diff --git a/feed.xml b/feed.xml index 9f4d73d..72dab2b 100644 --- a/feed.xml +++ b/feed.xml @@ -7,251 +7,307 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 29 Sep 2025 00:02:47 +0000 + Tue, 30 Sep 2025 00:02:57 +0000 - Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory - https://arxiv.org/abs/2509.14662 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14662.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Li, Nan Zhang, Chenrui Fan, Hong Jiao, Yanbin Fu, Sydney Peters, Qingshu Xu, Robert Lissitz, Tianyi Zhou</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> While Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, we lack a principled framework for understanding how these thoughts are structured. In this paper, we introduce a novel approach by applying Schoenfeld's Episode Theory, a classic cognitive framework for human mathematical problem-solving, to analyze the reasoning traces of LRMs. We annotated thousands of sentences and paragraphs from model-generated solutions to math problems using seven cognitive labels (e.g., Plan, Implement, Verify). The result is the first publicly available benchmark for the fine-grained analysis of machine reasoning, including a large annotated corpus and detailed annotation guidebooks. Our preliminary analysis reveals distinct patterns in LRM reasoning, such as the transition dynamics between cognitive states. This framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems.</p> - https://arxiv.org/abs/2509.14662 - Thu, 18 Sep 2025 06:42:41 +0000 + Instruction-Following Evaluation in Function Calling for Large Language Models + https://arxiv.org/abs/2509.18420 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18420.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikolai Skripko</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Function calling is a core capability of large language models, essential for AI agents. Existing benchmarks such as the Berkeley Function Calling Leaderboard (BFCL), tau^2-Bench (arXiv:2506.07982), and ACEBench (arXiv:2501.12851) evaluate argument correctness but do not test adherence to format instructions embedded in parameter descriptions, such as enclosing values in double quotes or using ISO date formats. We introduce IFEval-FC, a benchmark inspired by IFEval (arXiv:2311.07911) that assesses precise instruction following in function calling. IFEval-FC encodes verifiable formats directly within JSON schema descriptions, for example specifying that a value must not contain punctuation. It includes 750 test cases, each consisting of a function with an embedded format for one of its input parameters and a corresponding user query. Evaluation is fully algorithmic, ensuring objectivity, reproducibility, and scalability. Our results show that even state-of-the-art proprietary models, including GPT-5 and Claude 4.1 Opus, frequently fail to follow basic formatting rules, highlighting a practical limitation for real-world agent systems. The complete codebase and data are publicly available at https://github.com/Skripkon/IFEval-FC.</p> + https://arxiv.org/abs/2509.18420 + Mon, 22 Sep 2025 21:04:39 +0000 - Evaluating Large Language Models for Detecting Antisemitism - https://arxiv.org/abs/2509.18293 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18293.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jay Patel, Hrudayangam Mehta, Jeremy Blackburn</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Detecting hateful content is a challenging and important problem. Automated tools, like machine-learning models, can help, but they require continuous training to adapt to the ever-changing landscape of social media. In this work, we evaluate eight open-source LLMs' capability to detect antisemitic content, specifically leveraging in-context definition as a policy guideline. We explore various prompting techniques and design a new CoT-like prompt, Guided-CoT. Guided-CoT handles the in-context policy well, increasing performance across all evaluated models, regardless of decoding configuration, model sizes, or reasoning capability. Notably, Llama 3.1 70B outperforms fine-tuned GPT-3.5. Additionally, we examine LLM errors and introduce metrics to quantify semantic divergence in model-generated rationales, revealing notable differences and paradoxical behaviors among LLMs. Our experiments highlight the differences observed across LLMs' utility, explainability, and reliability.</p> - https://arxiv.org/abs/2509.18293 - Mon, 22 Sep 2025 18:23:21 +0000 + TUN3D: Towards Real-World Scene Understanding from Unposed Images + https://arxiv.org/abs/2509.21388 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21388.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anton Konushin, Nikita Drozdov, Bulat Gabdullin, Alexey Zakharov, Anna Vorontsova, Danila Rukhovich, Maksim Kolodiazhnyi</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Layout estimation and 3D object detection are two fundamental tasks in indoor scene understanding. When combined, they enable the creation of a compact yet semantically rich spatial representation of a scene. Existing approaches typically rely on point cloud input, which poses a major limitation since most consumer cameras lack depth sensors and visual-only data remains far more common. We address this issue with TUN3D, the first method that tackles joint layout estimation and 3D object detection in real scans, given multi-view images as input, and does not require ground-truth camera poses or depth supervision. Our approach builds on a lightweight sparse-convolutional backbone and employs two dedicated heads: one for 3D object detection and one for layout estimation, leveraging a novel and effective parametric wall representation. Extensive experiments show that TUN3D achieves state-of-the-art performance across three challenging scene understanding benchmarks: (i) using ground-truth point clouds, (ii) using posed images, and (iii) using unposed images. While performing on par with specialized 3D object detection methods, TUN3D significantly advances layout estimation, setting a new benchmark in holistic indoor scene understanding. Code is available at https://github.com/col14m/tun3d .</p> + https://arxiv.org/abs/2509.21388 + Tue, 23 Sep 2025 20:24:07 +0000 - Blueprints of Trust: AI System Cards for End to End Transparency and Governance - https://arxiv.org/abs/2509.20394 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20394.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huzaifa Sidhpurwala, Emily Fox, Garth Mollett, Florencio Cano Gabarda, Roman Zhukov</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This paper introduces the Hazard-Aware System Card (HASC), a novel framework designed to enhance transparency and accountability in the development and deployment of AI systems. The HASC builds upon existing model card and system card concepts by integrating a comprehensive, dynamic record of an AI system's security and safety posture. The framework proposes a standardized system of identifiers, including a novel AI Safety Hazard (ASH) ID, to complement existing security identifiers like CVEs, allowing for clear and consistent communication of fixed flaws. By providing a single, accessible source of truth, the HASC empowers developers and stakeholders to make more informed decisions about AI system safety throughout its lifecycle. Ultimately, we also compare our proposed AI system cards with the ISO/IEC 42001:2023 standard and discuss how they can be used to complement each other, providing greater transparency and accountability for AI systems.</p> - https://arxiv.org/abs/2509.20394 - Tue, 23 Sep 2025 05:58:32 +0000 + CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition + https://arxiv.org/abs/2509.19768 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sina J. Semnani, Han Zhang, Xinyan He, Merve Tekgürler, Monica S. Lam</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Accurate text recognition for historical documents can greatly advance the study and preservation of cultural heritage. Existing vision-language models (VLMs), however, are designed for modern, standardized texts and are not equipped to read the diverse languages and scripts, irregular layouts, and frequent degradation found in historical materials. This paper presents CHURRO, a 3B-parameter open-weight VLM specialized for historical text recognition. The model is trained on CHURRO-DS, the largest historical text recognition dataset to date. CHURRO-DS unifies 155 historical corpora comprising 99,491 pages, spanning 22 centuries of textual heritage across 46 language clusters, including historical variants and dead languages. We evaluate several open-weight and closed VLMs and optical character recognition (OCR) systems on CHURRO-DS and find that CHURRO outperforms all other VLMs. On the CHURRO-DS test set, CHURRO achieves 82.3% (printed) and 70.1% (handwritten) normalized Levenshtein similarity, surpassing the second-best model, Gemini 2.5 Pro, by 1.4% and 6.5%, respectively, while being 15.5 times more cost-effective. By releasing the model and dataset, we aim to enable community-driven research to improve the readability of historical texts and accelerate scholarship.</p> + https://arxiv.org/abs/2509.19768 + Wed, 24 Sep 2025 05:38:45 +0000 - CompLLM: Compression for Long Context Q&A - https://arxiv.org/abs/2509.19228 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19228.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriele Berton, Jayakrishnan Unnikrishnan, Son Tran, Mubarak Shah</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent representations, have shown promise, their real-world adoption is limited. Existing techniques typically compress the context as a single unit, which leads to quadratic compression complexity and an inability to reuse computations across queries with overlapping contexts. In this work, we introduce CompLLM, a soft compression technique designed for practical deployment. Instead of processing the context holistically, CompLLM divides it into segments and compresses each one independently. This simple design choice yields three critical properties: efficiency, as the compression step scales linearly with the context length; scalability, enabling models trained on short sequences (e.g., 1k tokens) to generalize to contexts of 100k tokens; and reusability, allowing compressed segments to be cached and reused across different queries. Our experiments show that with a 2x compression rate, at high context lengths CompLLM speeds up Time To First Token (TTFT) by up to 4x and reduces the KV cache size by 50%. Furthermore, CompLLM achieves performance comparable to that obtained with the uncompressed context, and even surpasses it on very long sequences, demonstrating its effectiveness and practical utility.</p> - https://arxiv.org/abs/2509.19228 - Tue, 23 Sep 2025 16:49:43 +0000 + PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning + https://arxiv.org/abs/2509.19894 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19894.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xueliang Zhao, Wei Wu, Jian Guan, Zhuocheng Gong, Lingpeng Kong</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Large language models (LLMs) are evolving from conversational systems into strong reasoners for tasks such as Olympiad mathematics and competitive programming. While scaling parameters and test-time computation has driven progress, a key bottleneck is the lack of high-quality training problems: human-curated datasets are costly and limited, while existing synthetic corpora are often too easy or narrow. PromptCoT 1.0 showed that injecting rationales into prompt synthesis increases problem difficulty. Building on this, we present PromptCoT 2.0, a scalable framework that replaces hand-crafted heuristics with an expectation-maximization (EM) loop, where rationales are iteratively refined to guide prompt construction. This produces problems that are both harder and more diverse than prior corpora. The synthetic prompts support two post-training regimes: (1) Self-Play, where strong models improve autonomously via verifiable feedback without stronger teachers; and (2) Supervised Fine-Tuning (SFT), where weaker models learn from teacher-distilled traces. Extensive experiments demonstrate the effectiveness of this approach. In self-play, applying PromptCoT 2.0 to Qwen3-30B-A3B-Thinking-2507 sets new state-of-the-art results at the 30B scale, with +4.4, +4.8, and +5.3 on AIME 24/25 and HMMT 25, +6.1 and +5.0 on LiveCodeBench v5/v6, and +35 Elo on Codeforces. In SFT, training Qwen2.5-7B-Instruct solely on synthetic prompts boosts accuracy to 73.1 (AIME 24), 65.6 (AIME 25), and 53.4 (LiveCodeBench v5), surpassing models trained on human or hybrid data. Analyses further confirm that PromptCoT 2.0 yields fundamentally harder and distributionally distinct problems. These results establish prompt synthesis as a new axis for scaling reasoning and position PromptCoT 2.0 as a scalable foundation for future open-source models. The implementation is available at https://github.com/inclusionAI/PromptCoT.</p> + https://arxiv.org/abs/2509.19894 + Wed, 24 Sep 2025 08:46:29 +0000 - OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps - https://arxiv.org/abs/2509.19282 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19282.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bingnan Li, Chen-Yu Wang, Haiyang Xu, Xiang Zhang, Ethan Armand, Divyansh Srivastava, Xiaojun Shan, Zeyuan Chen, Jianwen Xie, Zhuowen Tu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary challenges: (1) large overlapping regions and (2) overlapping instances with minimal semantic distinction. Through both qualitative examples and quantitative analysis, we demonstrate how these factors degrade generation quality. To systematically assess this issue, we introduce OverLayScore, a novel metric that quantifies the complexity of overlapping bounding boxes. Our analysis reveals that existing benchmarks are biased toward simpler cases with low OverLayScore values, limiting their effectiveness in evaluating model performance under more challenging conditions. To bridge this gap, we present OverLayBench, a new benchmark featuring high-quality annotations and a balanced distribution across different levels of OverLayScore. As an initial step toward improving performance on complex overlaps, we also propose CreatiLayout-AM, a model fine-tuned on a curated amodal mask dataset. Together, our contributions lay the groundwork for more robust layout-to-image generation under realistic and challenging scenarios. Project link: https://mlpc-ucsd.github.io/OverLayBench.</p> - https://arxiv.org/abs/2509.19282 - Tue, 23 Sep 2025 17:50:00 +0000 + Real-Time Object Detection Meets DINOv3 + https://arxiv.org/abs/2509.20787 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20787.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shihua Huang, Yongjie Hou, Longfei Liu, Xuanlong Yu, Xi Shen</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Benefiting from the simplicity and effectiveness of Dense O2O and MAL, DEIM has become the mainstream training framework for real-time DETRs, significantly outperforming the YOLO series. In this work, we extend it with DINOv3 features, resulting in DEIMv2. DEIMv2 spans eight model sizes from X to Atto, covering GPU, edge, and mobile deployment. For the X, L, M, and S variants, we adopt DINOv3-pretrained or distilled backbones and introduce a Spatial Tuning Adapter (STA), which efficiently converts DINOv3's single-scale output into multi-scale features and complements strong semantics with fine-grained details to enhance detection. For ultra-lightweight models (Nano, Pico, Femto, and Atto), we employ HGNetv2 with depth and width pruning to meet strict resource budgets. Together with a simplified decoder and an upgraded Dense O2O, this unified design enables DEIMv2 to achieve a superior performance-cost trade-off across diverse scenarios, establishing new state-of-the-art results. Notably, our largest model, DEIMv2-X, achieves 57.8 AP with only 50.3 million parameters, surpassing prior X-scale models that require over 60 million parameters for just 56.5 AP. On the compact side, DEIMv2-S is the first sub-10 million model (9.71 million) to exceed the 50 AP milestone on COCO, reaching 50.9 AP. Even the ultra-lightweight DEIMv2-Pico, with just 1.5 million parameters, delivers 38.5 AP, matching YOLOv10-Nano (2.3 million) with around 50 percent fewer parameters. Our code and pre-trained models are available at https://github.com/Intellindust-AI-Lab/DEIMv2</p> + https://arxiv.org/abs/2509.20787 + Thu, 25 Sep 2025 06:14:00 +0000 - Residual Off-Policy RL for Finetuning Behavior Cloning Policies - https://arxiv.org/abs/2509.19301 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19301.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lars Ankile, Zhenyu Jiang, Rocky Duan, Guanya Shi, Pieter Abbeel, Anusha Nagabandi</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing returns from increasing offline data. In comparison, reinforcement learning (RL) trains an agent through autonomous interaction with the environment and has shown remarkable success in various domains. Still, training RL policies directly on real-world robots remains challenging due to sample inefficiency, safety concerns, and the difficulty of learning from sparse rewards for long-horizon tasks, especially for high-degree-of-freedom (DoF) systems. We present a recipe that combines the benefits of BC and RL through a residual learning framework. Our approach leverages BC policies as black-box bases and learns lightweight per-step residual corrections via sample-efficient off-policy RL. We demonstrate that our method requires only sparse binary reward signals and can effectively improve manipulation policies on high-degree-of-freedom (DoF) systems in both simulation and the real world. In particular, we demonstrate, to the best of our knowledge, the first successful real-world RL training on a humanoid robot with dexterous hands. Our results demonstrate state-of-the-art performance in various vision-based tasks, pointing towards a practical pathway for deploying RL in the real world. Project website: https://residual-offpolicy-rl.github.io</p> - https://arxiv.org/abs/2509.19301 - Tue, 23 Sep 2025 17:59:46 +0000 + Finding 3D Positions of Distant Objects from Noisy Camera Movement and Semantic Segmentation Sequences + https://arxiv.org/abs/2509.20906 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20906.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Julius Pesonen, Arno Solin, Eija Honkavaara</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> 3D object localisation based on a sequence of camera measurements is essential for safety-critical surveillance tasks, such as drone-based wildfire monitoring. Localisation of objects detected with a camera can typically be solved with dense depth estimation or 3D scene reconstruction. However, in the context of distant objects or tasks limited by the amount of available computational resources, neither solution is feasible. In this paper, we show that the task can be solved using particle filters for both single and multiple target scenarios. The method was studied using a 3D simulation and a drone-based image segmentation sequence with global navigation satellite system (GNSS)-based camera pose estimates. The results showed that a particle filter can be used to solve practical localisation tasks based on camera poses and image segments in these situations where other solutions fail. The particle filter is independent of the detection method, making it flexible for new tasks. The study also demonstrates that drone-based wildfire monitoring can be conducted using the proposed method paired with a pre-existing image segmentation model.</p> + https://arxiv.org/abs/2509.20906 + Thu, 25 Sep 2025 08:46:37 +0000 - Thinking While Listening: Simple Test Time Scaling For Audio Classification - https://arxiv.org/abs/2509.19676 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prateek Verma, Mert Pilanci</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We propose a framework that enables neural models to "think while listening" to everyday sounds, thereby enhancing audio classification performance. Motivated by recent advances in the reasoning capabilities of large language models, we address two central questions: (i) how can thinking be incorporated into existing audio classification pipelines to enable reasoning in the category space and improve performance, and (ii) can a new architecture be designed from the ground up to support both thinking and test-time scaling? We demonstrate that in both settings, our models exhibit improved classification accuracy. Leveraging test-time scaling, we observe consistent gains as the number of sampled traces increases. Furthermore, we evaluate two open-source reasoning models, GPT-OSS-20B and Qwen3-14B, showing that while such models are capable of zero-shot reasoning, a lightweight approach--retraining only the embedding matrix of a frozen, smaller model like GPT-2--can surpass the performance of billion-parameter text-based reasoning models.</p> - https://arxiv.org/abs/2509.19676 - Wed, 24 Sep 2025 01:17:24 +0000 + CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization + https://arxiv.org/abs/2509.21150 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21150.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruiyu Wang, Shizhao Sun, Weijian Ma, Jiang Bian</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Computer-Aided Design (CAD) is a foundational component of industrial prototyping, where models are defined not by raw coordinates but by construction sequences such as sketches and extrusions. This sequential structure enables both efficient prototype initialization and subsequent editing. Text-guided CAD prototyping, which unifies Text-to-CAD generation and CAD editing, has the potential to streamline the entire design pipeline. However, prior work has not explored this setting, largely because standard large language model (LLM) tokenizers decompose CAD sequences into natural-language word pieces, failing to capture primitive-level CAD semantics and hindering attention modules from modeling geometric structure. We conjecture that a multimodal tokenization strategy, aligned with CAD's primitive and structural nature, can provide more effective representations. To this end, we propose CAD-Tokenizer, a framework that represents CAD data with modality-specific tokens using a sequence-based VQ-VAE with primitive-level pooling and constrained decoding. This design produces compact, primitive-aware representations that align with CAD's structural nature. Applied to unified text-guided CAD prototyping, CAD-Tokenizer significantly improves instruction following and generation quality, achieving better quantitative and qualitative performance over both general-purpose LLMs and task-specific baselines.</p> + https://arxiv.org/abs/2509.21150 + Thu, 25 Sep 2025 13:38:36 +0000 - UserRL: Training Interactive User-Centric Agent via Reinforcement Learning - https://arxiv.org/abs/2509.19736 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19736.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu, Zhiwei Liu, Haolin Chen, Shirley Kokane, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically vary turn-level reward assignment and trajectory-level score calculation to analyze how different formulations affect learning under the GRPO algorithm. Our experiments across Qwen3 models reveal three key findings: (i) SFT cold start is critical for unlocking initial interaction ability and enabling sustained RL improvements; (ii) deliberate trajectory scoring yields more efficient and effective multi-turn interactions; and (iii) while stronger simulated users (e.g., GPT-4o) facilitates training, open-source simulators (e.g., Qwen3-32B) remain a cost-effective and transferable option. Together, these results highlight that careful design of reward shaping and user simulation choice is as crucial as model scale, and establish UserRL as a practical pathway for developing robust user-centric agentic models. All codes and data are public for future research.</p> - https://arxiv.org/abs/2509.19736 - Wed, 24 Sep 2025 03:33:20 +0000 + The role of synthetic data in Multilingual, Multi-cultural AI systems: Lessons from Indic Languages + https://arxiv.org/abs/2509.21294 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21294.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pranjal A. Chitale, Varun Gumma, Sanchit Ahuja, Prashant Kodali, Manan Uppadhyay, Deepthi Sudharsan, Sunayana Sitaram</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Developing AI systems that operate effectively across languages while remaining culturally grounded is a long-standing challenge, particularly in low-resource settings. Synthetic data provides a promising avenue, yet its effectiveness in multilingual and multicultural contexts remains underexplored. We investigate the creation and impact of synthetic, culturally contextualized datasets for Indian languages through a bottom-up generation strategy that prompts large open-source LLMs (>= 235B parameters) to ground data generation in language-specific Wikipedia content. This approach complements the dominant top-down paradigm of translating synthetic datasets from high-resource languages such as English. We introduce Updesh, a high-quality large-scale synthetic instruction-following dataset comprising 9.5M data points across 13 Indian languages, encompassing diverse reasoning and generative tasks with an emphasis on long-context, multi-turn capabilities, and alignment with Indian cultural contexts. A comprehensive evaluation incorporating both automated metrics and human annotation across 10k assessments indicates that generated data is high quality; though, human evaluation highlights areas for further improvement. Additionally, we perform downstream evaluations by fine-tuning models on our dataset and assessing the performance across 15 diverse multilingual datasets. Models trained on Updesh consistently achieve significant gains on generative tasks and remain competitive on multiple-choice style NLU tasks. Notably, relative improvements are most pronounced in low and medium-resource languages, narrowing their gap with high-resource languages. These findings provide empirical evidence that effective multilingual AI requires multi-faceted data curation and generation strategies that incorporate context-aware, culturally grounded methodologies.</p> + https://arxiv.org/abs/2509.21294 + Thu, 25 Sep 2025 15:13:00 +0000 - VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models - https://arxiv.org/abs/2509.19803 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang</p><p><b>Upvotes:</b> 111</p><p><b>Summary:</b> Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.</p> - https://arxiv.org/abs/2509.19803 - Wed, 24 Sep 2025 06:38:58 +0000 + RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards + https://arxiv.org/abs/2509.21319 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Ellie Evans, Daniel Egert, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with interpretability and reward hacking because it relies on human judgments that usually lack explicit criteria, whereas RLVR is limited in scope by its focus on correctness-based verifiers. We propose Reinforcement Learning with Binary Flexible Feedback (RLBFF), which combines the versatility of human-driven preferences with the precision of rule-based verification, enabling reward models to capture nuanced aspects of response quality beyond mere correctness. RLBFF extracts principles that can be answered in a binary fashion (e.g. accuracy of information: yes, or code readability: no) from natural language feedback. Such principles can then be used to ground Reward Model training as an entailment task (response satisfies or does not satisfy an arbitrary principle). We show that Reward Models trained in this manner can outperform Bradley-Terry models when matched for data and achieve top performance on RM-Bench (86.2%) and JudgeBench (81.4%, #1 on leaderboard as of September 24, 2025). Additionally, users can specify principles of interest at inference time to customize the focus of our reward models, in contrast to Bradley-Terry models. Finally, we present a fully open source recipe (including data) to align Qwen3-32B using RLBFF and our Reward Model, to match or exceed the performance of o3-mini and DeepSeek R1 on general alignment benchmarks of MT-Bench, WildBench, and Arena Hard v2 (at <5% of the inference cost).</p> + https://arxiv.org/abs/2509.21319 + Thu, 25 Sep 2025 16:19:06 +0000 - SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent - https://arxiv.org/abs/2509.20414 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yandan Yang, Baoxiong Jia, Shujie Zhang, Siyuan Huang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have advanced visual fidelity, they often remain constrained to fixed scene categories, lack sufficient object-level detail and physical consistency, and struggle to align with complex user instructions. In this work, we present SceneWeaver, a reflective agentic framework that unifies diverse scene synthesis paradigms through tool-based iterative refinement. At its core, SceneWeaver employs a language model-based planner to select from a suite of extensible scene generation tools, ranging from data-driven generative models to visual- and LLM-based methods, guided by self-evaluation of physical plausibility, visual realism, and semantic alignment with user input. This closed-loop reason-act-reflect design enables the agent to identify semantic inconsistencies, invoke targeted tools, and update the environment over successive iterations. Extensive experiments on both common and open-vocabulary room types demonstrate that SceneWeaver not only outperforms prior methods on physical, visual, and semantic metrics, but also generalizes effectively to complex scenes with diverse instructions, marking a step toward general-purpose 3D environment generation. Project website: https://scene-weaver.github.io/.</p> - https://arxiv.org/abs/2509.20414 - Wed, 24 Sep 2025 09:06:41 +0000 + Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training + https://arxiv.org/abs/2509.21500 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkai Zhang, Zihao Wang, Lin Gui, Swarnashree Mysore Sathyendra, Jaehwan Jeong, Victor Veitch, Wei Wang, Yunzhong He, Bing Liu, Lifeng Jin</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in reward misspecification at the high-reward tail: the inability to reliably distinguish Excellent responses from merely Great ones. This motivate us to focus on the high-reward region. However, such tail examples are scarce under the base LLM. While off-policy exemplars (e.g. from stronger models or rewrites) are easier to obtain, naively training on them yields a misspecified reward for the policy we aim to align. To address this, we study rubric-based rewards. By design, rubrics can leverage off-policy examples while remaining insensitive to their artifacts. To elicit rubrics that capture the high-reward tail, we highlight the importance of distinguishing among great and diverse responses, and introduce a workflow to implement this idea. We empirically demonstrate that rubric-based rewards substantially mitigate reward over-optimization and deliver effective LLM post-training improvements. Our code can be accessed at https://github.com/Jun-Kai-Zhang/rubrics.git .</p> + https://arxiv.org/abs/2509.21500 + Thu, 25 Sep 2025 19:57:39 +0000 - Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving - https://arxiv.org/abs/2509.20109 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20109.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengxiang Li, Yinan Zheng, Yue Wang, Huimin Wang, Hang Zhao, Jingjing Liu, Xianyuan Zhan, Kun Zhan, Xianpeng Lang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on complex rule-based post-refinement, employ reinforcement learning that remains largely limited to simulation, or utilize diffusion guidance that requires computationally expensive gradient calculations. To address these challenges, we introduce ReflectDrive, a novel learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion. We first discretize the two-dimensional driving space to construct an action codebook, enabling the use of pre-trained Diffusion Language Models for planning tasks through fine-tuning. Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient computation. Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors. Based on this, we apply local search methods to identify unsafe tokens and determine feasible solutions, which then serve as safe anchors for inpainting-based regeneration. Evaluated on the NAVSIM benchmark, ReflectDrive demonstrates significant advantages in safety-critical trajectory generation, offering a scalable and reliable solution for autonomous driving systems.</p> - https://arxiv.org/abs/2509.20109 - Wed, 24 Sep 2025 13:35:15 +0000 + X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning + https://arxiv.org/abs/2509.21559 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21559.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Prasanna Reddy Pulakurthi, Jiamian Wang, Majid Rabbani, Sohail Dianat, Raghuveer Rao, Zhiqiang Tao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Prevalent text-to-video retrieval systems mainly adopt embedding models for feature extraction and compute cosine similarities for ranking. However, this design presents two limitations. Low-quality text-video data pairs could compromise the retrieval, yet are hard to identify and examine. Cosine similarity alone provides no explanation for the ranking results, limiting the interpretability. We ask that can we interpret the ranking results, so as to assess the retrieval models and examine the text-video data? This work proposes X-CoT, an explainable retrieval framework upon LLM CoT reasoning in place of the embedding model-based similarity ranking. We first expand the existing benchmarks with additional video annotations to support semantic understanding and reduce data bias. We also devise a retrieval CoT consisting of pairwise comparison steps, yielding detailed reasoning and complete ranking. X-CoT empirically improves the retrieval performance and produces detailed rationales. It also facilitates the model behavior and data quality analysis. Code and data are available at: https://github.com/PrasannaPulakurthi/X-CoT.</p> + https://arxiv.org/abs/2509.21559 + Thu, 25 Sep 2025 20:39:45 +0000 - V-GameGym: Visual Game Generation for Code Large Language Models - https://arxiv.org/abs/2509.20136 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20136.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Zhang, Jack Yang, Renshuai Tao, Lingzheng Chai, Shawn Guo, Jiajun Wu, Xiaoming Chen, Ganqu Cui, Ning Ding, Xander Xu, Hu Wei, Bowen Zhou</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Code large language models have demonstrated remarkable capabilities in programming tasks, yet current benchmarks primarily focus on single modality rather than visual game development. Most existing code-related benchmarks evaluate syntax correctness and execution accuracy, overlooking critical game-specific metrics such as playability, visual aesthetics, and user engagement that are essential for real-world deployment. To address the gap between current LLM capabilities in algorithmic problem-solving and competitive programming versus the comprehensive requirements of practical game development, we present V-GameGym, a comprehensive benchmark comprising 2,219 high-quality samples across 100 thematic clusters derived from real-world repositories, adopting a novel clustering-based curation methodology to ensure both diversity and structural completeness. Further, we introduce a multimodal evaluation framework with an automated LLM-driven pipeline for visual code synthesis using complete UI sandbox environments. Our extensive analysis reveals that V-GameGym effectively bridges the gap between code generation accuracy and practical game development workflows, providing quantifiable quality metrics for visual programming and interactive element generation.</p> - https://arxiv.org/abs/2509.20136 - Wed, 24 Sep 2025 14:01:18 +0000 + X-Streamer: Unified Human World Modeling with Audiovisual Interaction + https://arxiv.org/abs/2509.21574 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21574.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> You Xie, Tianpei Gu, Zenan Li, Chenxu Zhang, Guoxian Song, Xiaochen Zhao, Chao Liang, Jianwen Jiang, Hongyi Xu, Linjie Luo</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce X-Streamer, an end-to-end multimodal human world modeling framework for building digital human agents capable of infinite interactions across text, speech, and video within a single unified architecture. Starting from a single portrait, X-Streamer enables real-time, open-ended video calls driven by streaming multimodal inputs. At its core is a Thinker-Actor dual-transformer architecture that unifies multimodal understanding and generation, turning a static portrait into persistent and intelligent audiovisual interactions. The Thinker module perceives and reasons over streaming user inputs, while its hidden states are translated by the Actor into synchronized multimodal streams in real time. Concretely, the Thinker leverages a pretrained large language-speech model, while the Actor employs a chunk-wise autoregressive diffusion model that cross-attends to the Thinker's hidden states to produce time-aligned multimodal responses with interleaved discrete text and audio tokens and continuous video latents. To ensure long-horizon stability, we design inter- and intra-chunk attentions with time-aligned multimodal positional embeddings for fine-grained cross-modality alignment and context retention, further reinforced by chunk-wise diffusion forcing and global identity referencing. X-Streamer runs in real time on two A100 GPUs, sustaining hours-long consistent video chat experiences from arbitrary portraits and paving the way toward unified world modeling of interactive digital humans.</p> + https://arxiv.org/abs/2509.21574 + Thu, 25 Sep 2025 20:53:27 +0000 - Thinking Augmented Pre-training - https://arxiv.org/abs/2509.20186 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Wang, Nan Yang, Shaohan Huang, Li Dong, Furu Wei</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an unprecedented rate, while the availability of high-quality data remains limited. Consequently, maximizing the utility of available data constitutes a significant research challenge. A primary impediment is that certain high-quality tokens are difficult to learn given a fixed model capacity, as the underlying rationale for a single token can be exceptionally complex and deep. To address this issue, we propose Thinking augmented Pre-Training (TPT), a universal methodology that augments text with automatically generated thinking trajectories. Such augmentation effectively increases the volume of the training data and makes high-quality tokens more learnable through step-by-step reasoning and decomposition. We apply TPT across diverse training configurations up to 100B tokens, encompassing pre-training with both constrained and abundant data, as well as mid-training from strong open-source checkpoints. Experimental results indicate that our method substantially improves the performance of LLMs across various model sizes and families. Notably, TPT enhances the data efficiency of LLM pre-training by a factor of 3. For a 3B parameter model, it improves the post-training performance by over 10% on several challenging reasoning benchmarks.</p> - https://arxiv.org/abs/2509.20186 - Wed, 24 Sep 2025 14:45:13 +0000 + ReviewScore: Misinformed Peer Review Detection with Large Language Models + https://arxiv.org/abs/2509.21679 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, Hyeongwon Jang, Changhun Kim, Haechan Kim, Jina Kim, Joowon Kim, Yoonjeon Kim, Kwanhyung Lee, Chanjae Park, Heecheol Yun, Gregor Betz, Eunho Yang</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-quality reviews, we define misinformed review points as either "weaknesses" in a review that contain incorrect premises, or "questions" in a review that can be already answered by the paper. We verify that 15.2% of weaknesses and 26.4% of questions are misinformed and introduce ReviewScore indicating if a review point is misinformed. To evaluate the factuality of each premise of weaknesses, we propose an automated engine that reconstructs every explicit and implicit premise from a weakness. We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation. Then, we measure human-model agreements on ReviewScore using eight current state-of-the-art LLMs and verify moderate agreements. We also prove that evaluating premise-level factuality shows significantly higher agreements than evaluating weakness-level factuality. A thorough disagreement analysis further supports a potential of fully automated ReviewScore evaluation.</p> + https://arxiv.org/abs/2509.21679 + Thu, 25 Sep 2025 22:55:05 +0000 - When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity - https://arxiv.org/abs/2509.20293 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20293.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Benjamin Feuer, Chiung-Yi Tseng, Astitwa Sarthak Lathe, Oussama Elachqar, John P Dickerson</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> LLM-judged benchmarks are increasingly used to evaluate complex model behaviors, yet their design introduces failure modes absent in conventional ground-truth based benchmarks. We argue that without tight objectives and verifiable constructions, benchmark rankings can produce high-confidence rankings that are in fact largely noise. We introduce two mechanisms to diagnose these issues. Schematic adherence quantifies how much of a judge's overall verdict is explained by the explicit evaluation schema, revealing unexplained variance when judges deviate from their own rubric. Psychometric validity aggregates internal consistency and discriminant validity signals to quantify irreducible uncertainty in any benchmarking run. Applying these tools to Arena-Hard Auto, we find severe schema incoherence and factor collapse across popular judges: for example, unexplained variance exceeding 90 percent for DeepSeek-R1-32B and factor correlations above 0.93 for most criteria. We also show that the ELO-style aggregation used by Arena-Hard Auto collapses and masks genuine ranking uncertainty. Our results highlight design failures that undermine validity and offer actionable principles for building better-scoped, reliability-aware LLM-judged benchmarks. We release our code at https://anonymous.4open.science/r/judgment-to-noise-947D/README.md</p> - https://arxiv.org/abs/2509.20293 - Wed, 24 Sep 2025 16:26:47 +0000 + Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval + https://arxiv.org/abs/2509.21710 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21710.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaojun Wu, Cehao Yang, Xueyuan Lin, Chengjin Xu, Xuhui Jiang, Yuanliang Sun, Hui Xiong, Jia Li, Jian Guo</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) and Graph-based RAG has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches face a fundamental trade-off. While graph-based methods are inherently dependent on high-quality graph structures, they face significant practical constraints: manually constructed knowledge graphs are prohibitively expensive to scale, while automatically extracted graphs from corpora are limited by the performance of the underlying LLM extractors, especially when using smaller, local-deployed models. This paper presents Think-on-Graph 3.0 (ToG-3), a novel framework that introduces Multi-Agent Context Evolution and Retrieval (MACER) mechanism to overcome these limitations. Our core innovation is the dynamic construction and refinement of a Chunk-Triplets-Community heterogeneous graph index, which pioneeringly incorporates a dual-evolution mechanism of Evolving Query and Evolving Sub-Graph for precise evidence retrieval. This approach addresses a critical limitation of prior Graph-based RAG methods, which typically construct a static graph index in a single pass without adapting to the actual query. A multi-agent system, comprising Constructor, Retriever, Reflector, and Responser agents, collaboratively engages in an iterative process of evidence retrieval, answer generation, sufficiency reflection, and, crucially, evolving query and subgraph. This dual-evolving multi-agent system allows ToG-3 to adaptively build a targeted graph index during reasoning, mitigating the inherent drawbacks of static, one-time graph construction and enabling deep, precise reasoning even with lightweight LLMs. Extensive experiments demonstrate that ToG-3 outperforms compared baselines on both deep and broad reasoning benchmarks, and ablation studies confirm the efficacy of the components of MACER framework.</p> + https://arxiv.org/abs/2509.21710 + Fri, 26 Sep 2025 00:13:10 +0000 - Seedream 4.0: Toward Next-generation Multimodal Image Generation - https://arxiv.org/abs/2509.20427 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Seedream, Yunpeng Chen, Yu Gao, Lixue Gong, Meng Guo, Qiushan Guo, Zhiyao Guo, Xiaoxia Hou, Weilin Huang, Yixuan Huang, Xiaowen Jian, Huafeng Kuang, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, Wei Liu, Yanzuo Lu, Zhengxiong Luo, Tongtong Ou, Guang Shi, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang, Rui Wang, Xun Wang, Ye Wang, Guofeng Wu, Jie Wu, Wenxu Wu, Yonghui Wu, Xin Xia, Xuefeng Xiao, Shuang Xu, Xin Yan, Ceyuan Yang, Jianchao Yang, Zhonghua Zhai, Chenlin Zhang, Heng Zhang, Qi Zhang, Xinyu Zhang, Yuwei Zhang, Shijia Zhao, Wenliang Zhao, Wenjia Zhu</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single framework. We develop a highly efficient diffusion transformer with a powerful VAE which also can reduce the number of image tokens considerably. This allows for efficient training of our model, and enables it to fast generate native high-resolution images (e.g., 1K-4K). Seedream 4.0 is pretrained on billions of text-image pairs spanning diverse taxonomies and knowledge-centric concepts. Comprehensive data collection across hundreds of vertical scenarios, coupled with optimized strategies, ensures stable and large-scale training, with strong generalization. By incorporating a carefully fine-tuned VLM model, we perform multi-modal post-training for training both T2I and image editing tasks jointly. For inference acceleration, we integrate adversarial distillation, distribution matching, and quantization, as well as speculative decoding. It achieves an inference time of up to 1.8 seconds for generating a 2K image (without a LLM/VLM as PE model). Comprehensive evaluations reveal that Seedream 4.0 can achieve state-of-the-art results on both T2I and multimodal image editing. In particular, it demonstrates exceptional multimodal capabilities in complex tasks, including precise image editing and in-context reasoning, and also allows for multi-image reference, and can generate multiple output images. This extends traditional T2I systems into an more interactive and multidimensional creative tool, pushing the boundary of generative AI for both creativity and professional applications. Seedream 4.0 is now accessible on https://www.volcengine.com/experience/ark?launch=seedream.</p> - https://arxiv.org/abs/2509.20427 - Wed, 24 Sep 2025 17:59:04 +0000 + UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models + https://arxiv.org/abs/2509.21760 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lan Chen, Yuchao Gu, Qi Mao</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing tasks into sequential visual sentences, where visual prompts serve as the context to guide outputs. However, such modeling requires task-specific pre-training across modalities and sources, which is costly and limits scalability to unseen tasks. Given that pre-trained video generation models inherently capture temporal sequence dependencies, we explore a more unified and scalable alternative: can a pre-trained video generation model adapt to diverse image and video tasks? To answer this, we propose UniVid, a framework that fine-tunes a video diffusion transformer to handle various vision tasks without task-specific modifications. Tasks are represented as visual sentences, where the context sequence defines both the task and the expected output modality. We evaluate the generalization of UniVid from two perspectives: (1) cross-modal inference with contexts composed of both images and videos, extending beyond LVM's uni-modal setting; (2) cross-source tasks from natural to annotated data, without multi-source pre-training. Despite being trained solely on natural video data, UniVid generalizes well in both settings. Notably, understanding and generation tasks can easily switch by simply reversing the visual sentence order in this paradigm. These findings highlight the potential of pre-trained video generation models to serve as a scalable and unified foundation for vision modeling. Our code will be released at https://github.com/CUC-MIPG/UniVid.</p> + https://arxiv.org/abs/2509.21760 + Fri, 26 Sep 2025 01:43:40 +0000 - MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model - https://arxiv.org/abs/2509.20706 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hsiao-Ying Huang, Yi-Cheng Lin, Hung-yi Lee</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large audio-language models (LALMs) show strong zero-shot ability on speech tasks, suggesting promise for speech emotion recognition (SER). However, SER in real-world deployments often fails under domain mismatch, where source data are unavailable and powerful LALMs are accessible only through an API. We ask: given only unlabeled target-domain audio and an API-only LALM, can a student model be adapted to outperform the LALM in the target domain? To this end, we propose MI-Fuse, a denoised label fusion framework that supplements the LALM with a source-domain trained SER classifier as an auxiliary teacher. The framework draws multiple stochastic predictions from both teachers, weights their mean distributions by mutual-information-based uncertainty, and stabilizes training with an exponential moving average teacher. Experiments across three public emotion datasets and six cross-domain transfers show consistent gains, with the student surpassing the LALM and outperforming the strongest baseline by 3.9%. This approach strengthens emotion-aware speech systems without sharing source data, enabling realistic adaptation.</p> - https://arxiv.org/abs/2509.20706 - Thu, 25 Sep 2025 03:16:32 +0000 + UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios + https://arxiv.org/abs/2509.21766 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haotian Luo, Huaisong Zhang, Xuelin Zhang, Haoyu Wang, Zeyu Qin, Wenjie Lu, Guozheng Ma, Haiying He, Yingsha Xie, Qiyang Zhou, Zixuan Hu, Hongze Mi, Yibo Wang, Naiqiang Tan, Hong Chen, Yi R. Fung, Chun Yuan, Li Shen</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery, unfold in long-horizon and partially observable scenarios where success hinges on sustained reasoning, planning, memory management, and tool use. Existing benchmarks rarely capture these long-horizon challenges, leaving a gap in systematic evaluation. To bridge this gap, we introduce UltraHorizon a novel benchmark that measures the foundational capabilities essential for complex real-world challenges. We use exploration as a unifying task across three distinct environments to validate these core competencies. Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules through sustained reasoning, planning, memory and tools management, and interaction with environments. Under the heaviest scale setting, trajectories average 200k+ tokens and 400+ tool calls, whereas in standard configurations they still exceed 35k tokens and involve more than 60 tool calls on average. Our extensive experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores, underscoring a persistent gap in agents' long-horizon abilities. We also observe that simple scaling fails in our task. To better illustrate the failure of agents, we conduct an in-depth analysis of collected trajectories. We identify eight types of errors and attribute them to two primary causes: in-context locking and functional fundamental capability gaps. https://github.com/StarDewXXX/UltraHorizon{Our code will be available here.}</p> + https://arxiv.org/abs/2509.21766 + Fri, 26 Sep 2025 02:04:00 +0000 - CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning - https://arxiv.org/abs/2509.20712 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenpeng Su, Leiyu Pan, Minxuan Lv, Yuntao Li, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between exploration and exploitation during training. Existing methods, such as proximal policy optimization (PPO) and its variants, discard valuable gradient signals from low-probability tokens due to the clipping mechanism. We systematically analyze the entropy dynamics and reveal that these clipped tokens play a critical yet overlooked role in regulating entropy evolution. We propose Controlling Entropy via Gradient-Preserving Policy Optimization (CE-GPPO), a novel algorithm that reintroduces gradients from clipped tokens in native PPO in a gentle and bounded manner. By controlling the magnitude of gradients from tokens outside the clipping interval, CE-GPPO is able to achieve an exploration-exploitation trade-off. We provide theoretical justification and empirical evidence showing that CE-GPPO effectively mitigates entropy instability. Extensive experiments on mathematical reasoning benchmarks show that CE-GPPO consistently outperforms strong baselines across different model scales.</p> - https://arxiv.org/abs/2509.20712 - Thu, 25 Sep 2025 03:22:04 +0000 + D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents + https://arxiv.org/abs/2509.21799 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21799.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hongze Mi, Yibo Feng, Wenjie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Naiqiang Tan, Gang Pan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of contradictory guidance. Inspired by the human cognitive loop of Thinking, Alignment, and Reflection, we present D-Artemis -- a novel deliberative framework in this paper. D-Artemis leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process. It also employs a proactive Pre-execution Alignment stage, where Thought-Action Consistency (TAC) Check module and Action Correction Agent (ACA) work in concert to mitigate the risk of execution failures. A post-execution Status Reflection Agent (SRA) completes the cognitive loop, enabling strategic learning from experience. Crucially, D-Artemis enhances the capabilities of general-purpose Multimodal large language models (MLLMs) for GUI tasks without the need for training on complex trajectory datasets, demonstrating strong generalization. D-Artemis establishes new state-of-the-art (SOTA) results across both major benchmarks, achieving a 75.8% success rate on AndroidWorld and 96.8% on ScreenSpot-V2. Extensive ablation studies further demonstrate the significant contribution of each component to the framework.</p> + https://arxiv.org/abs/2509.21799 + Fri, 26 Sep 2025 02:56:19 +0000 - StyleBench: Evaluating thinking styles in Large Language Models - https://arxiv.org/abs/2509.20868 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20868.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyu Guo, Shangding Gu, Ming Jin, Costas Spanos, Javad Lavaei</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The effectiveness of Large Language Models (LLMs) is heavily influenced by the reasoning strategies, or styles of thought, employed in their prompts. However, the interplay between these reasoning styles, model architecture, and task type remains poorly understood. To address this, we introduce StyleBench, a comprehensive benchmark for systematically evaluating reasoning styles across diverse tasks and models. We assess five representative reasoning styles, including Chain of Thought (CoT), Tree of Thought (ToT), Algorithm of Thought (AoT), Sketch of Thought (SoT), and Chain-of-Draft (CoD) on five reasoning tasks, using 15 open-source models from major families (LLaMA, Qwen, Mistral, Gemma, GPT-OSS, Phi, and DeepSeek) ranging from 270M to 120B parameters. Our large-scale analysis reveals that no single style is universally optimal. We demonstrate that strategy efficacy is highly contingent on both model scale and task type: search-based methods (AoT, ToT) excel in open-ended problems but require large-scale models, while concise styles (SoT, CoD) achieve radical efficiency gains on well-defined tasks. Furthermore, we identify key behavioral patterns: smaller models frequently fail to follow output instructions and default to guessing, while reasoning robustness emerges as a function of scale. Our findings offer a crucial roadmap for selecting optimal reasoning strategies based on specific constraints, we open source the benchmark in https://github.com/JamesJunyuGuo/Style_Bench.</p> - https://arxiv.org/abs/2509.20868 - Thu, 25 Sep 2025 08:00:39 +0000 + No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping + https://arxiv.org/abs/2509.21880 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such as GRPO rely only on problems where the model responses to the same input differ in correctness, while ignoring those where all responses receive the same reward - so-called zero-variance prompts. In this work, we argue that such prompts are not useless but can, in fact, provide meaningful feedback for policy optimization. To this end, we introduce RL with Zero-Variance Prompts (RL-ZVP), a novel algorithm that extract learning signals from zero-variance prompts. RL-ZVP directly rewards correctness and penalizes errors even without contrasting responses, modulating feedback with token-level characteristics to preserve informative, nuanced signals. Across six math reasoning benchmarks, RL-ZVP achieves significant improvements of up to 8.61 points in accuracy and 7.77 points in pass rate over GRPO, while consistently outperforming other baselines that filter out zero-variance prompts. These results highlight the untapped potential of learning from zero-variance prompts in RLVR.</p> + https://arxiv.org/abs/2509.21880 + Fri, 26 Sep 2025 05:03:54 +0000 - The Unanticipated Asymmetry Between Perceptual Optimization and Assessment - https://arxiv.org/abs/2509.20878 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20878.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiabei Zhang, Qi Wang, Siyu Wu, Du Chen, Tianhe Wu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Perceptual optimization is primarily driven by the fidelity objective, which enforces both semantic consistency and overall visual realism, while the adversarial objective provides complementary refinement by enhancing perceptual sharpness and fine-grained detail. Despite their central role, the correlation between their effectiveness as optimization objectives and their capability as image quality assessment (IQA) metrics remains underexplored. In this work, we conduct a systematic analysis and reveal an unanticipated asymmetry between perceptual optimization and assessment: fidelity metrics that excel in IQA are not necessarily effective for perceptual optimization, with this misalignment emerging more distinctly under adversarial training. In addition, while discriminators effectively suppress artifacts during optimization, their learned representations offer only limited benefits when reused as backbone initializations for IQA models. Beyond this asymmetry, our findings further demonstrate that discriminator design plays a decisive role in shaping optimization, with patch-level and convolutional architectures providing more faithful detail reconstruction than vanilla or Transformer-based alternatives. These insights advance the understanding of loss function design and its connection to IQA transferability, paving the way for more principled approaches to perceptual optimization.</p> - https://arxiv.org/abs/2509.20878 - Thu, 25 Sep 2025 08:08:26 +0000 + Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation + https://arxiv.org/abs/2509.21989 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21989.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem, Peter Wonka</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models, enabling visual correspondence in a manner analogous to the well-established semantic correspondence. While diffusion model backbones are known to encode semantically rich features, they must also contain visual features to support their image synthesis capabilities. However, isolating these visual features is challenging due to the absence of annotated datasets. To address this, we introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences based on existing subject-driven image generation datasets, and design a contrastive architecture to separate the two feature types. Leveraging the disentangled representations, we propose a new metric, Visual Semantic Matching (VSM), that quantifies visual inconsistencies in subject-driven image generation. Empirical results show that our approach outperforms global feature-based metrics such as CLIP, DINO, and vision--language models in quantifying visual inconsistencies while also enabling spatial localization of inconsistent regions. To our knowledge, this is the first method that supports both quantification and localization of inconsistencies in subject-driven generation, offering a valuable tool for advancing this task. Project Page:https://abdo-eldesokey.github.io/mind-the-glitch/</p> + https://arxiv.org/abs/2509.21989 + Fri, 26 Sep 2025 07:11:55 +0000 - Behind RoPE: How Does Causal Mask Encode Positional Information? - https://arxiv.org/abs/2509.21042 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21042.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junu Kim, Xiao Liu, Zhenghao Lin, Lei Ji, Yeyun Gong, Edward Choi</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While explicit positional encodings such as RoPE are a primary source of positional information in Transformer decoders, the causal mask also provides positional information. In this work, we prove that the causal mask can induce position-dependent patterns in attention scores, even without parameters or causal dependency in the input. Our theoretical analysis indicates that the induced attention pattern tends to favor nearby query-key pairs, mirroring the behavior of common positional encodings. Empirical analysis confirms that trained models exhibit the same behavior, with learned parameters further amplifying these patterns. Notably, we found that the interaction of causal mask and RoPE distorts RoPE's relative attention score patterns into non-relative ones. We consistently observed this effect in modern large language models, suggesting the importance of considering the causal mask as a source of positional information alongside explicit positional encodings.</p> - https://arxiv.org/abs/2509.21042 - Thu, 25 Sep 2025 11:48:24 +0000 + ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models + https://arxiv.org/abs/2509.21991 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21991.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jewon Lee, Wooksu Shin, Seungmin Yang, Ki-Ung Song, DongUk Lim, Jaeyeon Kim, Tae-Ho Kim, Bo-Kyeong Kim</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Efficient processing of high-resolution images is crucial for real-world vision-language applications. However, existing Large Vision-Language Models (LVLMs) incur substantial computational overhead due to the large number of vision tokens. With the advent of "thinking with images" models, reasoning now extends beyond text to the visual domain. This capability motivates our two-stage "coarse-to-fine" reasoning pipeline: first, a downsampled image is analyzed to identify task-relevant regions; then, only these regions are cropped at full resolution and processed in a subsequent reasoning stage. This approach reduces computational cost while preserving fine-grained visual details where necessary. A major challenge lies in inferring which regions are truly relevant to a given query. Recent related methods often fail in the first stage after input-image downsampling, due to perception-driven reasoning, where clear visual information is required for effective reasoning. To address this issue, we propose ERGO (Efficient Reasoning & Guided Observation) that performs reasoning-driven perception-leveraging multimodal context to determine where to focus. Our model can account for perceptual uncertainty, expanding the cropped region to cover visually ambiguous areas for answering questions. To this end, we develop simple yet effective reward components in a reinforcement learning framework for coarse-to-fine perception. Across multiple datasets, our approach delivers higher accuracy than the original model and competitive methods, with greater efficiency. For instance, ERGO surpasses Qwen2.5-VL-7B on the V* benchmark by 4.7 points while using only 23% of the vision tokens, achieving a 3x inference speedup. The code and models can be found at: https://github.com/nota-github/ERGO.</p> + https://arxiv.org/abs/2509.21991 + Fri, 26 Sep 2025 07:15:19 +0000 - ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning - https://arxiv.org/abs/2509.21070 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qizhi Pei, Zhuoshi Pan, Honglin Lin, Xin Gao, Yu Li, Zinan Tang, Conghui He, Rui Yan, Lijun Wu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Large Reasoning Models (LRMs) have shown impressive capabilities in complex problem-solving, often benefiting from training on difficult mathematical problems that stimulate intricate reasoning. Recent efforts have explored automated synthesis of mathematical problems by prompting proprietary models or large-scale open-source models from seed data or inherent mathematical concepts. However, scaling up these methods remains challenging due to their high computational/API cost, complexity of prompting, and limited difficulty level of the generated problems. To overcome these limitations, we propose ScaleDiff, a simple yet effective pipeline designed to scale the creation of difficult problems. We efficiently identify difficult problems from existing datasets with only a single forward pass using an adaptive thinking model, which can perceive problem difficulty and automatically switch between "Thinking" and "NoThinking" modes. We then train a specialized difficult problem generator (DiffGen-8B) on this filtered difficult data, which can produce new difficult problems in large scale, eliminating the need for complex, per-instance prompting and its associated high API costs. Fine-tuning Qwen2.5-Math-7B-Instruct on the ScaleDiff-Math dataset yields a substantial performance increase of 11.3% compared to the original dataset and achieves a 65.9% average accuracy on AIME'24, AIME'25, HMMT-Feb'25, BRUMO'25, and MATH500, outperforming recent strong LRMs like OpenThinker3. Notably, this performance is achieved using the cost-efficient Qwen3-8B model as a teacher, demonstrating that our pipeline can effectively transfer advanced reasoning capabilities without relying on larger, more expensive teacher models. Furthermore, we observe a clear scaling phenomenon in model performance on difficult benchmarks as the quantity of difficult problems increases. Code: https://github.com/QizhiPei/ScaleDiff.</p> - https://arxiv.org/abs/2509.21070 - Thu, 25 Sep 2025 12:22:44 +0000 + Fine-tuning Done Right in Model Editing + https://arxiv.org/abs/2509.22072 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wanli Yang, Fei Sun, Rui Tang, Hongyu Zang, Du Su, Qi Cao, Jingang Wang, Huawei Shen, Xueqi Cheng</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Fine-tuning, a foundational method for adapting large language models, has long been considered ineffective for model editing. Here, we challenge this belief, arguing that the reported failure arises not from the inherent limitation of fine-tuning itself, but from adapting it to the sequential nature of the editing task, a single-pass depth-first pipeline that optimizes each sample to convergence before moving on. While intuitive, this depth-first pipeline coupled with sample-wise updating over-optimizes each edit and induces interference across edits. Our controlled experiments reveal that simply restoring fine-tuning to the standard breadth-first (i.e., epoch-based) pipeline with mini-batch optimization substantially improves its effectiveness for model editing. Moreover, fine-tuning in editing also suffers from suboptimal tuning parameter locations inherited from prior methods. Through systematic analysis of tuning locations, we derive LocFT-BF, a simple and effective localized editing method built on the restored fine-tuning framework. Extensive experiments across diverse LLMs and datasets demonstrate that LocFT-BF outperforms state-of-the-art methods by large margins. Notably, to our knowledge, it is the first to sustain 100K edits and 72B-parameter models,10 x beyond prior practice, without sacrificing general capabilities. By clarifying a long-standing misconception and introducing a principled localized tuning strategy, we advance fine-tuning from an underestimated baseline to a leading method for model editing, establishing a solid foundation for future research.</p> + https://arxiv.org/abs/2509.22072 + Fri, 26 Sep 2025 08:53:13 +0000 - Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution - https://arxiv.org/abs/2509.21072 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiwen He, Zhiwei Wang, Chenyi Zhuang, Jinjie Gu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from disordered action sequencing and excessive trial and error during execution. This paper introduces Recon-Act, a self-evolving multi-agent framework grounded in Reconnaissance-Action behavioral paradigm. The system comprises a Reconnaissance Team and an Action Team: the former conducts comparative analysis and tool generation, while the latter handles intent decomposition, tool orchestration, and execution. By contrasting the erroneous trajectories with successful ones, the Reconnaissance Team infers remedies, and abstracts them into a unified notion of generalized tools, either expressed as hints or as rule-based codes, and register to the tool archive in real time. The Action Team reinference the process empowered with these targeting tools, thus establishing a closed-loop training pipeline of data-tools-action-feedback. Following the 6 level implementation roadmap proposed in this work, we have currently reached Level 3 (with limited human-in-the-loop intervention). Leveraging generalized tools obtained through reconnaissance, Recon-Act substantially improves adaptability to unseen websites and solvability on long-horizon tasks, and achieves state-of-the-art performance on the challenging VisualWebArena dataset.</p> - https://arxiv.org/abs/2509.21072 - Thu, 25 Sep 2025 12:23:49 +0000 + COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning + https://arxiv.org/abs/2509.22075 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dmitriy Shopkhoev, Denis Makhov, Magauiya Zhussip, Ammar Ali, Stamatios Lefkimmiatis</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Post-training compression of large language models (LLMs) largely relies on low-rank weight approximation, which represents each column of a weight matrix in a shared low-dimensional subspace. While this is a computationally efficient strategy, the imposed structural constraint is rigid and can lead to a noticeable model accuracy drop. In this work, we propose CoSpaDi (Compression via Sparse Dictionary Learning), a novel training-free compression framework that replaces low-rank decomposition with a more flexible structured sparse factorization in which each weight matrix is represented with a dense dictionary and a column-sparse coefficient matrix. This formulation enables a union-of-subspaces representation: different columns of the original weight matrix are approximated in distinct subspaces spanned by adaptively selected dictionary atoms, offering greater expressiveness than a single invariant basis. Crucially, CoSpaDi leverages a small calibration dataset to optimize the factorization such that the output activations of compressed projection layers closely match those of the original ones, thereby minimizing functional reconstruction error rather than mere weight approximation. This data-aware strategy preserves better model fidelity without any fine-tuning under reasonable compression ratios. Moreover, the resulting structured sparsity allows efficient sparse-dense matrix multiplication and is compatible with post-training quantization for further memory and latency gains. We evaluate CoSpaDi across multiple Llama and Qwen models under per-layer and per-group settings at 20-50\% compression ratios, demonstrating consistent superiority over state-of-the-art data-aware low-rank methods both in accuracy and perplexity. Our results establish structured sparse dictionary learning as a powerful alternative to conventional low-rank approaches for efficient LLM deployment.</p> + https://arxiv.org/abs/2509.22075 + Fri, 26 Sep 2025 08:55:09 +0000 - BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback - https://arxiv.org/abs/2509.21106 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunseo Kim, Sangam Lee, Kwangwook Seo, Dongha Lee</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Search-augmented large language models (LLMs) have advanced information-seeking tasks by integrating retrieval into generation, reducing users' cognitive burden compared to traditional search systems. Yet they remain insufficient for fully addressing diverse user needs, which requires recognizing how the same query can reflect different intents across users and delivering information in preferred forms. While recent systems such as ChatGPT and Gemini attempt personalization by leveraging user histories, systematic evaluation of such personalization is under-explored. To address this gap, we propose BESPOKE, the realistic benchmark for evaluating personalization in search-augmented LLMs. BESPOKE is designed to be both realistic, by collecting authentic chat and search histories directly from humans, and diagnostic, by pairing responses with fine-grained preference scores and feedback. The benchmark is constructed through long-term, deeply engaged human annotation, where human annotators contributed their own histories, authored queries with detailed information needs, and evaluated responses with scores and diagnostic feedback. Leveraging BESPOKE, we conduct systematic analyses that reveal key requirements for effective personalization in information-seeking tasks, providing a foundation for fine-grained evaluation of personalized search-augmented LLMs. Our code and data are available at https://augustinlib.github.io/BESPOKE/.</p> - https://arxiv.org/abs/2509.21106 - Thu, 25 Sep 2025 12:53:07 +0000 + MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing + https://arxiv.org/abs/2509.22186 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Jingzhou Chen, Fangdong Wang, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, Ruiliang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Keming Wang, Dechen Lin, Guanlin Shen, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Yu Qiao, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.</p> + https://arxiv.org/abs/2509.22186 + Fri, 26 Sep 2025 10:45:48 +0000 - MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning - https://arxiv.org/abs/2509.21113 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicheng Tao, Jungang Li, Yibo Yan, Junyan Zhang, Yubo Gao, Hanqian Li, ShuHang Xun, Yuxuan Fan, Hong Chen, Jianxiang He, Xuming Hu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs often exhibit process inconsistency, where intermediate reasoning drifts from video dynamics even when the final answer is correct, undermining interpretability and robustness. To address this issue, we introduce MOSS-ChatV, a reinforcement learning framework with a Dynamic Time Warping (DTW)-based process reward. This rule-based reward aligns reasoning traces with temporally grounded references, enabling efficient process supervision without auxiliary reward models. We further identify dynamic state prediction as a key measure of video reasoning and construct MOSS-Video, a benchmark with annotated reasoning traces, where the training split is used to fine-tune MOSS-ChatV and the held-out split is reserved for evaluation. MOSS-ChatV achieves 87.2\% on MOSS-Video (test) and improves performance on general video benchmarks such as MVBench and MMVU. The framework consistently yields gains across different architectures, including Qwen2.5-VL and Phi-2, confirming its broad applicability. Evaluations with GPT-4o-as-judge further show that MOSS-ChatV produces more consistent and stable reasoning traces.</p> - https://arxiv.org/abs/2509.21113 - Thu, 25 Sep 2025 12:59:13 +0000 + FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing + https://arxiv.org/abs/2509.22244 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyi Wu, Zhiteng Li, Haotong Qin, Xiaohong Liu, Linghe Kong, Yulun Zhang, Xiaokang Yang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Text-guided image editing with diffusion models has achieved remarkable quality but suffers from prohibitive latency, hindering real-world applications. We introduce FlashEdit, a novel framework designed to enable high-fidelity, real-time image editing. Its efficiency stems from three key innovations: (1) a One-Step Inversion-and-Editing (OSIE) pipeline that bypasses costly iterative processes; (2) a Background Shield (BG-Shield) technique that guarantees background preservation by selectively modifying features only within the edit region; and (3) a Sparsified Spatial Cross-Attention (SSCA) mechanism that ensures precise, localized edits by suppressing semantic leakage to the background. Extensive experiments demonstrate that FlashEdit maintains superior background consistency and structural integrity, while performing edits in under 0.2 seconds, which is an over 150times speedup compared to prior multi-step methods. Our code will be made publicly available at https://github.com/JunyiWuCode/FlashEdit.</p> + https://arxiv.org/abs/2509.22244 + Fri, 26 Sep 2025 11:59:30 +0000 - CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling - https://arxiv.org/abs/2509.21114 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21114.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuze He, Yanning Zhou, Wang Zhao, Jingwen Ye, Yushi Bai, Kaiwen Xiao, Yong-Jin Liu, Zhongqian Sun, Wei Yang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present CHARM, a novel parametric representation and generative framework for anime hairstyle modeling. While traditional hair modeling methods focus on realistic hair using strand-based or volumetric representations, anime hairstyle exhibits highly stylized, piecewise-structured geometry that challenges existing techniques. Existing works often rely on dense mesh modeling or hand-crafted spline curves, making them inefficient for editing and unsuitable for scalable learning. CHARM introduces a compact, invertible control-point-based parameterization, where a sequence of control points represents each hair card, and each point is encoded with only five geometric parameters. This efficient and accurate representation supports both artist-friendly design and learning-based generation. Built upon this representation, CHARM introduces an autoregressive generative framework that effectively generates anime hairstyles from input images or point clouds. By interpreting anime hairstyles as a sequential "hair language", our autoregressive transformer captures both local geometry and global hairstyle topology, resulting in high-fidelity anime hairstyle creation. To facilitate both training and evaluation of anime hairstyle generation, we construct AnimeHair, a large-scale dataset of 37K high-quality anime hairstyles with separated hair cards and processed mesh data. Extensive experiments demonstrate state-of-the-art performance of CHARM in both reconstruction accuracy and generation quality, offering an expressive and scalable solution for anime hairstyle modeling. Project page: https://hyzcluster.github.io/charm/</p> - https://arxiv.org/abs/2509.21114 - Thu, 25 Sep 2025 13:00:38 +0000 + MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning + https://arxiv.org/abs/2509.22281 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, Jiangmiao Pang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> The ability of robots to interpret human instructions and execute manipulation tasks necessitates the availability of task-relevant tabletop scenes for training. However, traditional methods for creating these scenes rely on time-consuming manual layout design or purely randomized layouts, which are limited in terms of plausibility or alignment with the tasks. In this paper, we formulate a novel task, namely task-oriented tabletop scene generation, which poses significant challenges due to the substantial gap between high-level task instructions and the tabletop scenes. To support research on such a challenging task, we introduce MesaTask-10K, a large-scale dataset comprising approximately 10,700 synthetic tabletop scenes with manually crafted layouts that ensure realistic layouts and intricate inter-object relations. To bridge the gap between tasks and scenes, we propose a Spatial Reasoning Chain that decomposes the generation process into object inference, spatial interrelation reasoning, and scene graph construction for the final 3D layout. We present MesaTask, an LLM-based framework that utilizes this reasoning chain and is further enhanced with DPO algorithms to generate physically plausible tabletop scenes that align well with given task descriptions. Exhaustive experiments demonstrate the superior performance of MesaTask compared to baselines in generating task-conforming tabletop scenes with realistic layouts. Project page is at https://mesatask.github.io/</p> + https://arxiv.org/abs/2509.22281 + Fri, 26 Sep 2025 12:46:00 +0000 - TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them - https://arxiv.org/abs/2509.21117 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yidong Wang, Yunze Song, Tingyuan Zhu, Xuanwang Zhang, Zhuohao Yu, Hao Chen, Chiyu Song, Qiufeng Wang, Cunxiang Wang, Zhen Wu, Xinyu Dai, Yue Zhang, Wei Ye, Shikun Zhang</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> The adoption of Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks. We identify two fundamental types of inconsistencies: (1) Score-Comparison Inconsistency, where lower-rated responses outperform higher-scored ones in pairwise comparisons, and (2) Pairwise Transitivity Inconsistency, manifested through circular preference chains (A>B>C>A) and equivalence contradictions (A=B=C\neq A). We argue that these issues come from information loss in discrete rating systems and ambiguous tie judgments during pairwise evaluation. We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations: 1) distribution-sensitive scoring that computes continuous expectations from discrete rating probabilities, preserving information entropy for more precise scoring, and 2) likelihood-aware aggregation that resolves transitivity violations using bidirectional preference probabilities or perplexity. We also formalize the theoretical limitations of current LLM-as-a-judge frameworks and demonstrate how TrustJudge's components overcome them. When evaluated with Llama-3.1-70B-Instruct as judge using our dataset, TrustJudge reduces Score-Comparison inconsistency by 8.43% (from 23.32% to 14.89%) and Pairwise Transitivity inconsistency by 10.82% (from 15.22% to 4.40%), while maintaining higher evaluation accuracy. Our work provides the first systematic analysis of evaluation framework inconsistencies in LLM-as-a-judge paradigms, offering both theoretical insights and practical solutions for reliable automated assessment. The framework demonstrates consistent improvements across various model architectures and scales, enabling more trustworthy LLM evaluation without requiring additional training or human annotations. The codes can be found at https://github.com/TrustJudge/TrustJudge.</p> - https://arxiv.org/abs/2509.21117 - Thu, 25 Sep 2025 13:04:29 +0000 + HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models + https://arxiv.org/abs/2509.22300 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22300.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While diffusion models have made remarkable progress in image generation, their outputs can still appear unrealistic and lack fine details, especially when using fewer number of neural function evaluations (NFEs) or lower guidance scales. To address this issue, we propose a novel momentum-based sampling technique, termed history-guided sampling (HiGS), which enhances quality and efficiency of diffusion sampling by integrating recent model predictions into each inference step. Specifically, HiGS leverages the difference between the current prediction and a weighted average of past predictions to steer the sampling process toward more realistic outputs with better details and structure. Our approach introduces practically no additional computation and integrates seamlessly into existing diffusion frameworks, requiring neither extra training nor fine-tuning. Extensive experiments show that HiGS consistently improves image quality across diverse models and architectures and under varying sampling budgets and guidance scales. Moreover, using a pretrained SiT model, HiGS achieves a new state-of-the-art FID of 1.61 for unguided ImageNet generation at 256times256 with only 30 sampling steps (instead of the standard 250). We thus present HiGS as a plug-and-play enhancement to standard diffusion sampling that enables faster generation with higher fidelity.</p> + https://arxiv.org/abs/2509.22300 + Fri, 26 Sep 2025 13:01:10 +0000 - AutoIntent: AutoML for Text Classification - https://arxiv.org/abs/2509.21138 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21138.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ilya Alekseev, Roman Solomatin, Darina Rustamova, Denis Kuznetsov</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> AutoIntent is an automated machine learning tool for text classification tasks. Unlike existing solutions, AutoIntent offers end-to-end automation with embedding model selection, classifier optimization, and decision threshold tuning, all within a modular, sklearn-like interface. The framework is designed to support multi-label classification and out-of-scope detection. AutoIntent demonstrates superior performance compared to existing AutoML tools on standard intent classification datasets and enables users to balance effectiveness and resource consumption.</p> - https://arxiv.org/abs/2509.21138 - Thu, 25 Sep 2025 13:27:52 +0000 + LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer + https://arxiv.org/abs/2509.22414 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22414.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Song Fei, Tian Ye, Lujia Wang, Lei Zhu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Universal image restoration (UIR) aims to recover images degraded by unknown mixtures while preserving semantics -- conditions under which discriminative restorers and UNet-based diffusion priors often oversmooth, hallucinate, or drift. We present LucidFlux, a caption-free UIR framework that adapts a large diffusion transformer (Flux.1) without image captions. LucidFlux introduces a lightweight dual-branch conditioner that injects signals from the degraded input and a lightly restored proxy to respectively anchor geometry and suppress artifacts. Then, a timestep- and layer-adaptive modulation schedule is designed to route these cues across the backbone's hierarchy, in order to yield coarse-to-fine and context-aware updates that protect the global structure while recovering texture. After that, to avoid the latency and instability of text prompts or MLLM captions, we enforce caption-free semantic alignment via SigLIP features extracted from the proxy. A scalable curation pipeline further filters large-scale data for structure-rich supervision. Across synthetic and in-the-wild benchmarks, LucidFlux consistently outperforms strong open-source and commercial baselines, and ablation studies verify the necessity of each component. LucidFlux shows that, for large DiTs, when, where, and what to condition on -- rather than adding parameters or relying on text prompts -- is the governing lever for robust and caption-free universal image restoration in the wild.</p> + https://arxiv.org/abs/2509.22414 + Fri, 26 Sep 2025 14:39:08 +0000 - Tree Search for LLM Agent Reinforcement Learning - https://arxiv.org/abs/2509.21240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.</p> - https://arxiv.org/abs/2509.21240 - Thu, 25 Sep 2025 14:37:09 +0000 + Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation + https://arxiv.org/abs/2509.22496 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22496.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoyu Chen, Xiaoqing Guo, Kangwei Liu, Siyuan Liang, Shiming Liu, Qunli Zhang, Hua Zhang, Xiaochun Cao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains poorly understood, limiting interpretability and reliability. In this work, we present EAGLE, a lightweight black-box framework for explaining autoregressive token generation in MLLMs. EAGLE attributes any selected tokens to compact perceptual regions while quantifying the relative influence of language priors and perceptual evidence. The framework introduces an objective function that unifies sufficiency (insight score) and indispensability (necessity score), optimized via greedy search over sparsified image regions for faithful and efficient attribution. Beyond spatial attribution, EAGLE performs modality-aware analysis that disentangles what tokens rely on, providing fine-grained interpretability of model decisions. Extensive experiments across open-source MLLMs show that EAGLE consistently outperforms existing methods in faithfulness, localization, and hallucination diagnosis, while requiring substantially less GPU memory. These results highlight its effectiveness and practicality for advancing the interpretability of MLLMs. The code is available at https://github.com/RuoyuChen10/EAGLE.</p> + https://arxiv.org/abs/2509.22496 + Fri, 26 Sep 2025 15:38:42 +0000 - Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets - https://arxiv.org/abs/2509.21245 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Hunyuan3D, Bowen Zhang, Chunchao Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jingwei Huang, Junlin Yu, Kunhong Li, Linus, Penghao Wang, Qingxiang Lin, Sicong Liu, Xianghui Yang, Yixuan Tang, Yunfei Zhao, Zeqiang Lai, Zhihao Liang, Zibo Zhao</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows.</p> - https://arxiv.org/abs/2509.21245 - Thu, 25 Sep 2025 14:39:17 +0000 + EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning + https://arxiv.org/abs/2509.22576 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitris</p><p><b>Upvotes:</b> 72</p><p><b>Summary:</b> Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical failure mode unique to this setting: the exploration-exploitation cascade failure. This cascade begins with early-stage policy premature convergence, where sparse feedback causes agents to commit to flawed, low-entropy strategies. Subsequently, agents enter late-stage policy collapse, where conventional entropy regularization becomes counterproductive, promoting chaotic exploration that destabilizes training. We propose Entropy-regularized Policy Optimization (EPO), a general framework that breaks this failure cycle through three synergistic mechanisms: (1) adopting entropy regularization in multi-turn settings to enhance exploration, (2) an entropy smoothing regularizer that bounds policy entropy within historical averages to prevent abrupt fluctuations, and (3) adaptive phase-based weighting that balances exploration and exploitation across training. Our analysis justifies that EPO guarantees monotonically decreasing entropy variance while maintaining convergence. EPO achieves up to 152% performance improvement on ScienceWorld and up to 19.8% on ALFWorld. Our work demonstrates that multi-turn sparse-reward settings require fundamentally different entropy control than traditional RL, with broad implications for LLM agent training.</p> + https://arxiv.org/abs/2509.22576 + Fri, 26 Sep 2025 16:51:44 +0000 - MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources - https://arxiv.org/abs/2509.21268 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21268.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicong Leng, Jing Wang, Jiaxi Li, Hao Zhang, Zhiqiang Hu, Boqiang Zhang, Yuming Jiang, Hang Zhang, Xin Li, Lidong Bing, Deli Zhao, Wei Lu, Yu Rong, Aixin Sun, Shijian Lu</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of reinforcement learning (RL) algorithms in post-training. Group Relative Policy Optimization (GRPO), the standard framework for RL fine-tuning, is prone to gradient vanishing when reward variance is low, which weakens optimization signals and impairs convergence. This work makes three contributions: (1) We propose Variance-Aware Sampling (VAS), a data selection strategy guided by Variance Promotion Score (VPS) that combines outcome variance and trajectory diversity to promote reward variance and stabilize policy optimization. (2) We release large-scale, carefully curated resources containing ~1.6M long CoT cold-start data and ~15k RL QA pairs, designed to ensure quality, difficulty, and diversity, along with a fully reproducible end-to-end training codebase. (3) We open-source a family of multimodal reasoning models in multiple scales, establishing standardized baselines for the community. Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS. Comprehensive ablation studies and analyses provide further insight into the contributions of each component. In addition, we theoretically establish that reward variance lower-bounds the expected policy gradient magnitude, with VAS serving as a practical mechanism to realize this guarantee. Our code, data, and checkpoints are available at https://github.com/LengSicong/MMR1.</p> - https://arxiv.org/abs/2509.21268 - Thu, 25 Sep 2025 14:58:29 +0000 + Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning + https://arxiv.org/abs/2509.22601 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22601.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li, Haojia Lin, Zongyi Li, Zihan Xu, Yuchen Shi, Siqi Cai, Renting Rui, Shaofei Cai, Yuzheng Cai, Xuan Zhang, Sheng Ye, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL training instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a curriculum-based self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL framework, where a replay buffer stores self-generated promising trajectories for off-policy update, by gradually steering the policy evolution within a well-balanced range of entropy across stages. Specifically, our approach incorporates a curriculum to manage the exploration process, utilizing intrinsic rewards to foster skill-level exploration and facilitating action-level exploration through SIL. At first, the auxiliary tool call reward plays a critical role in the accumulation of tool-use skills, enabling broad exposure to the unfamiliar distributions of the environment feedback with an upward entropy trend. As training progresses, self-imitation gets strengthened to exploit existing successful patterns from replayed experiences for comparative action-level exploration, accelerating solution iteration without unbounded entropy growth. To further stabilize training, we recalibrate the advantages of experiences in the replay buffer to address the potential policy drift. Reugularizations such as the clipping of tokens with high covariance between probability and advantage are introduced to the trajectory-level entropy control to curb over-confidence.</p> + https://arxiv.org/abs/2509.22601 + Fri, 26 Sep 2025 17:20:38 +0000 - Does FLUX Already Know How to Perform Physically Plausible Image Composition? - https://arxiv.org/abs/2509.21278 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang, Chen Zhao, Adams Wai-Kin Kong</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image diffusion models (e.g., SD3.5, FLUX) already encode essential physical and resolution priors, yet lack a framework to unleash them without resorting to latent inversion, which often locks object poses into contextually inappropriate orientations, or brittle attention surgery. We propose SHINE, a training-free framework for Seamless, High-fidelity Insertion with Neutralized Errors. SHINE introduces manifold-steered anchor loss, leveraging pretrained customization adapters (e.g., IP-Adapter) to guide latents for faithful subject representation while preserving background integrity. Degradation-suppression guidance and adaptive background blending are proposed to further eliminate low-quality outputs and visible seams. To address the lack of rigorous benchmarks, we introduce ComplexCompo, featuring diverse resolutions and challenging conditions such as low lighting, strong illumination, intricate shadows, and reflective surfaces. Experiments on ComplexCompo and DreamEditBench show state-of-the-art performance on standard metrics (e.g., DINOv2) and human-aligned scores (e.g., DreamSim, ImageReward, VisionReward). Code and benchmark will be publicly available upon publication.</p> - https://arxiv.org/abs/2509.21278 - Thu, 25 Sep 2025 15:01:49 +0000 + Quantile Advantage Estimation for Entropy-Safe Reasoning + https://arxiv.org/abs/2509.22611 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22611.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO and DAPO), which improperly penalizes negative-advantage samples under reward outliers. We propose {Quantile Advantage Estimation} (QAE), replacing the mean with a group-wise K-quantile baseline. QAE induces a response-level, two-regime gate: on hard queries (p <= 1 - K) it reinforces rare successes, while on easy queries (p > 1 - K) it targets remaining failures. Under first-order softmax updates, we prove {two-sided entropy safety}, giving lower and upper bounds on one-step entropy change that curb explosion and prevent collapse. Empirically, this minimal modification stabilizes entropy, sparsifies credit assignment (with tuned K, roughly 80% of responses receive zero advantage), and yields sustained pass@1 gains on Qwen3-8B/14B-Base across AIME 2024/2025 and AMC 2023. These results identify {baseline design} -- rather than token-level heuristics -- as the primary mechanism for scaling RLVR.</p> + https://arxiv.org/abs/2509.22611 + Fri, 26 Sep 2025 17:37:52 +0000 - Quantized Visual Geometry Grounded Transformer - https://arxiv.org/abs/2509.21302 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21302.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder real-world deployment. Post-Training Quantization (PTQ) has become a common practice for compressing and accelerating models. However, we empirically observe that PTQ faces unique obstacles when compressing billion-scale VGGTs: the data-independent special tokens induce heavy-tailed activation distributions, while the multi-view nature of 3D data makes calibration sample selection highly unstable. This paper proposes the first Quantization framework for VGGTs, namely QuantVGGT. This mainly relies on two technical contributions: First, we introduce Dual-Smoothed Fine-Grained Quantization, which integrates pre-global Hadamard rotation and post-local channel smoothing to mitigate heavy-tailed distributions and inter-channel variance robustly. Second, we design Noise-Filtered Diverse Sampling, which filters outliers via deep-layer statistics and constructs frame-aware diverse calibration clusters to ensure stable quantization ranges. Comprehensive experiments demonstrate that QuantVGGT achieves the state-of-the-art results across different benchmarks and bit-width, surpassing the previous state-of-the-art generic quantization method with a great margin. We highlight that our 4-bit QuantVGGT can deliver a 3.7times memory reduction and 2.5times acceleration in real-hardware inference, while maintaining reconstruction accuracy above 98\% of its full-precision counterpart. This demonstrates the vast advantages and practicality of QuantVGGT in resource-constrained scenarios. Our code is released in https://github.com/wlfeng0509/QuantVGGT.</p> - https://arxiv.org/abs/2509.21302 - Thu, 25 Sep 2025 15:17:11 +0000 + LongLive: Real-time Interactive Long Video Generation + https://arxiv.org/abs/2509.22622 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22622.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen</p><p><b>Upvotes:</b> 129</p><p><b>Summary:</b> We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.</p> + https://arxiv.org/abs/2509.22622 + Fri, 26 Sep 2025 17:48:24 +0000 - Interactive Recommendation Agent with Active User Commands - https://arxiv.org/abs/2509.21317 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiakai Tang, Yujie Luo, Xunke Xi, Fei Sun, Xueyang Feng, Sunhao Dai, Chao Yi, Dian Chen, Zhujin Gao, Yang Li, Xu Chen, Wen Chen, Jian Wu, Yuning Jiang, Bo Zheng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Traditional recommender systems rely on passive feedback mechanisms that limit users to simple choices such as like and dislike. However, these coarse-grained signals fail to capture users' nuanced behavior motivations and intentions. In turn, current systems cannot also distinguish which specific item attributes drive user satisfaction or dissatisfaction, resulting in inaccurate preference modeling. These fundamental limitations create a persistent gap between user intentions and system interpretations, ultimately undermining user satisfaction and harming system effectiveness. To address these limitations, we introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds. Unlike traditional systems that confine users to passive implicit behavioral influence, IRF empowers active explicit control over recommendation policies through real-time linguistic commands. To support this paradigm, we develop RecBot, a dual-agent architecture where a Parser Agent transforms linguistic expressions into structured preferences and a Planner Agent dynamically orchestrates adaptive tool chains for on-the-fly policy adjustment. To enable practical deployment, we employ simulation-augmented knowledge distillation to achieve efficient performance while maintaining strong reasoning capabilities. Through extensive offline and long-term online experiments, RecBot shows significant improvements in both user satisfaction and business outcomes.</p> - https://arxiv.org/abs/2509.21317 - Thu, 25 Sep 2025 15:38:27 +0000 + SPARK: Synergistic Policy And Reward Co-Evolving Framework + https://arxiv.org/abs/2509.22624 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Liu, Yuhang Zang, Shengyuan Ding, Yuhang Cao, Xiaoyi Dong, Haodong Duan, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Recent Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) increasingly use Reinforcement Learning (RL) for post-pretraining, such as RL with Verifiable Rewards (RLVR) for objective tasks and RL from Human Feedback (RLHF) for subjective tasks. However, RLHF incurs high costs and potential reward-policy mismatch due to reliance on human preferences, while RLVR still wastes supervision by discarding rollouts and correctness signals after each update. To address these challenges, we introduce the Synergistic Policy And Reward Co-Evolving Framework (SPARK), an efficient, on-policy, and stable method that builds on RLVR. Instead of discarding rollouts and correctness data, SPARK recycles this valuable information to simultaneously train the model itself as a generative reward model. This auxiliary training uses a mix of objectives, such as pointwise reward score, pairwise comparison, and evaluation conditioned on further-reflection responses, to teach the model to evaluate and improve its own responses. Our process eliminates the need for a separate reward model and costly human preference data. SPARK creates a positive co-evolving feedback loop: improved reward accuracy yields better policy gradients, which in turn produce higher-quality rollouts that further refine the reward model. Our unified framework supports test-time scaling via self-reflection without external reward models and their associated costs. We show that SPARK achieves significant performance gains on multiple LLM and LVLM models and multiple reasoning, reward models, and general benchmarks. For example, SPARK-VL-7B achieves an average 9.7% gain on 7 reasoning benchmarks, 12.1% on 2 reward benchmarks, and 1.5% on 8 general benchmarks over the baselines, demonstrating robustness and broad generalization.</p> + https://arxiv.org/abs/2509.22624 + Fri, 26 Sep 2025 17:50:12 +0000 - SD3.5-Flash: Distribution-Guided Distillation of Generative Flows - https://arxiv.org/abs/2509.21318 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21318.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hmrishav Bandyopadhyay, Rahim Entezari, Jim Scott, Reshinth Adithyan, Yi-Zhe Song, Varun Jampani</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to accessible consumer devices. Our approach distills computationally prohibitive rectified flow models through a reformulated distribution matching objective tailored specifically for few-step generation. We introduce two key innovations: "timestep sharing" to reduce gradient noise and "split-timestep fine-tuning" to improve prompt alignment. Combined with comprehensive pipeline optimizations like text encoder restructuring and specialized quantization, our system enables both rapid generation and memory-efficient deployment across different hardware configurations. This democratizes access across the full spectrum of devices, from mobile phones to desktop computers. Through extensive evaluation including large-scale user studies, we demonstrate that SD3.5-Flash consistently outperforms existing few-step methods, making advanced generative AI truly accessible for practical deployment.</p> - https://arxiv.org/abs/2509.21318 - Thu, 25 Sep 2025 16:07:38 +0000 + StateX: Enhancing RNN Recall via Post-training State Expansion + https://arxiv.org/abs/2509.22630 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyu Shen, Yingfa Chen, Zhen Leng Thai, Xu Han, Zhiyuan Liu, Maosong Sun</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While Transformer-based models have demonstrated remarkable language modeling performance, their high complexities result in high costs when processing long contexts. In contrast, recurrent neural networks (RNNs) such as linear attention and state space models have gained popularity due to their constant per-token complexities. However, these recurrent models struggle with tasks that require accurate recall of contextual information from long contexts, because all contextual information is compressed into a constant-size recurrent state. Previous works have shown that recall ability is positively correlated with the recurrent state size, yet directly training RNNs with larger recurrent states results in high training costs. In this paper, we introduce StateX, a training pipeline for efficiently expanding the states of pre-trained RNNs through post-training. For two popular classes of RNNs, linear attention and state space models, we design post-training architectural modifications to scale up the state size with no or negligible increase in model parameters. Experiments on models up to 1.3B parameters demonstrate that StateX efficiently enhances the recall and in-context learning ability of RNNs without incurring high post-training costs or compromising other capabilities.</p> + https://arxiv.org/abs/2509.22630 + Fri, 26 Sep 2025 17:55:22 +0000 - SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines - https://arxiv.org/abs/2509.21320 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yizhou Wang, Chen Tang, Han Deng, Jiabei Xiao, Jiaqi Liu, Jianyu Wu, Jun Yao, Pengze Li, Encheng Su, Lintao Wang, Guohang Zhuang, Yuchen Ren, Ben Fei, Ming Hu, Xin Chen, Dongzhan Zhou, Junjun He, Xiangyu Yue, Zhenfei Yin, Jiamin Wu, Qihao Zheng, Yuhao Zhou, Huihui Xu, Chenglong Ma, Yan Lu, Wenlong Zhang, Chunfeng Song, Philip Torr, Shixiang Tang, Xinzhu Ma, Wanli Ouyang, Lei Bai</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.</p> - https://arxiv.org/abs/2509.21320 - Thu, 25 Sep 2025 17:52:06 +0000 + Scale-Wise VAR is Secretly Discrete Diffusion + https://arxiv.org/abs/2509.22636 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Amandeep Kumar, Nithin Gopalakrishnan Nair, Vishal M. Patel</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with language and vision. Among them, next scale prediction Visual Autoregressive Generation (VAR) has recently demonstrated remarkable performance, even surpassing diffusion-based models. In this work, we revisit VAR and uncover a theoretical insight: when equipped with a Markovian attention mask, VAR is mathematically equivalent to a discrete diffusion. We term this reinterpretation as Scalable Visual Refinement with Discrete Diffusion (SRDD), establishing a principled bridge between AR transformers and diffusion models. Leveraging this new perspective, we show how one can directly import the advantages of diffusion such as iterative refinement and reduce architectural inefficiencies into VAR, yielding faster convergence, lower inference cost, and improved zero-shot reconstruction. Across multiple datasets, we show that the diffusion based perspective of VAR leads to consistent gains in efficiency and generation.</p> + https://arxiv.org/abs/2509.22636 + Fri, 26 Sep 2025 17:58:04 +0000 + + + Variational Reasoning for Language Models + https://arxiv.org/abs/2509.22637 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22637.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.</p> + https://arxiv.org/abs/2509.22637 + Fri, 26 Sep 2025 17:58:10 +0000 + + + Language Models Can Learn from Verbal Feedback Without Scalar Rewards + https://arxiv.org/abs/2509.22638 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing scale imbalance. We propose treating verbal feedback as a conditioning signal. Inspired by language priors in text-to-image generation, which enable novel outputs from unseen prompts, we introduce the feedback-conditional policy (FCP). FCP learns directly from response-feedback pairs, approximating the feedback-conditional posterior through maximum likelihood training on offline data. We further develop an online bootstrapping stage where the policy generates under positive conditions and receives fresh feedback to refine itself. This reframes feedback-driven learning as conditional generation rather than reward optimization, offering a more expressive way for LLMs to directly learn from verbal feedback. Our code is available at https://github.com/sail-sg/feedback-conditional-policy.</p> + https://arxiv.org/abs/2509.22638 + Fri, 26 Sep 2025 17:58:27 +0000 + + + WoW: Towards a World omniscient World model Through Embodied Interaction + https://arxiv.org/abs/2509.22642 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22642.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaowei Chi, Peidong Jia, Chun-Kai Fan, Xiaozhu Ju, Weishi Mi, Kevin Zhang, Zhiyuan Qin, Wanxin Tian, Kuangzhi Ge, Hao Li, Zezhong Qian, Anthony Chen, Qiang Zhou, Yueru Jia, Jiaming Liu, Yong Dai, Qingpo Wuwu, Chengyu Bai, Yu-Kai Wang, Ying Li, Lizhang Chen, Yong Bao, Zhiyuan Jiang, Jiacheng Zhu, Kai Tang, Ruichuan An, Yulin Luo, Qiuxuan Feng, Siyuan Zhou, Chi-min Chan, Chengkai Hou, Wei Xue, Sirui Han, Yike Guo, Shanghang Zhang, Jian Tang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping physical causality. This observation leads to our central hypothesis: authentic physical intuition of the world model must be grounded in extensive, causally rich interactions with the real world. To test this hypothesis, we present WoW, a 14-billion-parameter generative world model trained on 2 million robot interaction trajectories. Our findings reveal that the model's understanding of physics is a probabilistic distribution of plausible outcomes, leading to stochastic instabilities and physical hallucinations. Furthermore, we demonstrate that this emergent capability can be actively constrained toward physical realism by SOPHIA, where vision-language model agents evaluate the DiT-generated output and guide its refinement by iteratively evolving the language instructions. In addition, a co-trained Inverse Dynamics Model translates these refined plans into executable robotic actions, thus closing the imagination-to-action loop. We establish WoWBench, a new benchmark focused on physical consistency and causal reasoning in video, where WoW achieves state-of-the-art performance in both human and autonomous evaluation, demonstrating strong ability in physical causality, collision dynamics, and object permanence. Our work provides systematic evidence that large-scale, real-world interaction is a cornerstone for developing physical intuition in AI. Models, data, and benchmarks will be open-sourced.</p> + https://arxiv.org/abs/2509.22642 + Fri, 26 Sep 2025 17:59:07 +0000 + + + WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning + https://arxiv.org/abs/2509.22644 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22644.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Junting Pan, Mingjie Zhan, Hongsheng Li</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent that leverages comprehensive and multi-level visual feedback to iteratively generate and refine the website codebase. Detailed and expressive text descriptions and suggestions regarding the screenshots and GUI-agent testing of the websites are generated by a visual language model (VLM), together with scores that quantify their quality. The screenshot and GUI-agent scores are further integrated with a backtracking and select-best mechanism, enhancing the performance of the agent. Utilizing the accurate visual scores inherent in the WebGen-Agent workflow, we further introduce Step-GRPO with Screenshot and GUI-agent Feedback to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent. By using the screenshot and GUI-agent scores at each step as the reward in Step-GRPO, we provide a dense and reliable process supervision signal, which effectively improves the model's website-generation ability. On the WebGen-Bench dataset, WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system. Additionally, our Step-GRPO training approach increases the accuracy of Qwen2.5-Coder-7B-Instruct from 38.9% to 45.4% and raises the appearance score from 3.4 to 3.7.</p> + https://arxiv.org/abs/2509.22644 + Fri, 26 Sep 2025 17:59:51 +0000 + + + CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning + https://arxiv.org/abs/2509.22647 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu, Dahua Lin</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable data annotated by humans or proprietary models. This approach often leads to models that memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome the limitation of SFT, we propose applying the Reinforcement Learning with Verifiable Rewards (RLVR) paradigm to the open-ended task of image captioning. A primary challenge, however, is designing an objective reward function for the inherently subjective nature of what constitutes a "good" caption. We introduce Captioning Reinforcement Learning (CapRL), a novel training framework that redefines caption quality through its utility: a high-quality caption should enable a non-visual language model to accurately answer questions about the corresponding image. CapRL employs a decoupled two-stage pipeline where an LVLM generates a caption, and the objective reward is derived from the accuracy of a separate, vision-free LLM answering Multiple-Choice Questions based solely on that caption. As the first study to apply RLVR to the subjective image captioning task, we demonstrate that CapRL significantly enhances multiple settings. Pretraining on the CapRL-5M caption dataset annotated by CapRL-3B results in substantial gains across 12 benchmarks. Moreover, within the Prism Framework for caption quality evaluation, CapRL achieves performance comparable to Qwen2.5-VL-72B, while exceeding the baseline by an average margin of 8.4%. Code is available here: https://github.com/InternLM/CapRL.</p> + https://arxiv.org/abs/2509.22647 + Fri, 26 Sep 2025 17:59:55 +0000 + + + RefAM: Attention Magnets for Zero-Shot Referral Segmentation + https://arxiv.org/abs/2509.22650 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22650.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anna Kukleva, Enis Simsar, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional training and architectural modifications. Meanwhile, large-scale generative diffusion models encode rich semantic information, making them attractive as general-purpose feature extractors. In this work, we introduce a new method that directly exploits features, attention scores, from diffusion transformers for downstream tasks, requiring neither architectural modifications nor additional training. To systematically evaluate these features, we extend benchmarks with vision-language grounding tasks spanning both images and videos. Our key insight is that stop words act as attention magnets: they accumulate surplus attention and can be filtered to reduce noise. Moreover, we identify global attention sinks (GAS) emerging in deeper layers and show that they can be safely suppressed or redirected onto auxiliary tokens, leading to sharper and more accurate grounding maps. We further propose an attention redistribution strategy, where appended stop words partition background activations into smaller clusters, yielding sharper and more localized heatmaps. Building on these findings, we develop RefAM, a simple training-free grounding framework that combines cross-attention maps, GAS handling, and redistribution. Across zero-shot referring image and video segmentation benchmarks, our approach consistently outperforms prior methods, establishing a new state of the art without fine-tuning or additional components.</p> + https://arxiv.org/abs/2509.22650 + Fri, 26 Sep 2025 17:59:57 +0000 + + + See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation + https://arxiv.org/abs/2509.22653 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chih Yao Hu, Yang-Sen Lin, Yuna Lee, Chih-Hai Su, Jie-Ying Lee, Shr-Ruei Tsai, Chin-Yang Lin, Kuan-Wen Chen, Tsung-Wei Ke, Yu-Lun Liu</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We present See, Point, Fly (SPF), a training-free aerial vision-and-language navigation (AVLN) framework built atop vision-language models (VLMs). SPF is capable of navigating to any goal based on any type of free-form instructions in any kind of environment. In contrast to existing VLM-based approaches that treat action prediction as a text generation task, our key insight is to consider action prediction for AVLN as a 2D spatial grounding task. SPF harnesses VLMs to decompose vague language instructions into iterative annotation of 2D waypoints on the input image. Along with the predicted traveling distance, SPF transforms predicted 2D waypoints into 3D displacement vectors as action commands for UAVs. Moreover, SPF also adaptively adjusts the traveling distance to facilitate more efficient navigation. Notably, SPF performs navigation in a closed-loop control manner, enabling UAVs to follow dynamic targets in dynamic environments. SPF sets a new state of the art in DRL simulation benchmark, outperforming the previous best method by an absolute margin of 63%. In extensive real-world evaluations, SPF outperforms strong baselines by a large margin. We also conduct comprehensive ablation studies to highlight the effectiveness of our design choice. Lastly, SPF shows remarkable generalization to different VLMs. Project page: https://spf-web.pages.dev</p> + https://arxiv.org/abs/2509.22653 + Fri, 26 Sep 2025 17:59:59 +0000 + + + VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing + https://arxiv.org/abs/2509.22651 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22651.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ke Wang, Houxing Ren, Zimu Lu, Mingjie Zhan, Hongsheng Li</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> The growing capabilities of large language models and multimodal systems have spurred interest in voice-first AI assistants, yet existing benchmarks are inadequate for evaluating the full range of these systems' capabilities. We introduce VoiceAssistant-Eval, a comprehensive benchmark designed to assess AI assistants across listening, speaking, and viewing. VoiceAssistant-Eval comprises 10,497 curated examples spanning 13 task categories. These tasks include natural sounds, music, and spoken dialogue for listening; multi-turn dialogue, role-play imitation, and various scenarios for speaking; and highly heterogeneous images for viewing. To demonstrate its utility, we evaluate 21 open-source models and GPT-4o-Audio, measuring the quality of the response content and speech, as well as their consistency. The results reveal three key findings: (1) proprietary models do not universally outperform open-source models; (2) most models excel at speaking tasks but lag in audio understanding; and (3) well-designed smaller models can rival much larger ones. Notably, the mid-sized Step-Audio-2-mini (7B) achieves more than double the listening accuracy of LLaMA-Omni2-32B-Bilingual. However, challenges remain: multimodal (audio plus visual) input and role-play voice imitation tasks are difficult for current models, and significant gaps persist in robustness and safety alignment. VoiceAssistant-Eval identifies these gaps and establishes a rigorous framework for evaluating and guiding the development of next-generation AI assistants. Code and data will be released at https://mathllm.github.io/VoiceAssistantEval/ .</p> + https://arxiv.org/abs/2509.22651 + Fri, 26 Sep 2025 17:59:59 +0000