bot: update RSS feed
This commit is contained in:
github-actions[bot]
286
feed.xml
286
feed.xml
@@ -7,97 +7,251 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Fri, 26 Sep 2025 00:02:40 +0000</lastBuildDate>
|
||||
<lastBuildDate>Sat, 27 Sep 2025 00:02:40 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub</title>
|
||||
<link>https://arxiv.org/abs/2509.14745</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.14745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Miku Watanabe, Hao Li, Yutaro Kashiwa, Brittany Reid, Hajimu Iida, Ahmed E. Hassan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to become a standard practice. However, little is known about the practical usefulness of these pull requests and the extent to which their contributions are accepted in real-world projects. In this paper, we empirically study 567 GitHub pull requests (PRs) generated using Claude Code, an agentic coding tool, across 157 diverse open-source projects. Our analysis reveals that developers tend to rely on agents for tasks such as refactoring, documentation, and testing. The results indicate that 83.8% of these agent-assisted PRs are eventually accepted and merged by project maintainers, with 54.9% of the merged PRs are integrated without further modification. The remaining 45.1% require additional changes benefit from human revisions, especially for bug fixes, documentation, and adherence to project-specific standards. These findings suggest that while agent-assisted PRs are largely acceptable, they still benefit from human oversight and refinement.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.14745</guid>
|
||||
<pubDate>Thu, 18 Sep 2025 08:48:32 +0000</pubDate>
|
||||
<title>Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory</title>
|
||||
<link>https://arxiv.org/abs/2509.14662</link>
|
||||
<description><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> 7</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.14662</guid>
|
||||
<pubDate>Thu, 18 Sep 2025 06:42:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>kh2d-solver: A Python Library for Idealized Two-Dimensional Incompressible Kelvin-Helmholtz Instability</title>
|
||||
<link>https://arxiv.org/abs/2509.16080</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sandy H. S. Herho, Nurjanna J. Trilaksono, Faiz R. Fajary, Gandhi Napitupulu, Iwan P. Anwar, Faruq Khadami, Dasapta E. Irawan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We present an open-source Python library for simulating two-dimensional incompressible Kelvin-Helmholtz instabilities in stratified shear flows. The solver employs a fractional-step projection method with spectral Poisson solution via Fast Sine Transform, achieving second-order spatial accuracy. Implementation leverages NumPy, SciPy, and Numba JIT compilation for efficient computation. Four canonical test cases explore Reynolds numbers 1000--5000 and Richardson numbers 0.1--0.3: classical shear layer, double shear configuration, rotating flow, and forced turbulence. Statistical analysis using Shannon entropy and complexity indices reveals that double shear layers achieve 2.8times higher mixing rates than forced turbulence despite lower Reynolds numbers. The solver runs efficiently on standard desktop hardware, with 384times192 grid simulations completing in approximately 31 minutes. Results demonstrate that mixing efficiency depends on instability generation pathways rather than intensity measures alone, challenging Richardson number-based parameterizations and suggesting refinements for subgrid-scale representation in climate models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.16080</guid>
|
||||
<pubDate>Fri, 19 Sep 2025 15:26:37 +0000</pubDate>
|
||||
<title>Evaluating Large Language Models for Detecting Antisemitism</title>
|
||||
<link>https://arxiv.org/abs/2509.18293</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.18293</guid>
|
||||
<pubDate>Mon, 22 Sep 2025 18:23:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Advancing Speech Understanding in Speech-Aware Language Models with GRPO</title>
|
||||
<link>https://arxiv.org/abs/2509.16990</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.16990.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Avishai Elmakies, Hagai Aronowitz, Nimrod Shabtay, Eli Schwartz, Ron Hoory, Avihu Dekel</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> In this paper, we introduce a Group Relative Policy Optimization (GRPO)-based method for training Speech-Aware Large Language Models (SALLMs) on open-format speech understanding tasks, such as Spoken Question Answering and Automatic Speech Translation. SALLMs have proven highly effective for speech understanding tasks. GRPO has recently gained traction for its efficiency in training LLMs, and prior work has explored its application to SALLMs, primarily in multiple-choice tasks. Building on this, we focus on open-format tasks that better reflect the generative abilities of the models. Our approach leverages GRPO with BLEU as the reward signal to optimize SALLMs, and we demonstrate empirically that it surpasses standard SFT across several key metrics. Finally, we explore the potential of incorporating off-policy samples within GRPO for these tasks, highlighting avenues for further improvement and further research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.16990</guid>
|
||||
<pubDate>Sun, 21 Sep 2025 09:09:36 +0000</pubDate>
|
||||
<title>Blueprints of Trust: AI System Cards for End to End Transparency and Governance</title>
|
||||
<link>https://arxiv.org/abs/2509.20394</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20394</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 05:58:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ATLAS: Benchmarking and Adapting LLMs for Global Trade via Harmonized Tariff Code Classification</title>
|
||||
<link>https://arxiv.org/abs/2509.18400</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18400.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pritish Yuvraj, Siva Devarakonda</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Accurate classification of products under the Harmonized Tariff Schedule (HTS) is a critical bottleneck in global trade, yet it has received little attention from the machine learning community. Misclassification can halt shipments entirely, with major postal operators suspending deliveries to the U.S. due to incomplete customs documentation. We introduce the first benchmark for HTS code classification, derived from the U.S. Customs Rulings Online Search System (CROSS). Evaluating leading LLMs, we find that our fine-tuned Atlas model (LLaMA-3.3-70B) achieves 40 percent fully correct 10-digit classifications and 57.5 percent correct 6-digit classifications, improvements of 15 points over GPT-5-Thinking and 27.5 points over Gemini-2.5-Pro-Thinking. Beyond accuracy, Atlas is roughly five times cheaper than GPT-5-Thinking and eight times cheaper than Gemini-2.5-Pro-Thinking, and can be self-hosted to guarantee data privacy in high-stakes trade and compliance workflows. While Atlas sets a strong baseline, the benchmark remains highly challenging, with only 40 percent 10-digit accuracy. By releasing both dataset and model, we aim to position HTS classification as a new community benchmark task and invite future work in retrieval, reasoning, and alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.18400</guid>
|
||||
<pubDate>Mon, 22 Sep 2025 20:32:24 +0000</pubDate>
|
||||
<title>CompLLM: Compression for Long Context Q&A</title>
|
||||
<link>https://arxiv.org/abs/2509.19228</link>
|
||||
<description><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> 2</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19228</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 16:49:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SimpleFold: Folding Proteins is Simpler than You Think</title>
|
||||
<link>https://arxiv.org/abs/2509.18480</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.18480.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyang Wang, Jiarui Lu, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Protein folding models have achieved groundbreaking results typically via a combination of integrating domain knowledge into the architectural blocks and training pipelines. Nonetheless, given the success of generative models across different but related problems, it is natural to question whether these architectural designs are a necessary condition to build performant models. In this paper, we introduce SimpleFold, the first flow-matching based protein folding model that solely uses general purpose transformer blocks. Protein folding models typically employ computationally expensive modules involving triangular updates, explicit pair representations or multiple training objectives curated for this specific domain. Instead, SimpleFold employs standard transformer blocks with adaptive layers and is trained via a generative flow-matching objective with an additional structural term. We scale SimpleFold to 3B parameters and train it on approximately 9M distilled protein structures together with experimental PDB data. On standard folding benchmarks, SimpleFold-3B achieves competitive performance compared to state-of-the-art baselines, in addition SimpleFold demonstrates strong performance in ensemble prediction which is typically difficult for models trained via deterministic reconstruction objectives. Due to its general-purpose architecture, SimpleFold shows efficiency in deployment and inference on consumer-level hardware. SimpleFold challenges the reliance on complex domain-specific architectures designs in protein folding, opening up an alternative design space for future progress.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.18480</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 00:33:32 +0000</pubDate>
|
||||
<title>OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps</title>
|
||||
<link>https://arxiv.org/abs/2509.19282</link>
|
||||
<description><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> 0</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19282</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 17:50:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation</title>
|
||||
<link>https://arxiv.org/abs/2509.19244</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19244.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Zijun Wei, Aditya Grover, Jason Kuen</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported by token compression, universal text conditioning and stratified sampling for efficient and high-quality generation. Lavida-O further incorporates planning and iterative self-reflection in image generation and editing tasks, seamlessly boosting generation quality with its understanding capabilities. Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing, outperforming existing autoregressive models and continuous diffusion models such as Qwen2.5-VL and FluxKontext-dev, while offering considerable speedup at inference. These advances establish Lavida-O as a new paradigm for scalable multimodal reasoning and generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19244</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 17:05:46 +0000</pubDate>
|
||||
<title>Residual Off-Policy RL for Finetuning Behavior Cloning Policies</title>
|
||||
<link>https://arxiv.org/abs/2509.19301</link>
|
||||
<description><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> 12</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19301</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 17:59:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LLMs4All: A Review on Large Language Models for Research and Applications in Academic Disciplines</title>
|
||||
<link>https://arxiv.org/abs/2509.19580</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19580.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanfang, Ye, Zheyuan Zhang, Tianyi Ma, Zehong Wang, Yiyang Li, Shifu Hou, Weixiang Sun, Kaiwen Shi, Yijun Ma, Wei Song, Ahmed Abbasi, Ying Cheng, Jane Cleland-Huang, Steven Corcelli, Patricia Culligan, Robert Goulding, Ming Hu, Ting Hua, John Lalor, Fang Liu, Tengfei Luo, Ed Maginn, Nuno Moniz, Jason Rohr, Brett Savoie, Daniel Slate, Tom Stapleford, Matthew Webber, Olaf Wiest, Johnny Zhang, Nitesh Chawla</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on extensive topics. Due to the impressive performance on a variety of language-related tasks (e.g., open-domain question answering, translation, and document summarization), one can envision the far-reaching impacts that can be brought by the LLMs with broader real-world applications (e.g., customer service, education and accessibility, and scientific discovery). Inspired by their success, this paper will offer an overview of state-of-the-art LLMs and their integration into a wide range of academic disciplines, including: (1) arts, letters, and law (e.g., history, philosophy, political science, arts and architecture, law), (2) economics and business (e.g., finance, economics, accounting, marketing), and (3) science and engineering (e.g., mathematics, physics and mechanical engineering, chemistry and chemical engineering, life sciences and bioengineering, earth sciences and civil engineering, computer science and electrical engineering). Integrating humanity and technology, in this paper, we will explore how LLMs are shaping research and practice in these fields, while also discussing key limitations, open challenges, and future directions in the era of generative AI. The review of how LLMs are engaged across disciplines-along with key observations and insights-can help researchers and practitioners interested in exploiting LLMs to advance their works in diverse real-world applications.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19580</guid>
|
||||
<pubDate>Tue, 23 Sep 2025 21:09:24 +0000</pubDate>
|
||||
<title>Thinking While Listening: Simple Test Time Scaling For Audio Classification</title>
|
||||
<link>https://arxiv.org/abs/2509.19676</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19676</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 01:17:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Logics-Parsing Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2509.19760</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.19760.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyang Chen, Shuzhao Li, Xiuwen Zhu, Yongfan Chen, Fan Yang, Cheng Fang, Lin Qu, Xiaoxiao Xu, Hu Wei, Minggang Wu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advances in Large Vision-Language models (LVLM) have spurred significant progress in document parsing task. Compared to traditional pipeline-based methods, end-to-end paradigms have shown their excellence in converting PDF images into structured outputs through integrated Optical Character Recognition (OCR), table recognition, mathematical formula recognition and so on. However, the absence of explicit analytical stages for document layouts and reading orders limits the LVLM's capability in handling complex document types such as multi-column newspapers or posters. To address this limitation, we propose in this report Logics-Parsing: an end-to-end LVLM-based model augmented with reinforcement learning. Our model incorporates meticulously designed reward mechanisms to optimize complex layout analysis and reading order inference. In addition, we expand the model's versatility by incorporating diverse data types such as chemical formulas and handwritten Chinese characters into supervised fine-tuning. Finally, to enable rigorous evaluation of our approach, we introduce LogicsParsingBench, a curated set of 1,078 page-level PDF images spanning nine major categories and over twenty sub-categories, which will be released later. Comprehensive experiments conducted on LogicsParsingBench have validated the efficacy and State-of-the-art (SOTA) performance of our proposed model across diverse document analysis scenarios. Project Page: https://github.com/alibaba/Logics-Parsing</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19760</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 04:54:37 +0000</pubDate>
|
||||
<title>UserRL: Training Interactive User-Centric Agent via Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2509.19736</link>
|
||||
<description><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> 2</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19736</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 03:33:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SIM-CoT: Supervised Implicit Chain-of-Thought</title>
|
||||
<link>https://arxiv.org/abs/2509.20317</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Xipeng Qiu, Dahua Lin</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Implicit Chain-of-Thought (CoT) methods present a promising, token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited the application of implicit CoT. We identify a core latent instability issue by scaling the computational budget of implicit CoT approaches: as we increase the number of implicit reasoning tokens to enhance performance, the training process often becomes unstable and collapses. Our analysis reveals that this instability arises from the latent representations becoming homogeneous and losing their semantic diversity, a failure caused by insufficient step-level supervision in existing implicit CoT approaches. To address this issue, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. Specifically, SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring that latent states capture distinct and meaningful information. The proposed auxiliary decoder is removed during inference, preserving the computational efficiency of implicit CoT methods with no added overhead. In addition, the auxiliary decoder affords interpretability of implicit reasoning by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization of semantic roles and diagnosis. SIM-CoT significantly enhances both the in-domain accuracy and out-of-domain stability of various implicit CoT methods, boosting baselines like Coconut by +8.2% on GPT-2 and CODI by +3.0% on LLaMA-3.1 8B. Demonstrating strong scalability, SIM-CoT also surpasses the explicit CoT baseline on GPT-2 by 2.1% with 2.3\times greater token efficiency, while substantially closing the performance gap on larger models like LLaMA-3.1 8B.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20317</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:01:32 +0000</pubDate>
|
||||
<title>VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2509.19803</link>
|
||||
<description><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> 95</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.19803</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 06:38:58 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Video models are zero-shot learners and reasoners</title>
|
||||
<link>https://arxiv.org/abs/2509.20328</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20328</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:17:27 +0000</pubDate>
|
||||
<title>SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent</title>
|
||||
<link>https://arxiv.org/abs/2509.20414</link>
|
||||
<description><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> 4</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20414</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 09:06:41 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>EmbeddingGemma: Powerful and Lightweight Text Representations</title>
|
||||
<link>https://arxiv.org/abs/2509.20354</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Juyeong Ji, Renjie Wu, Jingxiao Zheng, Jyotinder Singh, Abheesht Sharma, Divya Sreepat, Aashi Jain, Adham Elarabawy, AJ Co, Andreas Doumanoglou, Babak Samari, Ben Hora, Brian Potetz, Dahun Kim, Enrique Alfonseca, Fedor Moiseev, Feng Han, Frank Palma Gomez, Gustavo Hernández Ábrego, Hesen Zhang, Hui Hui, Jay Han, Karan Gill, Ke Chen, Koert Chen, Madhuri Shanbhogue, Michael Boratko, Paul Suganthan, Sai Meher Karthik Duddu, Sandeep Mariserla, Setareh Ariafar, Shanfeng Zhang, Shijie Zhang, Simon Baumgartner, Sonam Goenka, Steve Qiu, Tanmaya Dabral, Trevor Walker, Vikram Rao, Waleed Khawaja, Wenlei Zhou, Xiaoqi Ren, Ye Xia, Yichang Chen, Yi-Ting Chen, Zhe Dong, Zhongli Ding, Francesco Visin, Gaël Liu, Jiageng Zhang, Kathleen Kenealy, Michelle Casbon, Ravin Kumar, Thomas Mesnard, Zach Gleicher, Cormac Brick, Olivier Lacombe, Adam Roberts, Yunhsuan Sung, Raphael Hoffmann, Tris Warkentin, Armand Joulin, Tom Duerig, Mojtaba Seyedhosseini</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20354</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:56:51 +0000</pubDate>
|
||||
<title>Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving</title>
|
||||
<link>https://arxiv.org/abs/2509.20109</link>
|
||||
<description><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> 2</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20109</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 13:35:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2509.20358</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20358.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou, Yuan Liu, Jiatao Gu, Lingjie Liu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Project Page: https://cwchenwang.github.io/physctrl</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20358</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:58:04 +0000</pubDate>
|
||||
<title>V-GameGym: Visual Game Generation for Code Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2509.20136</link>
|
||||
<description><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> 8</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20136</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 14:01:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning</title>
|
||||
<link>https://arxiv.org/abs/2509.20360</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.20360.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuan Ju, Tianyu Wang, Yuqian Zhou, He Zhang, Qing Liu, Nanxuan Zhao, Zhifei Zhang, Yijun Li, Yuanhao Cai, Shaoteng Liu, Daniil Pakhomov, Zhe Lin, Soo Ye Kim, Qiang Xu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified frameworks, video generation and editing remain fragmented due to architectural limitations and data scarcity. In this work, we introduce EditVerse, a unified framework for image and video generation and editing within a single model. By representing all modalities, i.e., text, image, and video, as a unified token sequence, EditVerse leverages self-attention to achieve robust in-context learning, natural cross-modal knowledge transfer, and flexible handling of inputs and outputs with arbitrary resolutions and durations. To address the lack of video editing training data, we design a scalable data pipeline that curates 232K video editing samples and combines them with large-scale image and video datasets for joint training. Furthermore, we present EditVerseBench, the first benchmark for instruction-based video editing covering diverse tasks and resolutions. Extensive experiments and user studies demonstrate that EditVerse achieves state-of-the-art performance, surpassing existing open-source and commercial models, while exhibiting emergent editing and generation abilities across modalities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20360</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:59:30 +0000</pubDate>
|
||||
<title>Thinking Augmented Pre-training</title>
|
||||
<link>https://arxiv.org/abs/2509.20186</link>
|
||||
<description><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> 10</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20186</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 14:45:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity</title>
|
||||
<link>https://arxiv.org/abs/2509.20293</link>
|
||||
<description><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> 4</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20293</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 16:26:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Seedream 4.0: Toward Next-generation Multimodal Image Generation</title>
|
||||
<link>https://arxiv.org/abs/2509.20427</link>
|
||||
<description><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> 45</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20427</guid>
|
||||
<pubDate>Wed, 24 Sep 2025 17:59:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model</title>
|
||||
<link>https://arxiv.org/abs/2509.20706</link>
|
||||
<description><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> 1</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20706</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 03:16:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2509.20712</link>
|
||||
<description><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> 14</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20712</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 03:22:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>StyleBench: Evaluating thinking styles in Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2509.20868</link>
|
||||
<description><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> 1</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20868</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 08:00:39 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>The Unanticipated Asymmetry Between Perceptual Optimization and Assessment</title>
|
||||
<link>https://arxiv.org/abs/2509.20878</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.20878</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 08:08:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Behind RoPE: How Does Causal Mask Encode Positional Information?</title>
|
||||
<link>https://arxiv.org/abs/2509.21042</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21042</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 11:48:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2509.21070</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21070</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 12:22:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution</title>
|
||||
<link>https://arxiv.org/abs/2509.21072</link>
|
||||
<description><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> 10</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21072</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 12:23:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback</title>
|
||||
<link>https://arxiv.org/abs/2509.21106</link>
|
||||
<description><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> 5</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21106</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 12:53:07 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2509.21113</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21113</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 12:59:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling</title>
|
||||
<link>https://arxiv.org/abs/2509.21114</link>
|
||||
<description><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> 11</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21114</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 13:00:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them</title>
|
||||
<link>https://arxiv.org/abs/2509.21117</link>
|
||||
<description><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> 17</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21117</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 13:04:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AutoIntent: AutoML for Text Classification</title>
|
||||
<link>https://arxiv.org/abs/2509.21138</link>
|
||||
<description><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> 21</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21138</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 13:27:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Tree Search for LLM Agent Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2509.21240</link>
|
||||
<description><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> 58</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21240</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 14:37:09 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets</title>
|
||||
<link>https://arxiv.org/abs/2509.21245</link>
|
||||
<description><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> 26</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21245</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 14:39:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources</title>
|
||||
<link>https://arxiv.org/abs/2509.21268</link>
|
||||
<description><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> 65</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21268</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 14:58:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Does FLUX Already Know How to Perform Physically Plausible Image Composition?</title>
|
||||
<link>https://arxiv.org/abs/2509.21278</link>
|
||||
<description><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> 10</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21278</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 15:01:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Quantized Visual Geometry Grounded Transformer</title>
|
||||
<link>https://arxiv.org/abs/2509.21302</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21302</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 15:17:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Interactive Recommendation Agent with Active User Commands</title>
|
||||
<link>https://arxiv.org/abs/2509.21317</link>
|
||||
<description><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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21317</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 15:38:27 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SD3.5-Flash: Distribution-Guided Distillation of Generative Flows</title>
|
||||
<link>https://arxiv.org/abs/2509.21318</link>
|
||||
<description><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> 6</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21318</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 16:07:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines</title>
|
||||
<link>https://arxiv.org/abs/2509.21320</link>
|
||||
<description><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> 76</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.21320</guid>
|
||||
<pubDate>Thu, 25 Sep 2025 17:52:06 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user