RL approach achieves notable performance gains, increasing average accuracy across AIME24, AIME25, and LiveCodeBench from 57.8% to 72.8% (+15.0%) for the 32B model and from 43.6% to 57.5% (+13.9%) for the 7B model. Our Skywork-OR1-32B model surpasses both DeepSeek-R1 and Qwen3-32B on the AIME24 and AIME25 benchmarks, while achieving comparable results on LiveCodeBench. The Skywork-OR1-7B and Skywork-OR1-Math-7B models demonstrate competitive reasoning capabilities among models of similar size. We perform comprehensive ablation studies on the core components of our training pipeline to validate their effectiveness. Additionally, we thoroughly investigate the phenomenon of entropy collapse, identify key factors affecting entropy dynamics, and demonstrate that mitigating premature entropy collapse is critical for improved test performance. To support community research, we fully open-source our model weights, training code, and training datasets.</p> - https://arxiv.org/abs/2505.22312 - Wed, 28 May 2025 12:56:04 +0000 + Image Editing As Programs with Diffusion Models + https://arxiv.org/abs/2506.04158 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04158.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujia Hu, Songhua Liu, Zhenxiong Tan, Xingyi Yang, Xinchao Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle with structurally inconsistent edits that involve substantial layout changes. To mitigate this gap, we introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture. At its core, IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations. Each operation is implemented via a lightweight adapter sharing the same DiT backbone and is specialized for a specific type of edit. Programmed by a vision-language model (VLM)-based agent, these operations collaboratively support arbitrary and structurally inconsistent transformations. By modularizing and sequencing edits in this way, IEAP generalizes robustly across a wide range of editing tasks, from simple adjustments to substantial structural changes. Extensive experiments demonstrate that IEAP significantly outperforms state-of-the-art methods on standard benchmarks across various editing scenarios. In these evaluations, our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions. Codes are available at https://github.com/YujiaHu1109/IEAP.</p> + https://arxiv.org/abs/2506.04158 + Wed, 04 Jun 2025 16:57:24 +0000 - Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start - https://arxiv.org/abs/2505.22334 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lai Wei, Yuting Li, Kaipeng Zheng, Chen Wang, Yue Wang, Linghe Kong, Lichao Sun, Weiran Huang</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress. While "aha moment" patterns--where models exhibit self-correction through reflection--are often attributed to emergent properties from RL, we first demonstrate that these patterns exist in multimodal LLMs (MLLMs) prior to RL training but may not necessarily correlate with improved reasoning performance. Building on these insights, we present a comprehensive study on enhancing multimodal reasoning through a two-stage approach: (1) supervised fine-tuning (SFT) as a cold start with structured chain-of-thought reasoning patterns, followed by (2) reinforcement learning via GRPO to further refine these capabilities. Our extensive experiments show that this combined approach consistently outperforms both SFT-only and RL-only methods across challenging multimodal reasoning benchmarks. The resulting models achieve state-of-the-art performance among open-source MLLMs at both 3B and 7B scales, with our 7B model showing substantial improvements over base models (e.g., 66.3 %rightarrow73.4 % on MathVista, 62.9 %rightarrow70.4 % on We-Math) and our 3B model achieving performance competitive with several 7B models. Overall, this work provides practical guidance for building advanced multimodal reasoning models. Our code is available at https://github.com/waltonfuture/RL-with-Cold-Start.</p> - https://arxiv.org/abs/2505.22334 - Wed, 28 May 2025 13:21:38 +0000 + OpenThoughts: Data Recipes for Reasoning Models + https://arxiv.org/abs/2506.04178 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04178.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Etash Guha, Ryan Marten, Sedrick Keh, Negin Raoof, Georgios Smyrnis, Hritik Bansal, Marianna Nezhurina, Jean Mercat, Trung Vu, Zayne Sprague, Ashima Suvarna, Benjamin Feuer, Liangyu Chen, Zaid Khan, Eric Frankel, Sachin Grover, Caroline Choi, Niklas Muennighoff, Shiye Su, Wanjia Zhao, John Yang, Shreyas Pimpalgaonkar, Kartik Sharma, Charlie Cheng-Jie Ji, Yichuan Deng, Sarah Pratt, Vivek Ramanujan, Jon Saad-Falcon, Jeffrey Li, Achal Dave, Alon Albalak, Kushal Arora, Blake Wulfe, Chinmay Hegde, Greg Durrett, Sewoong Oh, Mohit Bansal, Saadia Gabriel, Aditya Grover, Kai-Wei Chang, Vaishaal Shankar, Aaron Gokaslan, Mike A. Merrill, Tatsunori Hashimoto, Yejin Choi, Jenia Jitsev, Reinhard Heckel, Maheswaran Sathiamoorthy, Alexandros G. Dimakis, Ludwig Schmidt</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoning since state-of-the-art models often rely on proprietary datasets with little to no public information available. To address this, the goal of the OpenThoughts project is to create open-source datasets for training reasoning models. After initial explorations, our OpenThoughts2-1M dataset led to OpenThinker2-32B, the first model trained on public reasoning data to match DeepSeek-R1-Distill-32B on standard reasoning benchmarks such as AIME and LiveCodeBench. We then improve our dataset further by systematically investigating each step of our data generation pipeline with 1,000+ controlled experiments, which led to OpenThoughts3. Scaling the pipeline to 1.2M examples and using QwQ-32B as teacher yields our OpenThinker3-7B model, which achieves state-of-the-art results: 53% on AIME 2025, 51% on LiveCodeBench 06/24-01/25, and 54% on GPQA Diamond. All of our datasets and models are available on https://openthoughts.ai.</p> + https://arxiv.org/abs/2506.04178 + Wed, 04 Jun 2025 17:25:39 +0000 - Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO - https://arxiv.org/abs/2505.22453 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22453.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, Lichao Sun</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL). However, these supervised methods require expensive and manually annotated multi-modal data--an ultimately unsustainable resource. While recent efforts have explored unsupervised post-training, their methods are complex and difficult to iterate. In this work, we are the first to investigate the use of GRPO, a stable and scalable online RL algorithm, for enabling continual self-improvement without any external supervision. We propose MM-UPT, a simple yet effective framework for unsupervised post-training of MLLMs. MM-UPT builds upon GRPO, replacing traditional reward signals with a self-rewarding mechanism based on majority voting over multiple sampled responses. Our experiments demonstrate that MM-UPT significantly improves the reasoning ability of Qwen2.5-VL-7B (e.g., 66.3 %rightarrow72.9 % on MathVista, 62.9 %rightarrow68.7 % on We-Math), using standard dataset without ground truth labels. MM-UPT also outperforms prior unsupervised baselines and even approaches the results of supervised GRPO. Furthermore, we show that incorporating synthetic questions, generated solely by MLLM itself, can boost performance as well, highlighting a promising approach for scalable self-improvement. Overall, MM-UPT offers a new paradigm for continual, autonomous enhancement of MLLMs in the absence of external supervision. Our code is available at https://github.com/waltonfuture/MM-UPT.</p> - https://arxiv.org/abs/2505.22453 - Wed, 28 May 2025 15:11:16 +0000 + SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models + https://arxiv.org/abs/2506.04180 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04180.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li, Roy Ka-Wei Lee</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these limitations, we propose SuperWriter-Agent, an agent-based framework designed to enhance the quality and consistency of long-form text generation. SuperWriter-Agent introduces explicit structured thinking-through planning and refinement stages into the generation pipeline, guiding the model to follow a more deliberate and cognitively grounded process akin to that of a professional writer. Based on this framework, we construct a supervised fine-tuning dataset to train a 7B SuperWriter-LM. We further develop a hierarchical Direct Preference Optimization (DPO) procedure that uses Monte Carlo Tree Search (MCTS) to propagate final quality assessments and optimize each generation step accordingly. Empirical results across diverse benchmarks demonstrate that SuperWriter-LM achieves state-of-the-art performance, surpassing even larger-scale baseline models in both automatic evaluation and human evaluation. Furthermore, comprehensive ablation studies demonstrate the effectiveness of hierarchical DPO and underscore the value of incorporating structured thinking steps to improve the quality of long-form text generation.</p> + https://arxiv.org/abs/2506.04180 + Wed, 04 Jun 2025 17:27:42 +0000 - Fostering Video Reasoning via Next-Event Prediction - https://arxiv.org/abs/2505.22457 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haonan Wang, Hongfu Liu, Xiangyan Liu, Chao Du, Kenji Kawaguchi, Ye Wang, Tianyu Pang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video question answering often rely on annotations from humans or much stronger MLLMs, while video captioning tends to entangle temporal reasoning with spatial information. To address this gap, we propose next-event prediction (NEP), a learning task that harnesses future video segments as a rich, self-supervised signal to foster temporal reasoning. We segment each video into past and future frames: the MLLM takes the past frames as input and predicts a summary of events derived from the future frames, thereby encouraging the model to reason temporally in order to complete the task. To support this task, we curate V1-33K, a dataset comprising 33,000 automatically extracted video segments spanning diverse real-world scenarios. We further explore a range of video instruction-tuning strategies to study their effects on temporal reasoning. To evaluate progress, we introduce FutureBench to assess coherence in predicting unseen future events. Experiments validate that NEP offers a scalable and effective training paradigm for fostering temporal reasoning in MLLMs.</p> - https://arxiv.org/abs/2505.22457 - Wed, 28 May 2025 15:13:34 +0000 + Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning + https://arxiv.org/abs/2506.04207 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04207.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Chen, Yue Guo, Zhaochen Su, Yafu Li, Yulun Wu, Jiacheng Chen, Jiayu Chen, Weijie Wang, Xiaoye Qu, Yu Cheng</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Inspired by the remarkable reasoning capabilities of Deepseek-R1 in complex textual tasks, many works attempt to incentivize similar capabilities in Multimodal Large Language Models (MLLMs) by directly applying reinforcement learning (RL). However, they still struggle to activate complex reasoning. In this paper, rather than examining multimodal RL in isolation, we delve into current training pipelines and identify three crucial phenomena: 1) Effective cold start initialization is critical for enhancing MLLM reasoning. Intriguingly, we find that initializing with carefully selected text data alone can lead to performance surpassing many recent multimodal reasoning models, even before multimodal RL. 2) Standard GRPO applied to multimodal RL suffers from gradient stagnation, which degrades training stability and performance. 3) Subsequent text-only RL training, following the multimodal RL phase, further enhances multimodal reasoning. This staged training approach effectively balances perceptual grounding and cognitive reasoning development. By incorporating the above insights and addressing multimodal RL issues, we introduce ReVisual-R1, achieving a new state-of-the-art among open-source 7B MLLMs on challenging benchmarks including MathVerse, MathVision, WeMath, LogicVista, DynaMath, and challenging AIME2024 and AIME2025.</p> + https://arxiv.org/abs/2506.04207 + Wed, 04 Jun 2025 17:51:08 +0000 - The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models - https://arxiv.org/abs/2505.22617 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22617.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ganqu Cui, Yuchen Zhang, Jiacheng Chen, Lifan Yuan, Zhi Wang, Yuxin Zuo, Haozhan Li, Yuchen Fan, Huayu Chen, Weize Chen, Zhiyuan Liu, Hao Peng, Lei Bai, Wanli Ouyang, Yu Cheng, Bowen Zhou, Ning Ding</p><p><b>Upvotes:</b> 102</p><p><b>Summary:</b> This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy dropped sharply at the early training stage, this diminished exploratory ability is always accompanied with the saturation of policy performance. In practice, we establish a transformation equation R=-a*e^H+b between entropy H and downstream performance R. This empirical law strongly indicates that, the policy performance is traded from policy entropy, thus bottlenecked by its exhaustion, and the ceiling is fully predictable H=0, R=-a+b. Our finding necessitates entropy management for continuous exploration toward scaling compute for RL. To this end, we investigate entropy dynamics both theoretically and empirically. Our derivation highlights that, the change in policy entropy is driven by the covariance between action probability and the change in logits, which is proportional to its advantage when using Policy Gradient-like algorithms. Empirical study shows that, the values of covariance term and entropy differences matched exactly, supporting the theoretical conclusion. Moreover, the covariance term stays mostly positive throughout training, further explaining why policy entropy would decrease monotonically. Through understanding the mechanism behind entropy dynamics, we motivate to control entropy by restricting the update of high-covariance tokens. Specifically, we propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively. Experiments show that these methods encourage exploration, thus helping policy escape entropy collapse and achieve better downstream performance.</p> - https://arxiv.org/abs/2505.22617 - Wed, 28 May 2025 17:38:45 +0000 + Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation + https://arxiv.org/abs/2506.04225 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04225.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Huang, Wangguandong Zheng, Tengfei Wang, Yuhao Liu, Zhenwei Wang, Junta Wu, Jie Jiang, Hui Li, Rynson W. H. Lau, Wangmeng Zuo, Chunchao Guo</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant progress has been made in generating 3D objects from text or images, creating long-range, 3D-consistent, explorable 3D scenes remains a complex and challenging problem. In this work, we present Voyager, a novel video diffusion framework that generates world-consistent 3D point-cloud sequences from a single image with user-defined camera path. Unlike existing approaches, Voyager achieves end-to-end scene generation and reconstruction with inherent consistency across frames, eliminating the need for 3D reconstruction pipelines (e.g., structure-from-motion or multi-view stereo). Our method integrates three key components: 1) World-Consistent Video Diffusion: A unified architecture that jointly generates aligned RGB and depth video sequences, conditioned on existing world observation to ensure global coherence 2) Long-Range World Exploration: An efficient world cache with point culling and an auto-regressive inference with smooth video sampling for iterative scene extension with context-aware consistency, and 3) Scalable Data Engine: A video reconstruction pipeline that automates camera pose estimation and metric depth prediction for arbitrary videos, enabling large-scale, diverse training data curation without manual 3D annotations. Collectively, these designs result in a clear improvement over existing methods in visual quality and geometric accuracy, with versatile applications.</p> + https://arxiv.org/abs/2506.04225 + Wed, 04 Jun 2025 17:59:04 +0000 - Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding - https://arxiv.org/abs/2505.22618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chengyue Wu, Hao Zhang, Shuchen Xue, Zhijian Liu, Shizhe Diao, Ligeng Zhu, Ping Luo, Song Han, Enze Xie</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind autoregressive models due to the lack of Key-Value (KV) Cache and quality degradation when decoding multiple tokens simultaneously. To bridge this gap, we introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop. Additionally, we identify the root cause of generation quality degradation in parallel decoding as the disruption of token dependencies under the conditional independence assumption. To address this, we propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality. Experimental results on LLaDA and Dream models across multiple LLM benchmarks demonstrate up to 27.6times throughput improvement with minimal accuracy loss, closing the performance gap with autoregressive models and paving the way for practical deployment of Diffusion LLMs.</p> - https://arxiv.org/abs/2505.22618 - Wed, 28 May 2025 17:39:15 +0000 + RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics + https://arxiv.org/abs/2506.04308 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04308.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enshen Zhou, Jingkun An, Cheng Chi, Yi Han, Shanyu Rong, Chi Zhang, Pengwei Wang, Zhongyuan Wang, Tiejun Huang, Lu Sheng, Shanghang Zhang</p><p><b>Upvotes:</b> 39</p><p><b>Summary:</b> Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), recent approaches are still not qualified to accurately understand the complex 3D scenes and dynamically reason about the instruction-indicated locations for interaction. To this end, we propose RoboRefer, a 3D-aware VLM that can first achieve precise spatial understanding by integrating a disentangled but dedicated depth encoder via supervised fine-tuning (SFT). Moreover, RoboRefer advances generalized multi-step spatial reasoning via reinforcement fine-tuning (RFT), with metric-sensitive process reward functions tailored for spatial referring tasks. To support SFT and RFT training, we introduce RefSpatial, a large-scale dataset of 20M QA pairs (2x prior), covering 31 spatial relations (vs. 15 prior) and supporting complex reasoning processes (up to 5 steps). In addition, we introduce RefSpatial-Bench, a challenging benchmark filling the gap in evaluating spatial referring with multi-step reasoning. Experiments show that SFT-trained RoboRefer achieves state-of-the-art spatial understanding, with an average success rate of 89.6%. RFT-trained RoboRefer further outperforms all other baselines by a large margin, even surpassing Gemini-2.5-Pro by 17.4% in average accuracy on RefSpatial-Bench. Notably, RoboRefer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (e,g., UR5, G1 humanoid) in cluttered real-world scenes.</p> + https://arxiv.org/abs/2506.04308 + Wed, 04 Jun 2025 17:59:27 +0000 - WebDancer: Towards Autonomous Information Seeking Agency - https://arxiv.org/abs/2505.22648 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22648.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jialong Wu, Baixuan Li, Runnan Fang, Wenbiao Yin, Liwen Zhang, Zhengwei Tao, Dingchu Zhang, Zekun Xi, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In this work, we present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective. Our approach consists of four key stages: (1) browsing data construction, (2) trajectories sampling, (3) supervised fine-tuning for effective cold start, and (4) reinforcement learning for enhanced generalisation. We instantiate this framework in a web agent based on the ReAct, WebDancer. Empirical evaluations on the challenging information seeking benchmarks, GAIA and WebWalkerQA, demonstrate the strong performance of WebDancer, achieving considerable results and highlighting the efficacy of our training paradigm. Further analysis of agent training provides valuable insights and actionable, systematic pathways for developing more capable agentic models. The codes and demo will be released in https://github.com/Alibaba-NLP/WebAgent.</p> - https://arxiv.org/abs/2505.22648 - Wed, 28 May 2025 17:57:07 +0000 + LayerFlow: A Unified Model for Layer-aware Video Generation + https://arxiv.org/abs/2506.04228 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04228.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sihui Ji, Hao Luo, Xi Chen, Yuanpeng Tu, Yiyang Wang, Hengshuang Zhao</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We present LayerFlow, a unified solution for layer-aware video generation. Given per-layer prompts, LayerFlow generates videos for the transparent foreground, clean background, and blended scene. It also supports versatile variants like decomposing a blended video or generating the background for the given foreground and vice versa. Starting from a text-to-video diffusion transformer, we organize the videos for different layers as sub-clips, and leverage layer embeddings to distinguish each clip and the corresponding layer-wise prompts. In this way, we seamlessly support the aforementioned variants in one unified framework. For the lack of high-quality layer-wise training videos, we design a multi-stage training strategy to accommodate static images with high-quality layer annotations. Specifically, we first train the model with low-quality video data. Then, we tune a motion LoRA to make the model compatible with static frames. Afterward, we train the content LoRA on the mixture of image data with high-quality layered images along with copy-pasted video data. During inference, we remove the motion LoRA thus generating smooth videos with desired layers.</p> + https://arxiv.org/abs/2506.04228 + Wed, 04 Jun 2025 17:59:58 +0000 - Sherlock: Self-Correcting Reasoning in Vision-Language Models - https://arxiv.org/abs/2505.22651 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Ding, Ruqi Zhang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or accurate verifiers, and struggle to generalize beyond specific domains. To address these limitations, we explore self-correction as a strategy to enhance reasoning VLMs. We first conduct an in-depth analysis of reasoning VLMs' self-correction abilities and identify key gaps. Based on our findings, we introduce Sherlock, a self-correction and self-improvement training framework. Sherlock introduces a trajectory-level self-correction objective, a preference data construction method based on visual perturbation, and a dynamic beta for preference tuning. Once the model acquires self-correction capabilities using only 20k randomly sampled annotated data, it continues to self-improve without external supervision. Built on the Llama3.2-Vision-11B model, Sherlock achieves remarkable results across eight benchmarks, reaching an average accuracy of 64.1 with direct generation and 65.4 after self-correction. It outperforms LLaVA-CoT (63.2), Mulberry (63.9), and LlamaV-o1 (63.4) while using less than 20% of the annotated data.</p> - https://arxiv.org/abs/2505.22651 - Wed, 28 May 2025 17:58:03 +0000 + Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations + https://arxiv.org/abs/2506.04633 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04633.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linjie Li, Mahtab Bigverdi, Jiawei Gu, Zixian Ma, Yinuo Yang, Ziang Li, Yejin Choi, Ranjay Krishna</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation. We introduce STARE(Spatial Transformations and Reasoning Evaluation), a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through multi-step visual simulation. STARE features 4K tasks spanning foundational geometric transformations (2D and 3D), integrated spatial reasoning (cube net folding and tangram puzzles), and real-world spatial reasoning (perspective and temporal reasoning), reflecting practical cognitive challenges like object assembly, mechanical diagram interpretation, and everyday spatial navigation. Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks like 3D cube net folding and tangram puzzles that require multi-step visual simulations. Humans achieve near-perfect accuracy but take considerable time (up to 28.9s) on complex tasks, significantly speeding up (down by 7.5 seconds on average) with intermediate visual simulations. In contrast, models exhibit inconsistent performance gains from visual simulations, improving on most tasks but declining in specific cases like tangram puzzles (GPT-4o, o1) and cube net folding (Claude-3.5, Gemini-2.0 Flash), indicating that models may not know how to effectively leverage intermediate visual information.</p> + https://arxiv.org/abs/2506.04633 + Thu, 05 Jun 2025 05:09:46 +0000 - The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason - https://arxiv.org/abs/2505.22653 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui Yan</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Recent studies on post-training large language models (LLMs) for reasoning through reinforcement learning (RL) typically focus on tasks that can be accurately verified and rewarded, such as solving math problems. In contrast, our research investigates the impact of reward noise, a more practical consideration for real-world scenarios involving the post-training of LLMs using reward models. We found that LLMs demonstrate strong robustness to substantial reward noise. For example, manually flipping 40% of the reward function's outputs in math tasks still allows a Qwen-2.5-7B model to achieve rapid convergence, improving its performance on math tasks from 5% to 72%, compared to the 75% accuracy achieved by a model trained with noiseless rewards. Surprisingly, by only rewarding the appearance of key reasoning phrases (namely reasoning pattern reward, RPR), such as ``first, I need to''-without verifying the correctness of answers, the model achieved peak downstream performance (over 70% accuracy for Qwen-2.5-7B) comparable to models trained with strict correctness verification and accurate rewards. Recognizing the importance of the reasoning process over the final results, we combined RPR with noisy reward models. RPR helped calibrate the noisy reward models, mitigating potential false negatives and enhancing the LLM's performance on open-ended tasks. These findings suggest the importance of improving models' foundational abilities during the pre-training phase while providing insights for advancing post-training techniques. Our code and scripts are available at https://github.com/trestad/Noisy-Rewards-in-Learning-to-Reason.</p> - https://arxiv.org/abs/2505.22653 - Wed, 28 May 2025 17:59:03 +0000 + Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design + https://arxiv.org/abs/2506.04734 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.04734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lin Sun, Weihong Lin, Jinzhu Wu, Yongfu Zhu, Xiaoqi Jian, Guangxiang Zhao, Change Jia, Linglin Zhang, Sai-er Hu, Yuhan Wu, Xiangzheng Zhang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, science, programming, and other domains. However, our study reveals that their benchmark evaluation results are subject to significant fluctuations caused by various factors. Subtle differences in evaluation conditions can lead to substantial variations in results. Similar phenomena are observed in other open-source inference models fine-tuned based on the Deepseek-R1-Distill series, as well as in the QwQ-32B model, making their claimed performance improvements difficult to reproduce reliably. Therefore, we advocate for the establishment of a more rigorous paradigm for model performance evaluation and present our empirical assessments of the Deepseek-R1-Distill series models.</p> + https://arxiv.org/abs/2506.04734 + Thu, 05 Jun 2025 08:09:11 +0000 - FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian - https://arxiv.org/abs/2505.22759 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sara Papi, Marco Gaido, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature--with inaccessible training data and code--poses major reproducibility and fair evaluation challenges. While other domains have made substantial progress toward open science by developing fully transparent models trained on open-source (OS) code and data, similar efforts in speech remain limited. To fill this gap, we introduce FAMA, the first family of open science SFMs for English and Italian, trained on 150k+ hours of OS speech data. Moreover, we present a new dataset containing 16k hours of cleaned and pseudo-labeled speech for both languages. Results show that FAMA achieves competitive performance compared to existing SFMs while being up to 8 times faster. All artifacts, including code, datasets, and models, are released under OS-compliant licenses, promoting openness in speech technology research.</p> - https://arxiv.org/abs/2505.22759 - Wed, 28 May 2025 18:19:34 +0000 + ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development + https://arxiv.org/abs/2506.05010 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05010.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenran Xu, Xue Yang, Yiyu Wang, Qingli Hu, Zijiao Wu, Longyue Wang, Weihua Luo, Kaifu Zhang, Baotian Hu, Min Zhang</p><p><b>Upvotes:</b> 55</p><p><b>Summary:</b> We introduce ComfyUI-Copilot, a large language model-powered plugin designed to enhance the usability and efficiency of ComfyUI, an open-source platform for AI-driven art creation. Despite its flexibility and user-friendly interface, ComfyUI can present challenges to newcomers, including limited documentation, model misconfigurations, and the complexity of workflow design. ComfyUI-Copilot addresses these challenges by offering intelligent node and model recommendations, along with automated one-click workflow construction. At its core, the system employs a hierarchical multi-agent framework comprising a central assistant agent for task delegation and specialized worker agents for different usages, supported by our curated ComfyUI knowledge bases to streamline debugging and deployment. We validate the effectiveness of ComfyUI-Copilot through both offline quantitative evaluations and online user feedback, showing that it accurately recommends nodes and accelerates workflow development. Additionally, use cases illustrate that ComfyUI-Copilot lowers entry barriers for beginners and enhances workflow efficiency for experienced users. The ComfyUI-Copilot installation package and a demo video are available at https://github.com/AIDC-AI/ComfyUI-Copilot.</p> + https://arxiv.org/abs/2506.05010 + Thu, 05 Jun 2025 13:20:50 +0000 - VidText: Towards Comprehensive Evaluation for Video Text Understanding - https://arxiv.org/abs/2505.22810 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22810.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhoufaran Yang, Yan Shu, Zhifei Yang, Yan Zhang, Yu Li, Keyang Lu, Gangyan Zeng, Shaohui Liu, Yu Zhou, Nicu Sebe</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. However, existing video understanding benchmarks largely overlook textual information, while OCR-specific benchmarks are constrained to static images, limiting their ability to capture the interaction between text and dynamic visual contexts. To address this gap, we propose VidText, a new benchmark designed for comprehensive and in-depth evaluation of video text understanding. VidText offers the following key features: 1) It covers a wide range of real-world scenarios and supports multilingual content, encompassing diverse settings where video text naturally appears. 2) It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks, enabling assessment of both global summarization and local retrieval capabilities. 3) The benchmark also introduces a set of paired perception reasoning tasks, ranging from visual text perception to cross-modal reasoning between textual and visual information. Extensive experiments on 18 state-of-the-art Large Multimodal Models (LMMs) reveal that current models struggle across most tasks, with significant room for improvement. Further analysis highlights the impact of both model-intrinsic factors, such as input resolution and OCR capability, and external factors, including the use of auxiliary information and Chain-of-Thought reasoning strategies. We hope VidText will fill the current gap in video understanding benchmarks and serve as a foundation for future research on multimodal reasoning with video text in dynamic environments.</p> - https://arxiv.org/abs/2505.22810 - Wed, 28 May 2025 19:39:35 +0000 + Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models + https://arxiv.org/abs/2506.05176 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05176.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, Jingren Zhou</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 foundation models. Leveraging the Qwen3 LLMs' robust capabilities in multilingual text understanding and generation, our innovative multi-stage training pipeline combines large-scale unsupervised pre-training with supervised fine-tuning on high-quality datasets. Effective model merging strategies further ensure the robustness and adaptability of the Qwen3 Embedding series. During the training process, the Qwen3 LLMs serve not only as backbone models but also play a crucial role in synthesizing high-quality, rich, and diverse training data across multiple domains and languages, thus enhancing the training pipeline. The Qwen3 Embedding series offers a spectrum of model sizes (0.6B, 4B, 8B) for both embedding and reranking tasks, addressing diverse deployment scenarios where users can optimize for either efficiency or effectiveness. Empirical evaluations demonstrate that the Qwen3 Embedding series achieves state-of-the-art results across diverse benchmarks. Notably, it excels on the multilingual evaluation benchmark MTEB for text embedding, as well as in various retrieval tasks, including code retrieval, cross-lingual retrieval and multilingual retrieval. To facilitate reproducibility and promote community-driven research and development, the Qwen3 Embedding models are publicly available under the Apache 2.0 license.</p> + https://arxiv.org/abs/2506.05176 + Thu, 05 Jun 2025 15:49:48 +0000 - cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning - https://arxiv.org/abs/2505.22914 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.22914.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov, Alexander Nikulin, Ilya Zisman, Anna Vorontsova, Anton Konushin, Vladislav Kurenkov, Danila Rukhovich</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Computer-Aided Design (CAD) plays a central role in engineering and manufacturing, making it possible to create precise and editable 3D models. Using a variety of sensor or user-provided data as inputs for CAD reconstruction can democratize access to design applications. However, existing methods typically focus on a single input modality, such as point clouds, images, or text, which limits their generalizability and robustness. Leveraging recent advances in vision-language models (VLM), we propose a multi-modal CAD reconstruction model that simultaneously processes all three input modalities. Inspired by large language model (LLM) training paradigms, we adopt a two-stage pipeline: supervised fine-tuning (SFT) on large-scale procedurally generated data, followed by reinforcement learning (RL) fine-tuning using online feedback, obtained programatically. Furthermore, we are the first to explore RL fine-tuning of LLMs for CAD tasks demonstrating that online RL algorithms such as Group Relative Preference Optimization (GRPO) outperform offline alternatives. In the DeepCAD benchmark, our SFT model outperforms existing single-modal approaches in all three input modalities simultaneously. More importantly, after RL fine-tuning, cadrille sets new state-of-the-art on three challenging datasets, including a real-world one.</p> - https://arxiv.org/abs/2505.22914 - Wed, 28 May 2025 22:32:31 +0000 + The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text + https://arxiv.org/abs/2506.05209 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikhil Kandpal, Brian Lester, Colin Raffel, Sebastian Majstorovic, Stella Biderman, Baber Abbasi, Luca Soldaini, Enrico Shippole, A. Feder Cooper, Aviya Skowron, John Kirchenbauer, Shayne Longpre, Lintang Sutawika, Alon Albalak, Zhenlin Xu, Guilherme Penedo, Loubna Ben Allal, Elie Bakouch, John David Pressman, Honglu Fan, Dashiell Stander, Guangyu Song, Aaron Gokaslan, Tom Goldstein, Brian R. Bartoldson, Bhavya Kailkhura, Tyler Murray</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Large language models (LLMs) are typically trained on enormous quantities of unlicensed text, a practice that has led to scrutiny due to possible intellectual property infringement and ethical concerns. Training LLMs on openly licensed text presents a first step towards addressing these issues, but prior data collection efforts have yielded datasets too small or low-quality to produce performant LLMs. To address this gap, we collect, curate, and release the Common Pile v0.1, an eight terabyte collection of openly licensed text designed for LLM pretraining. The Common Pile comprises content from 30 sources that span diverse domains including research papers, code, books, encyclopedias, educational materials, audio transcripts, and more. Crucially, we validate our efforts by training two 7 billion parameter LLMs on text from the Common Pile: Comma v0.1-1T and Comma v0.1-2T, trained on 1 and 2 trillion tokens respectively. Both models attain competitive performance to LLMs trained on unlicensed text with similar computational budgets, such as Llama 1 and 2 7B. In addition to releasing the Common Pile v0.1 itself, we also release the code used in its creation as well as the training mixture and checkpoints for the Comma v0.1 models.</p> + https://arxiv.org/abs/2506.05209 + Thu, 05 Jun 2025 16:21:30 +0000 - VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning? - https://arxiv.org/abs/2505.23359 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23359.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanxin Liu, Kun Ouyang, Haoning Wu, Yi Liu, Lin Sui, Xinhao Li, Yan Zhong, Y. Charles, Xinyu Zhou, Xu Sun</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks. However, this benefit is yet to be demonstrated in the domain of video understanding, since most existing benchmarks lack the reasoning depth required to demonstrate the advantages of extended CoT chains. While recent efforts have proposed benchmarks aimed at video reasoning, the tasks are often knowledge-driven and do not rely heavily on visual content. To bridge this gap, we introduce VideoReasonBench, a benchmark designed to evaluate vision-centric, complex video reasoning. To ensure visual richness and high reasoning complexity, each video in VideoReasonBench depicts a sequence of fine-grained operations on a latent state that is only visible in part of the video. The questions evaluate three escalating levels of video reasoning skills: recalling observed visual information, inferring the content of latent states, and predicting information beyond the video. Under such task setting, models have to precisely recall multiple operations in the video, and perform step-by-step reasoning to get correct final answers for these questions. Using VideoReasonBench, we comprehensively evaluate 18 state-of-the-art multimodal LLMs (MLLMs), finding that most perform poorly on complex video reasoning, e.g., GPT-4o achieves only 6.9% accuracy, while the thinking-enhanced Gemini-2.5-Pro significantly outperforms others with 56.0% accuracy. Our investigations on "test-time scaling" further reveal that extended thinking budget, while offering none or minimal benefits on existing video benchmarks, is essential for improving the performance on VideoReasonBench.</p> - https://arxiv.org/abs/2505.23359 - Thu, 29 May 2025 11:33:43 +0000 + Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts + https://arxiv.org/abs/2506.05229 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05229.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Danil Sivtsov, Ivan Rodkin, Gleb Kuzmin, Yuri Kuratov, Ivan Oseledets</p><p><b>Upvotes:</b> 34</p><p><b>Summary:</b> Transformer models struggle with long-context inference due to their quadratic time and linear memory complexity. Recurrent Memory Transformers (RMTs) offer a solution by reducing the asymptotic cost to linear time and constant memory usage. However, their memory update mechanism leads to sequential execution, causing a performance bottleneck. We introduce Diagonal Batching, a scheduling scheme that unlocks parallelism across segments in RMTs while preserving exact recurrence. This approach eliminates the sequential constraint, enabling efficient GPU inference even for single long-context inputs without complex batching and pipelining techniques. Because the technique is purely a run-time computation reordering, existing RMT models adopt it with no retraining. Applied to a LLaMA-1B ARMT model, Diagonal Batching yields a 3.3x speedup over standard full-attention LLaMA-1B and a 1.8x speedup over the sequential RMT implementation on 131,072-token sequences. By removing sequential bottleneck, Diagonal Batching reduces inference cost and latency, thereby strengthening RMTs as a practical solution for real-world, long-context applications.</p> + https://arxiv.org/abs/2506.05229 + Thu, 05 Jun 2025 16:43:48 +0000 - SWE-bench Goes Live! - https://arxiv.org/abs/2505.23419 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23419.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Linghao Zhang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Chengxing Xie, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in this domain, they suffer from key limitations: they have not been updated since their initial releases, cover a narrow set of repositories, and depend heavily on manual effort for instance construction and environment setup. These factors hinder scalability and introduce risks of overfitting and data contamination. In this work, we present SWE-bench-Live, a live-updatable benchmark designed to overcome these challenges. Our initial release consists of 1,319 tasks derived from real GitHub issues created since 2024, spanning 93 repositories. Each task is accompanied by a dedicated Docker image to ensure reproducible execution. Central to our benchmark is \method, an automated curation pipeline that streamlines the entire process from instance creation to environment setup, removing manual bottlenecks and enabling scalability and continuous updates. We evaluate a range of state-of-the-art agent frameworks and LLMs on SWE-bench-Live, revealing a substantial performance gap compared to static benchmarks like SWE-bench, even under controlled evaluation conditions. To better understand this discrepancy, we perform detailed analyses across repository origin, issue recency, and task difficulty. By providing a fresh, diverse, and executable benchmark grounded in live repository activity, SWE-bench-Live facilitates rigorous, contamination-resistant evaluation of LLMs and agents in dynamic, real-world software development settings.</p> - https://arxiv.org/abs/2505.23419 - Thu, 29 May 2025 13:09:44 +0000 + Aligning Latent Spaces with Flow Priors + https://arxiv.org/abs/2506.05240 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhuo Li, Yuying Ge, Yixiao Ge, Ying Shan, Ping Luo</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> This paper presents a novel framework for aligning learnable latent spaces to arbitrary target distributions by leveraging flow-based generative models as priors. Our method first pretrains a flow model on the target features to capture the underlying distribution. This fixed flow model subsequently regularizes the latent space via an alignment loss, which reformulates the flow matching objective to treat the latents as optimization targets. We formally prove that minimizing this alignment loss establishes a computationally tractable surrogate objective for maximizing a variational lower bound on the log-likelihood of latents under the target distribution. Notably, the proposed method eliminates computationally expensive likelihood evaluations and avoids ODE solving during optimization. As a proof of concept, we demonstrate in a controlled setting that the alignment loss landscape closely approximates the negative log-likelihood of the target distribution. We further validate the effectiveness of our approach through large-scale image generation experiments on ImageNet with diverse target distributions, accompanied by detailed discussions and ablation studies. With both theoretical and empirical validation, our framework paves a new way for latent space alignment.</p> + https://arxiv.org/abs/2506.05240 + Thu, 05 Jun 2025 16:59:53 +0000 - Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering - https://arxiv.org/abs/2505.23604 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guangtao Zeng, Maohao Shen, Delin Chen, Zhenting Qi, Subhro Das, Dan Gutfreund, David Cox, Gregory Wornell, Wei Lu, Zhang-Wei Hong, Chuang Gan</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller models are preferable in practice due to their lower computational cost, improving their performance remains challenging. Existing approaches primarily rely on supervised fine-tuning (SFT) with high-quality data, which is expensive to curate at scale. An alternative is test-time scaling: generating multiple outputs, scoring them using a verifier, and selecting the best one. Although effective, this strategy often requires excessive sampling and costly scoring, limiting its practical application. We propose Evolutionary Test-Time Scaling (EvoScale), a sample-efficient method that treats generation as an evolutionary process. By iteratively refining outputs via selection and mutation, EvoScale shifts the output distribution toward higher-scoring regions, reducing the number of samples needed to find correct solutions. To reduce the overhead from repeatedly sampling and selection, we train the model to self-evolve using reinforcement learning (RL). Rather than relying on external verifiers at inference time, the model learns to self-improve the scores of its own generations across iterations. Evaluated on SWE-Bench-Verified, EvoScale enables our 32B model, Satori-SWE-32B, to match or exceed the performance of models with over 100B parameters while using a few samples. Code, data, and models will be fully open-sourced.</p> - https://arxiv.org/abs/2505.23604 - Thu, 29 May 2025 16:15:36 +0000 + Video World Models with Long-term Spatial Memory + https://arxiv.org/abs/2506.05284 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05284.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Wu, Shuai Yang, Ryan Po, Yinghao Xu, Ziwei Liu, Dahua Lin, Gordon Wetzstein</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals. Due to limited temporal context window sizes, these models often struggle to maintain scene consistency during revisits, leading to severe forgetting of previously generated environments. Inspired by the mechanisms of human memory, we introduce a novel framework to enhancing long-term consistency of video world models through a geometry-grounded long-term spatial memory. Our framework includes mechanisms to store and retrieve information from the long-term spatial memory and we curate custom datasets to train and evaluate world models with explicitly stored 3D memory mechanisms. Our evaluations show improved quality, consistency, and context length compared to relevant baselines, paving the way towards long-term consistent world generation.</p> + https://arxiv.org/abs/2506.05284 + Thu, 05 Jun 2025 17:42:34 +0000 - Table-R1: Inference-Time Scaling for Table Reasoning - https://arxiv.org/abs/2505.23621 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23621.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zheyuan Yang, Lyuhao Chen, Arman Cohan, Yilun Zhao</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> In this work, we present the first study to explore inference-time scaling on table reasoning tasks. We develop and evaluate two post-training strategies to enable inference-time scaling: distillation from frontier model reasoning traces and reinforcement learning with verifiable rewards (RLVR). For distillation, we introduce a large-scale dataset of reasoning traces generated by DeepSeek-R1, which we use to fine-tune LLMs into the Table-R1-SFT model. For RLVR, we propose task-specific verifiable reward functions and apply the GRPO algorithm to obtain the Table-R1-Zero model. We evaluate our Table-R1-series models across diverse table reasoning tasks, including short-form QA, fact verification, and free-form QA. Notably, the Table-R1-Zero model matches or exceeds the performance of GPT-4.1 and DeepSeek-R1, while using only a 7B-parameter LLM. It also demonstrates strong generalization to out-of-domain datasets. Extensive ablation and qualitative analyses reveal the benefits of instruction tuning, model architecture choices, and cross-task generalization, as well as emergence of essential table reasoning skills during RL training.</p> - https://arxiv.org/abs/2505.23621 - Thu, 29 May 2025 16:28:50 +0000 + EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? + https://arxiv.org/abs/2506.05287 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05287.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqian Yuan, Ronghao Dang, Long Li, Wentong Li, Dian Jiao, Xin Li, Deli Zhao, Fan Wang, Wenqiao Zhang, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> The emergence of multimodal large language models (MLLMs) has driven breakthroughs in egocentric vision applications. These applications necessitate persistent, context-aware understanding of objects, as users interact with tools in dynamic and cluttered environments. However, existing embodied benchmarks primarily focus on static scene exploration, emphasizing object's appearance and spatial attributes while neglecting the assessment of dynamic changes arising from users' interactions. To address this gap, we introduce EOC-Bench, an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios. Specially, EOC-Bench features 3,277 meticulously annotated QA pairs categorized into three temporal categories: Past, Present, and Future, covering 11 fine-grained evaluation dimensions and 3 visual object referencing types. To ensure thorough assessment, we develop a mixed-format human-in-the-loop annotation framework with four types of questions and design a novel multi-scale temporal accuracy metric for open-ended temporal evaluation. Based on EOC-Bench, we conduct comprehensive evaluations of various proprietary, open-source, and object-level MLLMs. EOC-Bench serves as a crucial tool for advancing the embodied object cognitive capabilities of MLLMs, establishing a robust foundation for developing reliable core models for embodied systems.</p> + https://arxiv.org/abs/2506.05287 + Thu, 05 Jun 2025 17:44:12 +0000 - Are Reasoning Models More Prone to Hallucination? - https://arxiv.org/abs/2505.23646 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zijun Yao, Yantao Liu, Yanxu Chen, Jianhui Chen, Junfeng Fang, Lei Hou, Juanzi Li, Tat-Seng Chua</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability. As these LRMs are mostly developed by post-training on formal reasoning tasks, whether they generalize the reasoning capability to help reduce hallucination in fact-seeking tasks remains unclear and debated. For instance, DeepSeek-R1 reports increased performance on SimpleQA, a fact-seeking benchmark, while OpenAI-o3 observes even severer hallucination. This discrepancy naturally raises the following research question: Are reasoning models more prone to hallucination? This paper addresses the question from three perspectives. (1) We first conduct a holistic evaluation for the hallucination in LRMs. Our analysis reveals that LRMs undergo a full post-training pipeline with cold start supervised fine-tuning (SFT) and verifiable reward RL generally alleviate their hallucination. In contrast, both distillation alone and RL training without cold start fine-tuning introduce more nuanced hallucinations. (2) To explore why different post-training pipelines alters the impact on hallucination in LRMs, we conduct behavior analysis. We characterize two critical cognitive behaviors that directly affect the factuality of a LRM: Flaw Repetition, where the surface-level reasoning attempts repeatedly follow the same underlying flawed logic, and Think-Answer Mismatch, where the final answer fails to faithfully match the previous CoT process. (3) Further, we investigate the mechanism behind the hallucination of LRMs from the perspective of model uncertainty. We find that increased hallucination of LRMs is usually associated with the misalignment between model uncertainty and factual accuracy. Our work provides an initial understanding of the hallucination in LRMs.</p> - https://arxiv.org/abs/2505.23646 - Thu, 29 May 2025 16:53:41 +0000 + SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training + https://arxiv.org/abs/2506.05301 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianyi Wang, Shanchuan Lin, Zhijie Lin, Yuxi Ren, Meng Wei, Zongsheng Yue, Shangchen Zhou, Hao Chen, Yang Zhao, Ceyuan Yang, Xuefeng Xiao, Chen Change Loy, Lu Jiang</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches have exhibited the potential of one-step image restoration, extending existing approaches to VR remains challenging and underexplored, particularly when dealing with high-resolution video in real-world settings. In this work, we propose a one-step diffusion-based VR model, termed as SeedVR2, which performs adversarial VR training against real data. To handle the challenging high-resolution VR within a single step, we introduce several enhancements to both model architecture and training procedures. Specifically, an adaptive window attention mechanism is proposed, where the window size is dynamically adjusted to fit the output resolutions, avoiding window inconsistency observed under high-resolution VR using window attention with a predefined window size. To stabilize and improve the adversarial post-training towards VR, we further verify the effectiveness of a series of losses, including a proposed feature matching loss without significantly sacrificing training efficiency. Extensive experiments show that SeedVR2 can achieve comparable or even better performance compared with existing VR approaches in a single step.</p> + https://arxiv.org/abs/2506.05301 + Thu, 05 Jun 2025 17:51:05 +0000 - D-AR: Diffusion via Autoregressive Models - https://arxiv.org/abs/2505.23660 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziteng Gao, Mike Zheng Shou</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> This paper presents Diffusion via Autoregressive models (D-AR), a new paradigm recasting the image diffusion process as a vanilla autoregressive procedure in the standard next-token-prediction fashion. We start by designing the tokenizer that converts images into sequences of discrete tokens, where tokens in different positions can be decoded into different diffusion denoising steps in the pixel space. Thanks to the diffusion properties, these tokens naturally follow a coarse-to-fine order, which directly lends itself to autoregressive modeling. Therefore, we apply standard next-token prediction on these tokens, without modifying any underlying designs (either causal masks or training/inference strategies), and such sequential autoregressive token generation directly mirrors the diffusion procedure in image space. That is, once the autoregressive model generates an increment of tokens, we can directly decode these tokens into the corresponding diffusion denoising step in the streaming manner. Our pipeline naturally reveals several intriguing properties, for example, it supports consistent previews when generating only a subset of tokens and enables zero-shot layout-controlled synthesis. On the standard ImageNet benchmark, our method achieves 2.09 FID using a 775M Llama backbone with 256 discrete tokens. We hope our work can inspire future research on unified autoregressive architectures of visual synthesis, especially with large language models. Code and models will be available at https://github.com/showlab/D-AR</p> - https://arxiv.org/abs/2505.23660 - Thu, 29 May 2025 17:09:25 +0000 + Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting + https://arxiv.org/abs/2506.05327 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05327.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duochao Shi, Weijie Wang, Donny Y. Chen, Zeyu Zhang, Jia-Wang Bian, Bohan Zhuang, Chunhua Shen</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantages such as efficient training, the use of known camera poses, and accurate geometry estimation. However, depth discontinuities at object boundaries often lead to fragmented or sparse point clouds, degrading rendering quality -- a well-known limitation of depth-based representations. To tackle this issue, we introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer. Although the pointmap itself may be less accurate than the depth map, it effectively enforces geometric smoothness, especially around object boundaries. With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes, delivering consistently better rendering results. Our project page: https://aim-uofa.github.io/PMLoss</p> + https://arxiv.org/abs/2506.05327 + Thu, 05 Jun 2025 17:58:23 +0000 - VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos - https://arxiv.org/abs/2505.23693 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23693.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingyu Song, Tongyan Hu, Guo Gan, Yilun Zhao</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> MLLMs have been widely studied for video question answering recently. However, most existing assessments focus on natural videos, overlooking synthetic videos, such as AI-generated content (AIGC). Meanwhile, some works in video generation rely on MLLMs to evaluate the quality of generated videos, but the capabilities of MLLMs on interpreting AIGC videos remain largely underexplored. To address this, we propose a new benchmark, VF-Eval, which introduces four tasks-coherence validation, error awareness, error type detection, and reasoning evaluation-to comprehensively evaluate the abilities of MLLMs on AIGC videos. We evaluate 13 frontier MLLMs on VF-Eval and find that even the best-performing model, GPT-4.1, struggles to achieve consistently good performance across all tasks. This highlights the challenging nature of our benchmark. Additionally, to investigate the practical applications of VF-Eval in improving video generation, we conduct an experiment, RePrompt, demonstrating that aligning MLLMs more closely with human feedback can benefit video generation.</p> - https://arxiv.org/abs/2505.23693 - Thu, 29 May 2025 17:31:13 +0000 + AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs + https://arxiv.org/abs/2506.05328 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lidong Lu, Guo Chen, Zhiqi Li, Yicheng Liu, Tong Lu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Despite progress in video understanding, current MLLMs struggle with counting tasks. Existing benchmarks are limited by short videos, close-set queries, lack of clue annotations, and weak multimodal coverage. In this paper, we introduce CG-AV-Counting, a manually-annotated clue-grounded counting benchmark with 1,027 multimodal questions and 5,845 annotated clues over 497 long videos. It supports both black-box and white-box evaluation, serving as a comprehensive testbed for both end-to-end and reasoning-based counting. To explore ways to improve model's counting capability, we propose AV-Reasoner, a model trained with GRPO and curriculum learning to generalize counting ability from related tasks. AV-Reasoner achieves state-of-the-art results across multiple benchmarks, demonstrating the effectiveness of reinforcement learning. However, experiments show that on out-of-domain benchmarks, reasoning in the language space fails to bring performance gains. The code and benchmark have been realeased on https://av-reasoner.github.io.</p> + https://arxiv.org/abs/2506.05328 + Thu, 05 Jun 2025 17:58:33 +0000 - AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views - https://arxiv.org/abs/2505.23716 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23716.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lihan Jiang, Yucheng Mao, Linning Xu, Tao Lu, Kerui Ren, Yichen Jin, Xudong Xu, Mulin Yu, Jiangmiao Pang, Feng Zhao, Dahua Lin, Bo Dai</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> We introduce AnySplat, a feed forward network for novel view synthesis from uncalibrated image collections. In contrast to traditional neural rendering pipelines that demand known camera poses and per scene optimization, or recent feed forward methods that buckle under the computational weight of dense views, our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi view datasets without any pose annotations. In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios while surpassing existing pose free approaches. Moreover, it greatly reduce rendering latency compared to optimization based neural fields, bringing real time novel view synthesis within reach for unconstrained capture settings.Project page: https://city-super.github.io/anysplat/</p> - https://arxiv.org/abs/2505.23716 - Thu, 29 May 2025 17:49:56 +0000 + MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning + https://arxiv.org/abs/2506.05331 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05331.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyan Chen, Renrui Zhang, Dongzhi Jiang, Aojun Zhou, Shilin Yan, Weifeng Lin, Hongsheng Li</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Chain-of-Thought (CoT) has widely enhanced mathematical reasoning in Large Language Models (LLMs), but it still remains challenging for extending it to multimodal domains. Existing works either adopt a similar textual reasoning for image input, or seek to interleave visual signals into mathematical CoT. However, they face three key limitations for math problem-solving: reliance on coarse-grained box-shaped image regions, limited perception of vision encoders on math content, and dependence on external capabilities for visual modification. In this paper, we propose MINT-CoT, introducing Mathematical INterleaved Tokens for Chain-of-Thought visual reasoning. MINT-CoT adaptively interleaves relevant visual tokens into textual reasoning steps via an Interleave Token, which dynamically selects visual regions of any shapes within math figures. To empower this capability, we construct the MINT-CoT dataset, containing 54K mathematical problems aligning each reasoning step with visual regions at the token level, accompanied by a rigorous data generation pipeline. We further present a three-stage MINT-CoT training strategy, progressively combining text-only CoT SFT, interleaved CoT SFT, and interleaved CoT RL, which derives our MINT-CoT-7B model. Extensive experiments demonstrate the effectiveness of our method for effective visual interleaved reasoning in mathematical domains, where MINT-CoT-7B outperforms the baseline model by +34.08% on MathVista, +28.78% on GeoQA, and +23.2% on MMStar, respectively. Our code and data are available at https://github.com/xinyan-cxy/MINT-CoT</p> + https://arxiv.org/abs/2506.05331 + Thu, 05 Jun 2025 17:59:02 +0000 - ATLAS: Learning to Optimally Memorize the Context at Test Time - https://arxiv.org/abs/2505.23735 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23735.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Behrouz, Zeman Li, Praneeth Kacham, Majid Daliri, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale. Their quadratic memory and time complexity, however, bound their applicability in longer sequences and so has motivated researchers to explore effective alternative architectures such as modern recurrent neural networks (a.k.a long-term recurrent memory module). Despite their recent success in diverse downstream tasks, they struggle in tasks that requires long context understanding and extrapolation to longer sequences. We observe that these shortcomings come from three disjoint aspects in their design: (1) limited memory capacity that is bounded by the architecture of memory and feature mapping of the input; (2) online nature of update, i.e., optimizing the memory only with respect to the last input; and (3) less expressive management of their fixed-size memory. To enhance all these three aspects, we present ATLAS, a long-term memory module with high capacity that learns to memorize the context by optimizing the memory based on the current and past tokens, overcoming the online nature of long-term memory models. Building on this insight, we present a new family of Transformer-like architectures, called DeepTransformers, that are strict generalizations of the original Transformer architecture. Our experimental results on language modeling, common-sense reasoning, recall-intensive, and long-context understanding tasks show that ATLAS surpasses the performance of Transformers and recent linear recurrent models. ATLAS further improves the long context performance of Titans, achieving +80\% accuracy in 10M context length of BABILong benchmark.</p> - https://arxiv.org/abs/2505.23735 - Thu, 29 May 2025 17:57:16 +0000 + Search Arena: Analyzing Search-Augmented LLMs + https://arxiv.org/abs/2506.05334 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05334.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mihran Miroyan, Tsung-Han Wu, Logan King, Tianle Li, Jiayi Pan, Xinyan Hu, Wei-Lin Chiang, Anastasios N. Angelopoulos, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Search-augmented language models combine web search with Large Language Models (LLMs) to improve response groundedness and freshness. However, analyzing these systems remains challenging: existing datasets are limited in scale and narrow in scope, often constrained to static, single-turn, fact-checking questions. In this work, we introduce Search Arena, a crowd-sourced, large-scale, human-preference dataset of over 24,000 paired multi-turn user interactions with search-augmented LLMs. The dataset spans diverse intents and languages, and contains full system traces with around 12,000 human preference votes. Our analysis reveals that user preferences are influenced by the number of citations, even when the cited content does not directly support the attributed claims, uncovering a gap between perceived and actual credibility. Furthermore, user preferences vary across cited sources, revealing that community-driven platforms are generally preferred and static encyclopedic sources are not always appropriate and reliable. To assess performance across different settings, we conduct cross-arena analyses by testing search-augmented LLMs in a general-purpose chat environment and conventional LLMs in search-intensive settings. We find that web search does not degrade and may even improve performance in non-search settings; however, the quality in search settings is significantly affected if solely relying on the model's parametric knowledge. We open-sourced the dataset to support future research in this direction. Our dataset and code are available at: https://github.com/lmarena/search-arena.</p> + https://arxiv.org/abs/2506.05334 + Thu, 05 Jun 2025 17:59:26 +0000 - Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence - https://arxiv.org/abs/2505.23747 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23747.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Diankun Wu, Fangfu Liu, Yi-Hsin Hung, Yueqi Duan</p><p><b>Upvotes:</b> 60</p><p><b>Summary:</b> Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or 2.5D data to incorporate spatial awareness, restricting their utility in scenarios with only 2D inputs, such as images or videos. In this paper, we present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations. Unlike conventional video MLLMs which rely on CLIP-based visual encoders optimized for semantic understanding, our key insight is to unleash the strong structure prior from the feed-forward visual geometry foundation model. Specifically, we propose a dual-encoder architecture: a pretrained 2D visual encoder to extract semantic features, and a spatial encoder-initialized from the backbone of the visual geometry model-to extract 3D structure features. A connector then integrates both features into unified visual tokens for enhanced spatial understanding. Furthermore, we propose a space-aware frame sampling strategy at inference time, which selects the spatially informative frames of a video sequence, ensuring that even under limited token length, the model focuses on frames critical for spatial reasoning. Beyond architecture improvements, we construct the Spatial-MLLM-120k dataset and train the model on it using supervised fine-tuning and GRPO. Extensive experiments on various real-world datasets demonstrate that our spatial-MLLM achieves state-of-the-art performance in a wide range of visual-based spatial understanding and reasoning tasks. Project page: https://diankun-wu.github.io/Spatial-MLLM/.</p> - https://arxiv.org/abs/2505.23747 - Thu, 29 May 2025 17:59:04 +0000 + SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs + https://arxiv.org/abs/2506.05344 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05344.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahui Wang, Zuyan Liu, Yongming Rao, Jiwen Lu</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention mechanisms. We reveal a surprising sparsity phenomenon: only a small subset (approximately less than 5%) of attention heads in LLMs actively contribute to visual understanding, termed visual heads. To identify these heads efficiently, we design a training-free framework that quantifies head-level visual relevance through targeted response analysis. Building on this discovery, we introduce SparseMM, a KV-Cache optimization strategy that allocates asymmetric computation budgets to heads in LLMs based on their visual scores, leveraging the sparity of visual heads for accelerating the inference of MLLMs. Compared with prior KV-Cache acceleration methods that ignore the particularity of visual, SparseMM prioritizes stress and retaining visual semantics during decoding. Extensive evaluations across mainstream multimodal benchmarks demonstrate that SparseMM achieves superior accuracy-efficiency trade-offs. Notably, SparseMM delivers 1.38x real-time acceleration and 52% memory reduction during generation while maintaining performance parity on efficiency test. Our project is open sourced at https://github.com/CR400AF-A/SparseMM.</p> + https://arxiv.org/abs/2506.05344 + Thu, 05 Jun 2025 17:59:55 +0000 - LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers - https://arxiv.org/abs/2505.23758 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23758.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We introduce LoRAShop, the first framework for multi-concept image editing with LoRA models. LoRAShop builds on a key observation about the feature interaction patterns inside Flux-style diffusion transformers: concept-specific transformer features activate spatially coherent regions early in the denoising process. We harness this observation to derive a disentangled latent mask for each concept in a prior forward pass and blend the corresponding LoRA weights only within regions bounding the concepts to be personalized. The resulting edits seamlessly integrate multiple subjects or styles into the original scene while preserving global context, lighting, and fine details. Our experiments demonstrate that LoRAShop delivers better identity preservation compared to baselines. By eliminating retraining and external constraints, LoRAShop turns personalized diffusion models into a practical `photoshop-with-LoRAs' tool and opens new avenues for compositional visual storytelling and rapid creative iteration.</p> - https://arxiv.org/abs/2505.23758 - Thu, 29 May 2025 17:59:46 +0000 + Inference-Time Hyper-Scaling with KV Cache Compression + https://arxiv.org/abs/2506.05345 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05345.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adrian Łańcucki, Konrad Staniszewski, Piotr Nawrot, Edoardo M. Ponti</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than the number of generated tokens. Hence, we explore inference-time hyper-scaling: by compressing the KV cache, we can generate more tokens within the same compute budget and further improve the accuracy of scaled inference. The success of this approach, however, hinges on the ability of compression methods to preserve accuracy even at high compression ratios. To make hyper-scaling practical, we introduce Dynamic Memory Sparsification (DMS), a novel method for sparsifying KV caches that only requires 1K training steps to achieve 8times compression, while maintaining better accuracy than training-free sparse attention. Instead of prematurely discarding cached tokens, DMS delays token eviction, implicitly merging representations and preserving critical information. We demonstrate the effectiveness of inference-time hyper-scaling with DMS on multiple families of LLMs, showing that it boosts accuracy for comparable inference runtime and memory load. For instance, we enhance Qwen-R1 32B by an average of 9.1 points on AIME 24, 7.6 on GPQA, and 9.6 on LiveCodeBench across compute budgets.</p> + https://arxiv.org/abs/2506.05345 + Thu, 05 Jun 2025 17:59:55 +0000 - ZeroGUI: Automating Online GUI Learning at Zero Human Cost - https://arxiv.org/abs/2505.23762 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2505.23762.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenyu Yang, Shiqian Su, Shi Liu, Xuan Dong, Yue Yu, Weijie Su, Xuehui Wang, Zhaoyang Liu, Jinguo Zhu, Hao Li, Wenhai Wang, Yu Qiao, Xizhou Zhu, Jifeng Dai</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The rapid advancement of large Vision-Language Models (VLMs) has propelled the development of pure-vision-based GUI Agents, capable of perceiving and operating Graphical User Interfaces (GUI) to autonomously fulfill user instructions. However, existing approaches usually adopt an offline learning framework, which faces two core limitations: (1) heavy reliance on high-quality manual annotations for element grounding and action supervision, and (2) limited adaptability to dynamic and interactive environments. To address these limitations, we propose ZeroGUI, a scalable, online learning framework for automating GUI Agent training at Zero human cost. Specifically, ZeroGUI integrates (i) VLM-based automatic task generation to produce diverse training goals from the current environment state, (ii) VLM-based automatic reward estimation to assess task success without hand-crafted evaluation functions, and (iii) two-stage online reinforcement learning to continuously interact with and learn from GUI environments. Experiments on two advanced GUI Agents (UI-TARS and Aguvis) demonstrate that ZeroGUI significantly boosts performance across OSWorld and AndroidLab environments. The code is available at https://github.com/OpenGVLab/ZeroGUI.</p> - https://arxiv.org/abs/2505.23762 - Thu, 29 May 2025 17:59:51 +0000 + VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos + https://arxiv.org/abs/2506.05349 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2506.05349.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanoona Rasheed, Abdelrahman Shaker, Anqi Tang, Muhammad Maaz, Ming-Hsuan Yang, Salman Khan, Fahad Khan</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporally extended cross-modal reasoning on videos. The benchmark spans 10 diverse mathematical domains, covering videos ranging from 10 seconds to over 1 hour. It requires models to interpret structured visual content, understand instructional narratives, and jointly ground concepts across visual, audio, and textual modalities. We employ graduate-level experts to ensure high quality, totaling over 920 man-hours of annotation. To reflect real-world scenarios, questions are designed around three core reasoning challenges: direct problem solving, where answers are grounded in the presented question; conceptual transfer, which requires applying learned methods to new problems; and deep instructional comprehension, involving multi-step reasoning over extended explanations and partially worked-out solutions. Each question includes multi-step reasoning annotations, enabling fine-grained diagnosis of model capabilities. Through this benchmark, we highlight the limitations of existing approaches and establish a systematic evaluation framework for models that must reason, rather than merely perceive, across temporally extended and modality-rich mathematical problem settings. Our benchmark and evaluation code are available at: https://mbzuai-oryx.github.io/VideoMathQA</p> + https://arxiv.org/abs/2506.05349 + Thu, 05 Jun 2025 17:59:58 +0000