diff --git a/feed.xml b/feed.xml index e31f36f..fcd6fb1 100644 --- a/feed.xml +++ b/feed.xml @@ -7,370 +7,251 @@ http://www.rssboard.org/rss-specification python-feedgen en - Mon, 06 Oct 2025 00:02:34 +0000 + Tue, 07 Oct 2025 00:02:39 +0000 - SKYLENAGE Technical Report: Mathematical Reasoning and Contest-Innovation Benchmarks for Multi-Level Math Evaluation - https://arxiv.org/abs/2510.01241 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01241.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hu Wei, Ze Xu, Boyu Yang, Linlin Miao, Weiqi Zhai, Yihan Li, Zixuan Li, Zhijun Wang, Boya Wang, Jianwei Yu, Jialing Yuan, Xiaoyue Zhang, Cheng He, Minglei Chen, Zifan Zhang, Qianhui Li, Wei Wang, Xiang Xu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large language models (LLMs) now perform strongly on many public math suites, yet frontier separation within mathematics increasingly suffers from ceiling effects. We present two complementary benchmarks: SKYLENAGE-ReasoningMATH, a 100-item, structure-aware diagnostic set with per-item metadata on length, numeric density, and symbolic complexity; and SKYLENAGE-MATH, a 150-item contest-style suite spanning four stages from high school to doctoral under a seven-subject taxonomy. We evaluate fifteen contemporary LLM variants under a single setup and analyze subject x model and grade x model performance. On the contest suite, the strongest model reaches 44% while the runner-up reaches 37%; accuracy declines from high school to doctoral, and top systems exhibit a doctoral-to-high-school retention near 79%. On the reasoning set, the best model attains 81% overall, and hardest-slice results reveal clear robustness gaps between leaders and the mid-tier. In summary, we release SKYLENAGE-ReasoningMATH and report aggregate results for SKYLENAGE-MATH; together, SKYLENAGE provides a hard, reasoning-centered and broadly covering math benchmark with calibrated difficulty and rich metadata, serving as a reference benchmark for future evaluations of mathematical reasoning.</p> - https://arxiv.org/abs/2510.01241 - Wed, 24 Sep 2025 02:09:32 +0000 + OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features + https://arxiv.org/abs/2509.22033 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22033.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anton Korznikov, Andrey Galichin, Alexey Dontsov, Oleg Rogov, Elena Tutubalina, Ivan Oseledets</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of general features creating representation holes, and feature composition, where independent features merge into composite representations. In this work, we introduce Orthogonal SAE (OrtSAE), a novel approach aimed to mitigate these issues by enforcing orthogonality between the learned features. By implementing a new training procedure that penalizes high pairwise cosine similarity between SAE features, OrtSAE promotes the development of disentangled features while scaling linearly with the SAE size, avoiding significant computational overhead. We train OrtSAE across different models and layers and compare it with other methods. We find that OrtSAE discovers 9% more distinct features, reduces feature absorption (by 65%) and composition (by 15%), improves performance on spurious correlation removal (+6%), and achieves on-par performance for other downstream tasks compared to traditional SAEs.</p> + https://arxiv.org/abs/2509.22033 + Fri, 26 Sep 2025 08:10:52 +0000 - IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol - https://arxiv.org/abs/2510.01260 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01260.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ningyuan Yang, Guanliang Lyu, Mingchen Ma, Yiyi Lu, Yiming Li, Zhihui Gao, Hancheng Ye, Jianyi Zhang, Tingjun Chen, Yiran Chen</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing standardized communication between LLMs and physical devices. We propose IoT-MCP, a novel framework that implements MCP through edge-deployed servers to bridge LLMs and IoT ecosystems. To support rigorous evaluation, we introduce IoT-MCP Bench, the first benchmark containing 114 Basic Tasks (e.g., ``What is the current temperature?'') and 1,140 Complex Tasks (e.g., ``I feel so hot, do you have any ideas?'') for IoT-enabled LLMs. Experimental validation across 22 sensor types and 6 microcontroller units demonstrates IoT-MCP's 100% task success rate to generate tool calls that fully meet expectations and obtain completely accurate results, 205ms average response time, and 74KB peak memory footprint. This work delivers both an open-source integration framework (https://github.com/Duke-CEI-Center/IoT-MCP-Servers) and a standardized evaluation methodology for LLM-IoT systems.</p> - https://arxiv.org/abs/2510.01260 - Thu, 25 Sep 2025 08:35:47 +0000 + Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization + https://arxiv.org/abs/2509.23202 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23202.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Vage Egiazarian, Roberto L. Castro, Denis Kuznedelev, Andrei Panferov, Eldar Kurtic, Shubhra Pandit, Alexandre Marques, Mark Kurtz, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> The recent hardware-accelerated microscaling 4-bit floating-point formats such as MXFP4 and NVFP4, supported on NVIDIA and AMD GPUs, promise to revolutionize large language model (LLM) inference. Yet, their practical benefits remain unproven. We present the first comprehensive study of MXFP4 and NVFP4 for post-training quantization, revealing gaps between their promise and real-world performance. Our analysis shows that state-of-the-art methods struggle with FP4, due to two key issues: (1) NVFP4's small group size provably neutralizes traditional outlier mitigation techniques; (2) MXFP4's power-of-two scale quantization severely degrades accuracy due to high induced error. To bridge this gap, we introduce Micro-Rotated-GPTQ (MR-GPTQ), a variant of the classic GPTQ quantization algorithm that tailors the quantization process to FP4's unique properties, by using block-wise Hadamard transforms and format-specific optimizations. We support our proposal with a set of high-performance GPU kernels that enable the MR-GPTQ format with negligible overhead, by rotation fusion into the weights, and fast online computation of the activations. This leads to speedups vs. FP16 of up to 3.6x layer-wise, and 2.2x end-to-end on NVIDIA B200, and of 6x layer-wise and 4x end-to-end on RTX5090. Our extensive empirical evaluation demonstrates that MR-GPTQ matches or outperforms state-of-the-art accuracy, significantly boosting MXFP4, to the point where it nears that of NVFP4. We conclude that, while FP4 is not an automatic upgrade over INT4, format-specialized methods like MR-GPTQ can unlock a new frontier of accuracy-performance trade-offs.</p> + https://arxiv.org/abs/2509.23202 + Sat, 27 Sep 2025 09:22:21 +0000 - Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow - https://arxiv.org/abs/2509.21789 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.21789.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinlei Yu, Chengming Xu, Guibin Zhang, Yongbo He, Zhangquan Chen, Zhucun Xue, Jiangning Zhang, Yue Liao, Xiaobin Hu, Yu-Gang Jiang, Shuicheng Yan</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Multi-Agent System (MAS) powered by Visual Language Models (VLMs) enables challenging tasks but suffers from a novel failure term, multi-agent visual hallucination snowballing, where hallucinations are seeded in a single agent and amplified by following ones due to the over-reliance on textual flow to relay visual information. Through turn-, layer-, and token-wise attention analyses, we provide detailed insights into the essence of hallucination snowballing regarding the reduction of visual attention allocation. It leads us to identify a subset of vision tokens with a unimodal attention peak in middle layers that best preserve visual evidence but gradually diminish in deeper agent turns, resulting in the visual hallucination snowballing in MAS. Thus, we propose ViF, a lightweight, plug-and-play mitigation paradigm that relays inter-agent messages with Visual Flow powered by the selected visual relay tokens and applies attention reallocation to amplify this pattern. The experiment results demonstrate that our method markedly reduces hallucination snowballing, consistently improving the performance across eight benchmarks based on four common MAS structures and ten base models. The source code will be available at: https://github.com/YU-deep/ViF.git.</p> - https://arxiv.org/abs/2509.21789 - Fri, 26 Sep 2025 02:43:24 +0000 + Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces + https://arxiv.org/abs/2509.23291 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23291.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joseph Marvin Imperial, Harish Tayyar Madabushi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Policy compliance assessment is a fundamental task of evaluating whether an input case strictly complies with a set of human-defined rules, more generally known as policies. In practice, human experts follow a systematic, step-by-step process to identify violations with respect to specific stipulations outlined in the policy. However, such documentation of gold-standard, expert-level reasoning processes is costly to acquire. In this paper, we introduce Policy Reasoning Traces (PRT), a form of specialized generated reasoning chains that serve as a reasoning bridge to improve an LLM's policy compliance assessment capabilities. Our empirical evaluations demonstrate that the use of PRTs for both inference-time and training-time scenarios significantly enhances the performance of open-weight and commercial models, setting a new state-of-the-art for HIPAA and GDPR policies. Beyond accuracy gains, we also highlight how PRTs can improve an LLM's ability to accurately cite policy clauses, as well as influence compliance decisions through their high utilization from the raw chains of thought.</p> + https://arxiv.org/abs/2509.23291 + Sat, 27 Sep 2025 13:10:21 +0000 - The Rogue Scalpel: Activation Steering Compromises LLM Safety - https://arxiv.org/abs/2509.22067 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22067.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anton Korznikov, Andrey Galichin, Alexey Dontsov, Oleg Y. Rogov, Ivan Oseledets, Elena Tutubalina</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially safer alternative to fine-tuning. We demonstrate the opposite: steering systematically breaks model alignment safeguards, making it comply with harmful requests. Through extensive experiments on different model families, we show that even steering in a random direction can increase the probability of harmful compliance from 0% to 2-27%. Alarmingly, steering benign features from a sparse autoencoder (SAE), a common source of interpretable directions, increases these rates by a further 2-4%. Finally, we show that combining 20 randomly sampled vectors that jailbreak a single prompt creates a universal attack, significantly increasing harmful compliance on unseen requests. These results challenge the paradigm of safety through interpretability, showing that precise control over model internals does not guarantee precise control over model behavior.</p> - https://arxiv.org/abs/2509.22067 - Fri, 26 Sep 2025 08:49:47 +0000 + DiffTester: Accelerating Unit Test Generation for Diffusion LLMs via Repetitive Pattern + https://arxiv.org/abs/2509.24975 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24975.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lekang Yang, Yuetong Liu, Yitong Zhang, Jia Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Software development relies heavily on extensive unit testing, which makes the efficiency of automated Unit Test Generation (UTG) particularly important. However, most existing LLMs generate test cases one token at a time in each forward pass, which leads to inefficient UTG. Recently, diffusion LLMs (dLLMs) have emerged, offering promising parallel generation capabilities and showing strong potential for efficient UTG. Despite this advantage, their application to UTG is still constrained by a clear trade-off between efficiency and test quality, since increasing the number of tokens generated in each step often causes a sharp decline in the quality of test cases. To overcome this limitation, we present DiffTester, an acceleration framework specifically tailored for dLLMs in UTG. The key idea of DiffTester is that unit tests targeting the same focal method often share repetitive structural patterns. By dynamically identifying these common patterns through abstract syntax tree analysis during generation, DiffTester adaptively increases the number of tokens produced at each step without compromising the quality of the output. To enable comprehensive evaluation, we extend the original TestEval benchmark, which was limited to Python, by introducing additional programming languages including Java and C++. Extensive experiments on three benchmarks with two representative models show that DiffTester delivers significant acceleration while preserving test coverage. Moreover, DiffTester generalizes well across different dLLMs and programming languages, providing a practical and scalable solution for efficient UTG in software development. Code and data are publicly available at https://github.com/wellbeingyang/DLM4UTG-open .</p> + https://arxiv.org/abs/2509.24975 + Mon, 29 Sep 2025 16:04:18 +0000 - Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs - https://arxiv.org/abs/2509.22582 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.22582.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yehonatan Peisakhovsky, Zorik Gekhman, Yosi Mass, Liat Ein-Dor, Roi Reichart</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing complex evaluation pipelines. In the absence of established benchmarks for meta-evaluation of hallucinations localization, we construct one tailored to LLMs, involving a challenging human annotation of over 1,000 examples. We complement the benchmark with an LLM-based evaluation protocol, verifying its quality in a human evaluation. Since existing representations of hallucinations limit the types of errors that can be expressed, we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors. We conduct a comprehensive study, evaluating four large-scale LLMs, which highlights the benchmark's difficulty, as the best model achieves an F1 score of only 0.67. Through careful analysis, we offer insights into optimal prompting strategies for the task and identify the main factors that make it challenging for LLMs: (1) a tendency to incorrectly flag missing details as inconsistent, despite being instructed to check only facts in the output; and (2) difficulty with outputs containing factually correct information absent from the source - and thus not verifiable - due to alignment with the model's parametric knowledge.</p> - https://arxiv.org/abs/2509.22582 - Fri, 26 Sep 2025 17:03:24 +0000 + Triangle Splatting+: Differentiable Rendering with Opaque Triangles + https://arxiv.org/abs/2509.25122 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25122.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jan Held, Renaud Vandeghen, Sanghyun Son, Daniel Rebain, Matheus Gadelha, Yi Zhou, Ming C. Lin, Marc Van Droogenbroeck, Andrea Tagliasacchi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can achieve high-quality image synthesis, but their long training and rendering times limit practicality. 3D Gaussian Splatting (3DGS) addressed these issues by representing scenes with millions of Gaussians, enabling real-time rendering and fast optimization. However, Gaussian primitives are not natively compatible with the mesh-based pipelines used in VR headsets, and real-time graphics applications. Existing solutions attempt to convert Gaussians into meshes through post-processing or two-stage pipelines, which increases complexity and degrades visual quality. In this work, we introduce Triangle Splatting+, which directly optimizes triangles, the fundamental primitive of computer graphics, within a differentiable splatting framework. We formulate triangle parametrization to enable connectivity through shared vertices, and we design a training strategy that enforces opaque triangles. The final output is immediately usable in standard graphics engines without post-processing. Experiments on the Mip-NeRF360 and Tanks & Temples datasets show that Triangle Splatting+achieves state-of-the-art performance in mesh-based novel view synthesis. Our method surpasses prior splatting approaches in visual fidelity while remaining efficient and fast to training. Moreover, the resulting semi-connected meshes support downstream applications such as physics-based simulation or interactive walkthroughs. The project page is https://trianglesplatting2.github.io/trianglesplatting2/.</p> + https://arxiv.org/abs/2509.25122 + Mon, 29 Sep 2025 17:43:46 +0000 - RLP: Reinforcement as a Pretraining Objective - https://arxiv.org/abs/2510.01265 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01265.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye, Jan Kautz, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only as the very last phase of post-training, preceded by supervised fine-tuning. While dominant, is this an optimal way of training? In this paper, we present RLP, an information-driven reinforcement pretraining objective, that brings the core spirit of reinforcement learning -- exploration -- to the last phase of pretraining. The key idea is to treat chain-of-thought as an exploratory action, with rewards computed based on the information gain it provides for predicting future tokens. This training objective essentially encourages the model to think for itself before predicting what comes next, thus teaching an independent thinking behavior earlier in the pretraining. More concretely, the reward signal measures the increase in log-likelihood of the next token when conditioning on both context and a sampled reasoning chain, compared to conditioning on context alone. This approach yields a verifier-free dense reward signal, allowing for efficient training for the full document stream during pretraining. Specifically, RLP reframes reinforcement learning for reasoning as a pretraining objective on ordinary text, bridging the gap between next-token prediction and the emergence of useful chain-of-thought reasoning. Pretraining with RLP on Qwen3-1.7B-Base lifts the overall average across an eight-benchmark math-and-science suite by 19%. With identical post-training, the gains compound, with the largest improvements on reasoning-heavy tasks such as AIME25 and MMLU-Pro. Applying RLP to the hybrid Nemotron-Nano-12B-v2 increases the overall average from 42.81% to 61.32% and raises the average on scientific reasoning by 23%, demonstrating scalability across architectures and model sizes.</p> - https://arxiv.org/abs/2510.01265 - Fri, 26 Sep 2025 17:53:54 +0000 + Pretraining with hierarchical memories: separating long-tail and common knowledge + https://arxiv.org/abs/2510.02375 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02375.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel Tuzel</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices with limited inference-time memory and compute. We address this shortcoming by a memory-augmented architecture and a pretraining strategy aligned with existing hardware paradigms. We introduce small language models that access large hierarchical parametric memory banks encoding world knowledge. During pretraining and inference, we fetch a small, context-dependent memory block and add it to the model. Our pretraining learns to store long-tail world knowledge in the memory parameters, while the small language model acts as an anchor capturing common knowledge and general reasoning abilities. Through trillion-token-scale experiments, we show significant gains: a 160M-parameters model augmented with an 18M-parameters memory fetched from a 4.6B memory bank obtains comparable performance to a regular model with more than 2x the parameters. Through extensive experiments, we study the optimal type and size of parametric memories in transformers, scaling them to over 21B parameters. We find that our proposed hierarchical feed-forward memories work robustly across transformer architectures, whether added during pretraining or post-hoc.</p> + https://arxiv.org/abs/2510.02375 + Mon, 29 Sep 2025 17:59:50 +0000 - Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends - https://arxiv.org/abs/2509.24203 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chaorui Yao, Yanxi Chen, Yuchang Sun, Yushuo Chen, Wenhao Zhang, Xuchen Pan, Yaliang Li, Bolin Ding</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity of LLM-RL infrastructure, and the need for further innovations of RL methodologies. While classic REINFORCE and its modern variants like Group Relative Policy Optimization (GRPO) are typically regarded as on-policy algorithms with limited tolerance of off-policyness, we present in this work a first-principles derivation for group-relative REINFORCE without assuming a specific training data distribution, showing that it admits a native off-policy interpretation. This perspective yields two general principles for adapting REINFORCE to off-policy settings: regularizing policy updates, and actively shaping the data distribution. Our analysis demystifies some myths about the roles of importance sampling and clipping in GRPO, unifies and reinterprets two recent algorithms -- Online Policy Mirror Descent (OPMD) and Asymmetric REINFORCE (AsymRE) -- as regularized forms of the REINFORCE loss, and offers theoretical justification for seemingly heuristic data-weighting strategies. Our findings lead to actionable insights that are validated with extensive empirical studies, and open up new opportunities for principled algorithm design in off-policy RL for LLMs. Source code for this work is available at https://github.com/modelscope/Trinity-RFT/tree/main/examples/rec_gsm8k.</p> - https://arxiv.org/abs/2509.24203 - Mon, 29 Sep 2025 02:34:54 +0000 + Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs + https://arxiv.org/abs/2509.25771 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jia Jun Cheng Xian, Muchen Li, Haotian Yang, Xin Tao, Pengfei Wan, Leonid Sigal, Renjie Liao</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in diffusion-based text-to-image (T2I) models have led to remarkable success in generating high-quality images from textual prompts. However, ensuring accurate alignment between the text and the generated image remains a significant challenge for state-of-the-art diffusion models. To address this, existing studies employ reinforcement learning with human feedback (RLHF) to align T2I outputs with human preferences. These methods, however, either rely directly on paired image preference data or require a learned reward function, both of which depend heavily on costly, high-quality human annotations and thus face scalability limitations. In this work, we introduce Text Preference Optimization (TPO), a framework that enables "free-lunch" alignment of T2I models, achieving alignment without the need for paired image preference data. TPO works by training the model to prefer matched prompts over mismatched prompts, which are constructed by perturbing original captions using a large language model. Our framework is general and compatible with existing preference-based algorithms. We extend both DPO and KTO to our setting, resulting in TDPO and TKTO. Quantitative and qualitative evaluations across multiple benchmarks show that our methods consistently outperform their original counterparts, delivering better human preference scores and improved text-to-image alignment. Our Open-source code is available at https://github.com/DSL-Lab/T2I-Free-Lunch-Alignment.</p> + https://arxiv.org/abs/2509.25771 + Tue, 30 Sep 2025 04:32:34 +0000 - FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting - https://arxiv.org/abs/2509.24304 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefeng He, Xiaoye Qu, Yafu Li, Siyuan Huang, Daizong Liu, Yu Cheng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and struggle to handle visually intensive video tasks. To overcome these challenges, in this paper, we introduce the concept of thinking with long videos and propose a novel framework FrameThinker. Within this framework, LVLMs are able to iteratively interrogate video content. Developing such video reasoning capabilities in LVLMs presents notable challenges, particularly in adapting the model to new video actions (e.g. select frame), and designing reward functions to guide LVLMs to adopt the newly introduced action. To solve these challenges, we propose a two-phase training strategy, first employing Supervised Fine-Tuning (SFT) to instill fundamental action capabilities, followed by Reinforcement Learning (RL) to optimize a strategic decision-making policy. Notably, in this RL phase, we conduct an in-depth and comprehensive exploration of the reward design for each action and format reward. Extensive experiments on reasoning benchmarks like Video-Holmes, LongVideo-Reason, and long-video understanding benchmarks such as LongVideoBench, MLVU, VideoMME, and LVBench, demonstrate that FrameThinker achieves a significant average improvement of +10.4% over baselines while drastically reducing the number of processed frames. Most notably, our 7B model, FrameThinker establishes a new state-of-the-art on LongVideo-Reason, achieving 76.1% accuracy using an average of only 20.6 frames. This not only outperforms the competitive LongVILA-R1 (72.0%) but does so with over 20x fewer frames (vs. 512), demonstrating unparalleled efficiency and effectiveness.</p> - https://arxiv.org/abs/2509.24304 - Mon, 29 Sep 2025 05:36:58 +0000 + NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving + https://arxiv.org/abs/2509.25944 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25944.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Gao, Mattia Piccinini, Roberto Brusnicki, Yuchen Zhang, Johannes Betz</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Understanding risk in autonomous driving requires not only perception and prediction, but also high-level reasoning about agent behavior and context. Current Vision Language Models (VLMs)-based methods primarily ground agents in static images and provide qualitative judgments, lacking the spatio-temporal reasoning needed to capture how risks evolve over time. To address this gap, we propose NuRisk, a comprehensive Visual Question Answering (VQA) dataset comprising 2,900 scenarios and 1.1 million agent-level samples, built on real-world data from nuScenes and Waymo, supplemented with safety-critical scenarios from the CommonRoad simulator. The dataset provides Bird-Eye-View (BEV) based sequential images with quantitative, agent-level risk annotations, enabling spatio-temporal reasoning. We benchmark well-known VLMs across different prompting techniques and find that they fail to perform explicit spatio-temporal reasoning, resulting in a peak accuracy of 33% at high latency. To address these shortcomings, our fine-tuned 7B VLM agent improves accuracy to 41% and reduces latency by 75%, demonstrating explicit spatio-temporal reasoning capabilities that proprietary models lacked. While this represents a significant step forward, the modest accuracy underscores the profound challenge of the task, establishing NuRisk as a critical benchmark for advancing spatio-temporal reasoning in autonomous driving.</p> + https://arxiv.org/abs/2509.25944 + Tue, 30 Sep 2025 08:37:31 +0000 - Controlled Generation for Private Synthetic Text - https://arxiv.org/abs/2509.25729 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.25729.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihao Zhao, Anjalie Field</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Text anonymization is essential for responsibly developing and deploying AI in high-stakes domains such as healthcare, social services, and law. In this work, we propose a novel methodology for privacy-preserving synthetic text generation that leverages the principles of de-identification and the Hiding In Plain Sight (HIPS) theory. Our approach introduces entity-aware control codes to guide controllable generation using either in-context learning (ICL) or prefix tuning. The ICL variant ensures privacy levels consistent with the underlying de-identification system, while the prefix tuning variant incorporates a custom masking strategy and loss function to support scalable, high-quality generation. Experiments on legal and clinical datasets demonstrate that our method achieves a strong balance between privacy protection and utility, offering a practical and effective solution for synthetic text generation in sensitive domains.</p> - https://arxiv.org/abs/2509.25729 - Tue, 30 Sep 2025 03:38:36 +0000 + Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents + https://arxiv.org/abs/2509.26354 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Shao, Qihan Ren, Chen Qian, Boyi Wei, Dadi Guo, Jingyi Yang, Xinhao Song, Linfeng Zhang, Weinan Zhang, Dongrui Liu, Jing Shao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong capabilities. However, self-evolution also introduces novel risks overlooked by current safety research. In this work, we study the case where an agent's self-evolution deviates in unintended ways, leading to undesirable or even harmful outcomes. We refer to this as Misevolution. To provide a systematic investigation, we evaluate misevolution along four key evolutionary pathways: model, memory, tool, and workflow. Our empirical findings reveal that misevolution is a widespread risk, affecting agents built even on top-tier LLMs (e.g., Gemini-2.5-Pro). Different emergent risks are observed in the self-evolutionary process, such as the degradation of safety alignment after memory accumulation, or the unintended introduction of vulnerabilities in tool creation and reuse. To our knowledge, this is the first study to systematically conceptualize misevolution and provide empirical evidence of its occurrence, highlighting an urgent need for new safety paradigms for self-evolving agents. Finally, we discuss potential mitigation strategies to inspire further research on building safer and more trustworthy self-evolving agents. Our code and data are available at https://github.com/ShaoShuai0605/Misevolution . Warning: this paper includes examples that may be offensive or harmful in nature.</p> + https://arxiv.org/abs/2509.26354 + Tue, 30 Sep 2025 14:55:55 +0000 - One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient - https://arxiv.org/abs/2509.26313 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Ming, Haoyuan Wu, Shoubo Hu, Zhuolun He, Bei Yu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity stems not just from the loss function, but from a more fundamental difference: SFT learns from a fixed, pre-collected dataset, whereas RL utilizes on-policy data sampled from the current policy. Building on this hypothesis, we introduce one-token rollout (OTR), a novel fine-tuning algorithm that guides SFT with the policy gradient method. OTR reframes the autoregressive learning process by treating each token generation as a single-step reinforcement learning trajectory. At each step, it performs a Monte Carlo ``rollout'' by sampling multiple candidate tokens from the current policy's distribution. The ground-truth token from the supervised data is then used to provide a reward signal to these samples. Guided by policy gradient, our algorithm repurposes static, off-policy supervised data into a dynamic, on-policy signal at the token level, capturing the generalization benefits of on-policy learning while bypassing the costly overhead of full sentence generation. Through extensive experiments on a diverse suite of challenging benchmarks spanning mathematical reasoning, code generation, and general domain reasoning, we demonstrate that OTR consistently outperforms standard SFT. Our findings establish OTR as a powerful and practical alternative for fine-tuning LLMs and provide compelling evidence that the on-policy nature of data is a critical driver of generalization, offering a promising new direction for fine-tuning LLMs.</p> - https://arxiv.org/abs/2509.26313 - Tue, 30 Sep 2025 14:25:56 +0000 + Game-Time: Evaluating Temporal Dynamics in Spoken Language Models + https://arxiv.org/abs/2509.26388 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26388.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai-Wei Chang, En-Pei Hu, Chun-Yi Kuan, Wenze Ren, Wei-Chih Chen, Guan-Ting Lin, Yu Tsao, Shao-Hua Sun, Hung-yi Lee, James Glass</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Conversational Spoken Language Models (SLMs) are emerging as a promising paradigm for real-time speech interaction. However, their capacity of temporal dynamics, including the ability to manage timing, tempo and simultaneous speaking, remains a critical and unevaluated challenge for conversational fluency. To address this gap, we introduce the Game-Time Benchmark, a framework to systematically assess these temporal capabilities. Inspired by how humans learn a language through language activities, Game-Time consists of basic instruction-following tasks and advanced tasks with temporal constraints, such as tempo adherence and synchronized responses. Our evaluation of diverse SLM architectures reveals a clear performance disparity: while state-of-the-art models handle basic tasks well, many contemporary systems still struggle with fundamental instruction-following. More critically, nearly all models degrade substantially under temporal constraints, exposing persistent weaknesses in time awareness and full-duplex interaction. The Game-Time Benchmark provides a foundation for guiding future research toward more temporally-aware conversational AI. Demos and datasets are available on our project website https://ga642381.github.io/Game-Time.</p> + https://arxiv.org/abs/2509.26388 + Tue, 30 Sep 2025 15:23:39 +0000 - SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval - https://arxiv.org/abs/2509.26330 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications. Training-free zero-shot CIR (ZS-CIR) approaches, which require no task-specific training or labeled data, are highly desirable, yet accurately capturing user intent remains challenging. In this paper, we present SQUARE, a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enhance ZS-CIR. In the Semantic Query-Augmented Fusion (SQAF) stage, we enrich the query embedding derived from a vision-language model (VLM) such as CLIP with MLLM-generated captions of the target image. These captions provide high-level semantic guidance, enabling the query to better capture the user's intent and improve global retrieval quality. In the Efficient Batch Reranking (EBR) stage, top-ranked candidates are presented as an image grid with visual marks to the MLLM, which performs joint visual-semantic reasoning across all candidates. Our reranking strategy operates in a single pass and yields more accurate rankings. Experiments show that SQUARE, with its simplicity and effectiveness, delivers strong performance on four standard CIR benchmarks. Notably, it maintains high performance even with lightweight pre-trained, demonstrating its potential applicability.</p> - https://arxiv.org/abs/2509.26330 - Tue, 30 Sep 2025 14:41:24 +0000 + Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It + https://arxiv.org/abs/2510.00177 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00177.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuyue Stella Li, Avinandan Bose, Faeze Brahman, Simon Shaolei Du, Pang Wei Koh, Maryam Fazel, Yulia Tsvetkov</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Current large language model (LLM) development treats task-solving and preference alignment as separate challenges, optimizing first for objective correctness, then for alignment to aggregated human preferences. This paradigm fails in human-facing applications where solving a problem correctly is insufficient if the response mismatches the user's needs. This challenge intensifies in just-in-time scenarios where no prior user interaction history exists due to cold-start conditions or privacy constraints. LLMs need to identify what they don't know about user preferences, strategically elicit preference values through questioning, then adapt their reasoning processes and responses accordingly -- a complicated chain of cognitive processes which we term personalized reasoning. We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks using psychologically-grounded personas with sparse preferences. Our framework creates scenarios where identical questions require different reasoning chains depending on user context, as optimal explanation approaches vary by individual expertise and preferences while maintaining factual accuracy. Evaluation of 21 frontier models across 10 tasks reveals 29.0% of naive personalization attempts produce worse preference alignment than generic responses, yet generic responses also fail to serve individual user needs effectively. These findings suggest personalized reasoning requires dedicated development rather than emerging naturally. PREFDISCO establishes personalized reasoning as a measurable research frontier and reveals fundamental limitations in current LLMs' interactive capabilities, providing a foundation for developing systems that can adapt to individual users in education, healthcare, and technical domains where personalization is critical.</p> + https://arxiv.org/abs/2510.00177 + Tue, 30 Sep 2025 18:55:28 +0000 - Go with Your Gut: Scaling Confidence for Autoregressive Image Generation - https://arxiv.org/abs/2509.26376 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26376.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harold Haodong Chen, Xianfeng Wu, Wen-Jie Shu, Rongjin Guo, Disen Lan, Harry Yang, Ying-Cong Chen</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Test-time scaling (TTS) has demonstrated remarkable success in enhancing large language models, yet its application to next-token prediction (NTP) autoregressive (AR) image generation remains largely uncharted. Existing TTS approaches for visual AR (VAR), which rely on frequent partial decoding and external reward models, are ill-suited for NTP-based image generation due to the inherent incompleteness of intermediate decoding results. To bridge this gap, we introduce ScalingAR, the first TTS framework specifically designed for NTP-based AR image generation that eliminates the need for early decoding or auxiliary rewards. ScalingAR leverages token entropy as a novel signal in visual token generation and operates at two complementary scaling levels: (i) Profile Level, which streams a calibrated confidence state by fusing intrinsic and conditional signals; and (ii) Policy Level, which utilizes this state to adaptively terminate low-confidence trajectories and dynamically schedule guidance for phase-appropriate conditioning strength. Experiments on both general and compositional benchmarks show that ScalingAR (1) improves base models by 12.5% on GenEval and 15.2% on TIIF-Bench, (2) efficiently reduces visual token consumption by 62.0% while outperforming baselines, and (3) successfully enhances robustness, mitigating performance drops by 26.0% in challenging scenarios.</p> - https://arxiv.org/abs/2509.26376 - Tue, 30 Sep 2025 15:08:25 +0000 + Efficient Multi-modal Large Language Models via Progressive Consistency Distillation + https://arxiv.org/abs/2510.00515 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Wen, Shaobo Wang, Yufa Zhou, Junyuan Zhang, Qintong Zhang, Yifeng Gao, Zhaorun Chen, Bin Wang, Weijia Li, Conghui He, Linfeng Zhang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> Visual tokens consume substantial computational resources in multi-modal large models (MLLMs), significantly compromising their efficiency. Recent works have attempted to improve efficiency by compressing visual tokens during training, either through modifications to model components or by introducing additional parameters. However, they often overlook the increased learning difficulty caused by such compression, as the model's parameter space struggles to quickly adapt to the substantial perturbations in the feature space induced by token compression. In this work, we propose to develop Efficient MLLMs via Progressive Consistency Distillation (EPIC), a progressive learning framework. Specifically, by decomposing the feature space perturbations introduced by token compression along the token-wise and layer-wise dimensions, we introduce token consistency distillation and layer consistency distillation, respectively, aiming to reduce the training difficulty by leveraging guidance from a teacher model and following a progressive learning trajectory. Extensive experiments demonstrate the superior effectiveness, robustness, and generalization capabilities of our proposed framework.</p> + https://arxiv.org/abs/2510.00515 + Wed, 01 Oct 2025 04:56:40 +0000 - Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval - https://arxiv.org/abs/2510.00137 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00137.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nima Sheikholeslami, Erfan Hosseini, Patrice Bechard, Srivatsava Daruru, Sai Rajeswar</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Dual-encoder retrievers depend on the principle that relevant documents should score higher than irrelevant ones for a given query. Yet the dominant Noise Contrastive Estimation (NCE) objective, which underpins Contrastive Loss, optimizes a softened ranking surrogate that we rigorously prove is fundamentally oblivious to score separation quality and unrelated to AUC. This mismatch leads to poor calibration and suboptimal performance in downstream tasks like retrieval-augmented generation (RAG). To address this fundamental limitation, we introduce the MW loss, a new training objective that maximizes the Mann-Whitney U statistic, which is mathematically equivalent to the Area under the ROC Curve (AUC). MW loss encourages each positive-negative pair to be correctly ranked by minimizing binary cross entropy over score differences. We provide theoretical guarantees that MW loss directly upper-bounds the AoC, better aligning optimization with retrieval goals. We further promote ROC curves and AUC as natural threshold free diagnostics for evaluating retriever calibration and ranking quality. Empirically, retrievers trained with MW loss consistently outperform contrastive counterparts in AUC and standard retrieval metrics. Our experiments show that MW loss is an empirically superior alternative to Contrastive Loss, yielding better-calibrated and more discriminative retrievers for high-stakes applications like RAG.</p> - https://arxiv.org/abs/2510.00137 - Tue, 30 Sep 2025 18:14:01 +0000 + Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents + https://arxiv.org/abs/2510.00658 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Beomsu Kim, Byunghee Cha, Jong Chul Ye</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> With diffusion and flow matching models achieving state-of-the-art generating performance, the interest of the community now turned to reducing the inference time without sacrificing sample quality. Consistency Models (CMs), which are trained to be consistent on diffusion or probability flow ordinary differential equation (PF-ODE) trajectories, enable one or two-step flow or diffusion sampling. However, CMs typically require prolonged training with large batch sizes to obtain competitive sample quality. In this paper, we examine the training dynamics of CMs near convergence and discover that CM tangents -- CM output update directions -- are quite oscillatory, in the sense that they move parallel to the data manifold, not towards the manifold. To mitigate oscillatory tangents, we propose a new loss function, called the manifold feature distance (MFD), which provides manifold-aligned tangents that point toward the data manifold. Consequently, our method -- dubbed Align Your Tangent (AYT) -- can accelerate CM training by orders of magnitude and even out-perform the learned perceptual image patch similarity metric (LPIPS). Furthermore, we find that our loss enables training with extremely small batch sizes without compromising sample quality. Code: https://github.com/1202kbs/AYT</p> + https://arxiv.org/abs/2510.00658 + Wed, 01 Oct 2025 08:35:18 +0000 - Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation - https://arxiv.org/abs/2510.01284 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01284.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chetwin Low, Weimin Wang, Calder Katyal</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hundreds of thousands of hours of raw audio, the audio tower learns to generate realistic sound effects, as well as speech that conveys rich speaker identity and emotion. Fusion is obtained by jointly training the identical video and audio towers via blockwise exchange of timing (via scaled-RoPE embeddings) and semantics (through bidirectional cross-attention) on a vast video corpus. Our model enables cinematic storytelling with natural speech and accurate, context-matched sound effects, producing movie-grade video clips. All the demos, code and model weights are published at https://aaxwaz.github.io/Ovi</p> - https://arxiv.org/abs/2510.01284 - Tue, 30 Sep 2025 21:03:50 +0000 + Large Reasoning Models Learn Better Alignment from Flawed Thinking + https://arxiv.org/abs/2510.00938 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00938.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> ShengYun Peng, Eric Smith, Ivan Evtimov, Song Jiang, Pin-Yu Chen, Hongyuan Zhan, Haozhu Wang, Duen Horng Chau, Mahesh Pasupuleti, Jianfeng Chi</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise is injected into their thought process. We propose RECAP (Robust Safety Alignment via Counter-Aligned Prefilling), a principled reinforcement learning (RL) method for post-training that explicitly teaches models to override flawed reasoning trajectories and reroute to safe and helpful responses. RECAP trains on a mixture of synthetically generated counter-aligned CoT prefills and standard prompts, requires no additional training cost or modifications beyond vanilla reinforcement learning from human feedback (RLHF), and substantially improves safety and jailbreak robustness, reduces overrefusal, and preserves core reasoning capability -- all while maintaining inference token budget. Extensive analysis shows that RECAP-trained models engage in self-reflection more frequently and remain robust under adaptive attacks, preserving safety even after repeated attempts to override their reasoning.</p> + https://arxiv.org/abs/2510.00938 + Wed, 01 Oct 2025 14:15:43 +0000 - AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance - https://arxiv.org/abs/2510.00352 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00352.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Chen, Yinuo Zhang, Pranam Chatterjee</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce AReUReDi (Annealed Rectified Updates for Refining Discrete Flows), a discrete optimization algorithm with theoretical guarantees of convergence to the Pareto front. Building on Rectified Discrete Flows (ReDi), AReUReDi combines Tchebycheff scalarization, locally balanced proposals, and annealed Metropolis-Hastings updates to bias sampling toward Pareto-optimal states while preserving distributional invariance. Applied to peptide and SMILES sequence design, AReUReDi simultaneously optimizes up to five therapeutic properties (including affinity, solubility, hemolysis, half-life, and non-fouling) and outperforms both evolutionary and diffusion-based baselines. These results establish AReUReDi as a powerful, sequence-based framework for multi-property biomolecule generation.</p> - https://arxiv.org/abs/2510.00352 - Tue, 30 Sep 2025 23:33:33 +0000 + Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition + https://arxiv.org/abs/2510.01068 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01068.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahang Cao, Yize Huang, Hanzhong Guo, Rui Zhang, Mu Nan, Weijian Mai, Jiaxu Wang, Hao Cheng, Jingkai Sun, Gang Han, Wen Zhao, Qiang Zhang, Yijie Guo, Qihao Zheng, Chunfeng Song, Xiao Li, Ping Luo, Andrew F. Luo</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale interaction datasets. This work introduces an alternative paradigm for enhancing policy performance without additional model training. Perhaps surprisingly, we demonstrate that the composed policies can exceed the performance of either parent policy. Our contribution is threefold. First, we establish a theoretical foundation showing that the convex composition of distributional scores from multiple diffusion models can yield a superior one-step functional objective compared to any individual score. A Gr\"onwall-type bound is then used to show that this single-step improvement propagates through entire generation trajectories, leading to systemic performance gains. Second, motivated by these results, we propose General Policy Composition (GPC), a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies via a convex combination and test-time search. GPC is versatile, allowing for the plug-and-play composition of heterogeneous policies, including VA and VLA models, as well as those based on diffusion or flow-matching, irrespective of their input visual modalities. Third, we provide extensive empirical validation. Experiments on Robomimic, PushT, and RoboTwin benchmarks, alongside real-world robotic evaluations, confirm that GPC consistently improves performance and adaptability across a diverse set of tasks. Further analysis of alternative composition operators and weighting strategies offers insights into the mechanisms underlying the success of GPC. These results establish GPC as a simple yet effective method for improving control performance by leveraging existing policies.</p> + https://arxiv.org/abs/2510.01068 + Wed, 01 Oct 2025 16:05:53 +0000 - Automated Structured Radiology Report Generation with Rich Clinical Context - https://arxiv.org/abs/2510.00428 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00428.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seongjae Kang, Dong Bok Lee, Juho Jung, Dongseop Kim, Won Hwa Kim, Sunghoon Joo</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Automated structured radiology report generation (SRRG) from chest X-ray images offers significant potential to reduce workload of radiologists by generating reports in structured formats that ensure clarity, consistency, and adherence to clinical reporting standards. While radiologists effectively utilize available clinical contexts in their diagnostic reasoning, existing SRRG systems overlook these essential elements. This fundamental gap leads to critical problems including temporal hallucinations when referencing non-existent clinical contexts. To address these limitations, we propose contextualized SRRG (C-SRRG) that comprehensively incorporates rich clinical context for SRRG. We curate C-SRRG dataset by integrating comprehensive clinical context encompassing 1) multi-view X-ray images, 2) clinical indication, 3) imaging techniques, and 4) prior studies with corresponding comparisons based on patient histories. Through extensive benchmarking with state-of-the-art multimodal large language models, we demonstrate that incorporating clinical context with the proposed C-SRRG significantly improves report generation quality. We publicly release dataset, code, and checkpoints to facilitate future research for clinically-aligned automated RRG at https://github.com/vuno/contextualized-srrg.</p> - https://arxiv.org/abs/2510.00428 - Wed, 01 Oct 2025 02:14:23 +0000 + A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning + https://arxiv.org/abs/2510.01132 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01132.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruiyi Wang, Prithviraj Ammanabrolu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars -- environment, reward, and policy -- and empirically derive a recipe for training LLM agents in situated textual domains. In particular, we test TextWorld and ALFWorld, popular domains for testing situated embodied reasoning, as well as SWE-Gym for more software engineering style tasks. (i) For the environment, we analyze the impacts of task complexity in terms of sizes of the state and action spaces as well as optimal solution length, finding that even simple environments within a domain can provide signal on how well an agent can generalize to more complex tasks. (ii) For the reward, we ablate relative reward sparsity, observing that while dense turn-level rewards accelerate training, performance and stability is highly dependent on the choice of RL algorithm. (iii) And for the agent's policy, we explore the interplay between reward sparsity and biased (PPO, GRPO) and unbiased (RLOO) policy gradient methods in addition to showing how to find the optimal Supervised Fine-tuning (SFT) to RL training ratio given a fixed budget. We distill these findings into a training recipe that guides co-design across the three pillars, facilitating research and practical efforts in multi-turn agentic RL. Code: https://github.com/pearls-lab/meow-tea-taro</p> + https://arxiv.org/abs/2510.01132 + Wed, 01 Oct 2025 17:23:04 +0000 - LongCodeZip: Compress Long Context for Code Language Models - https://arxiv.org/abs/2510.00446 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00446.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuling Shi, Yichun Qian, Hongyu Zhang, Beijun Shen, Xiaodong Gu</p><p><b>Upvotes:</b> 90</p><p><b>Summary:</b> Code generation under long contexts is becoming increasingly critical as Large Language Models (LLMs) are required to reason over extensive information in the codebase. While recent advances enable code LLMs to process long inputs, high API costs and generation latency remain substantial bottlenecks. Existing context pruning techniques, such as LLMLingua, achieve promising results for general text but overlook code-specific structures and dependencies, leading to suboptimal performance in programming tasks. In this paper, we propose LongCodeZip, a novel plug-and-play code compression framework designed specifically for code LLMs. LongCodeZip employs a dual-stage strategy: (1) coarse-grained compression, which identifies and ranks function-level chunks using conditional perplexity with respect to the instruction, retaining only the most relevant functions; and (2) fine-grained compression, which segments retained functions into blocks based on perplexity and selects an optimal subset under an adaptive token budget to maximize relevance. Evaluations across multiple tasks, including code completion, summarization, and question answering, show that LongCodeZip consistently outperforms baseline methods, achieving up to a 5.6x compression ratio without degrading task performance. By effectively reducing context size while preserving essential information, LongCodeZip enables LLMs to better scale to real-world, large-scale code scenarios, advancing the efficiency and capability of code intelligence applications.</p> - https://arxiv.org/abs/2510.00446 - Wed, 01 Oct 2025 02:54:57 +0000 + Apriel-1.5-15b-Thinker + https://arxiv.org/abs/2510.01141 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01141.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla, Masoud Hashemi, Rishabh Maheshwary, Shiva Krishna Reddy Malay, Jash Mehta, Pulkit Pattnaik, Saloni Mittal, Khalil Slimi, Kelechi Ogueji, Akintunde Oladipo, Soham Parikh, Oluwanifemi Bamgbose, Toby Liang, Ahmed Masry, Khyati Mahajan, Sai Rajeswar Mudumba, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Torsten Scholak, Sagar Davasam, Srinivas Sunkara, Nicholas Chapados</p><p><b>Upvotes:</b> 77</p><p><b>Summary:</b> We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research.</p> + https://arxiv.org/abs/2510.01141 + Wed, 01 Oct 2025 17:29:35 +0000 - VIRTUE: Visual-Interactive Text-Image Universal Embedder - https://arxiv.org/abs/2510.00523 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00523.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei-Yao Wang, Kazuya Tateishi, Qiyu Wu, Shusuke Takahashi, Yuki Mitsufuji</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Multimodal representation learning models have demonstrated successful operation across complex tasks, and the integration of vision-language models (VLMs) has further enabled embedding models with instruction-following capabilities. However, existing embedding models lack visual-interactive capabilities to specify regions of interest from users (e.g., point, bounding box, mask), which have been explored in generative models to broaden their human-interactive applicability. Equipping embedding models with visual interactions not only would unlock new applications with localized grounding of user intent, which remains unexplored, but also enable the models to learn entity-level information within images to complement their global representations for conventional embedding tasks. In this paper, we propose a novel Visual-InteRactive Text-Image Universal Embedder (VIRTUE) that extends the capabilities of the segmentation model and the vision-language model to the realm of representation learning. In VIRTUE, the segmentation model can process visual prompts that pinpoint specific regions within an image, thereby enabling the embedder to handle complex and ambiguous scenarios more precisely. To evaluate the visual-interaction ability of VIRTUE, we introduce a large-scale Segmentation-and-Scene Caption Retrieval (SCaR) benchmark comprising 1M samples that aims to retrieve the text caption by jointly considering the entity with a specific object and image scene. VIRTUE consistently achieves a state-of-the-art performance with significant improvements across 36 universal MMEB (3.1%-8.5%) and five visual-interactive SCaR (15.2%-20.3%) tasks.</p> - https://arxiv.org/abs/2510.00523 - Wed, 01 Oct 2025 05:11:54 +0000 + Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling + https://arxiv.org/abs/2510.01329 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01329.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huangjie Zheng, Shansan Gong, Ruixiang Zhang, Tianrong Chen, Jiatao Gu, Mingyuan Zhou, Navdeep Jaitly, Yizhe Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented Discrete Diffusion (CADD), a framework that augments the discrete state space with a paired diffusion in a continuous latent space. This yields graded, gradually corrupted states in which masked tokens are represented by noisy yet informative latent vectors rather than collapsed 'information voids'. At each reverse step, CADD may leverage the continuous latent as a semantic hint to guide discrete denoising. The design is clean and compatible with existing discrete diffusion training. At sampling time, the strength and choice of estimator for the continuous latent vector enables a controlled trade-off between mode-coverage (generating diverse outputs) and mode-seeking (generating contextually precise outputs) behaviors. Empirically, we demonstrate CADD improves generative quality over mask-based diffusion across text generation, image synthesis, and code modeling, with consistent gains on both qualitative and quantitative metrics against strong discrete baselines.</p> + https://arxiv.org/abs/2510.01329 + Wed, 01 Oct 2025 18:00:56 +0000 - Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space? - https://arxiv.org/abs/2510.00537 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.00537.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nandan Kumar Jha, Brandon Reagen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> As large language models (LLMs) scale, the question is not only how large they become, but how much of their capacity is effectively utilized. Existing scaling laws relate model size to loss, yet overlook how components exploit their latent space. We study feed-forward networks (FFNs) and recast width selection as a spectral utilization problem. Using a lightweight diagnostic suite -- Hard Rank (participation ratio), Soft Rank (Shannon rank), Spectral Concentration, and the composite Spectral Utilization Index (SUI) -- we quantify how many latent directions are meaningfully activated across LLaMA, GPT-2, and nGPT families. Our key finding is an asymmetric spectral scaling law: soft rank follows an almost perfect power law with FFN width, while hard rank grows only sublinearly and with high variance. This asymmetry suggests that widening FFNs mostly adds low-energy tail directions, while dominant-mode subspaces saturate early. Moreover, at larger widths, variance further collapses into a narrow subspace, leaving much of the latent space under-utilized. These results recast FFN width selection as a principled trade-off between tail capacity and dominant-mode capacity, offering concrete guidance for inference-efficient LLM design.</p> - https://arxiv.org/abs/2510.00537 - Wed, 01 Oct 2025 05:38:21 +0000 + WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents + https://arxiv.org/abs/2510.01354 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01354.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinuo Liu, Ruohan Xu, Xilong Wang, Yuqi Jia, Neil Zhenqiang Gong</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents. We begin by introducing a fine-grained categorization of such attacks based on the threat model. We then construct datasets containing both malicious and benign samples: malicious text segments generated by different attacks, benign text segments from four categories, malicious images produced by attacks, and benign images from two categories. Next, we systematize both text-based and image-based detection methods. Finally, we evaluate their performance across multiple scenarios. Our key findings show that while some detectors can identify attacks that rely on explicit textual instructions or visible image perturbations with moderate to high accuracy, they largely fail against attacks that omit explicit instructions or employ imperceptible perturbations. Our datasets and code are released at: https://github.com/Norrrrrrr-lyn/WAInjectBench.</p> + https://arxiv.org/abs/2510.01354 + Wed, 01 Oct 2025 18:34:06 +0000 - Rethinking Thinking Tokens: LLMs as Improvement Operators - https://arxiv.org/abs/2510.01123 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01123.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Ruslan Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier, e.g., better accuracy with lower context length and/or latency? Abstractly, we view the model as an improvement operator on its own "thoughts" with a continuum of possible strategies. We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace, producing an output that seeds the next round. Importantly, context length (hence compute cost) is controllable via degree of parallelism, and is no longer conflated with the total number of generated tokens. We report PDR instantiations of current models that give better accuracy than long CoT while incurring lower latency. Setting degree of parallelism to 1 yields an interesting subcase, Sequential Refinement (SR) (iteratively improve a single candidate answer) which provides performance superior to long CoT. Success of such model orchestrations raises the question whether further training could shift the Pareto frontier. To this end, we train an 8B thinking model with Reinforcement Learning (RL) to make it consistent with PDR as the inference method. On math tasks with verifiable answers, iterative pipelines surpass single-pass baselines at matched sequential budgets, with PDR delivering the largest gains (e.g., +11% on AIME 2024 and +9% on AIME 2025).</p> - https://arxiv.org/abs/2510.01123 - Wed, 01 Oct 2025 17:08:59 +0000 + LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning + https://arxiv.org/abs/2510.01459 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01459.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhe Chen, Sven Koenig, Bistra Dilkina</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions to make RLVR more efficient and effective. In this paper, motivated by studies of overthinking in LLMs, we propose Length-aware Sampling for Policy Optimization (LSPO), a novel meta-RLVR algorithm that dynamically selects training data at each step based on the average response length. We evaluate LSPO across multiple base models and datasets, demonstrating that it consistently improves learning effectiveness. In addition, we conduct a detailed ablation study to examine alternative ways of incorporating length signals into dynamic sampling, offering further insights and highlighting promising directions for future research.</p> + https://arxiv.org/abs/2510.01459 + Wed, 01 Oct 2025 20:57:22 +0000 - Generalized Parallel Scaling with Interdependent Generations - https://arxiv.org/abs/2510.01143 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Harry Dong, David Brandfonbrener, Eryk Helenowski, Yun He, Mrinal Kumar, Han Fang, Yuejie Chi, Karthik Abinav Sankararaman</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Parallel LLM inference scaling involves sampling a set of N>1 responses for a single input prompt. However, these N parallel responses tend to be generated independently from each other, partitioning compute resources and leaving potentially useful information in one generation untapped by others. This is in contrast to response length scaling where past computation is used in all future steps. For higher quality responses and response sets, we propose Bridge to generate interdependent responses in parallel by rethinking batched LLM hidden states as holistic tensors rather than independent slices. With only a small amount (2.8%-5.1%) of new parameters, Bridge improves the relative mean accuracy gains from reinforcement learning with verifiable rewards by up to 50% and boosts consistency of correct responses. Trained once, Bridge scales to any generation width, all with greater performance than independent generations, unlocking a more general mode of parallel scaling that effectively leverages information between sequences, compatible with any post-generation aggregation technique.</p> - https://arxiv.org/abs/2510.01143 - Wed, 01 Oct 2025 17:33:35 +0000 + TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling + https://arxiv.org/abs/2510.01698 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01698.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Seungheon Doh, Keunwoo Choi, Juhan Nam</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While the recent developments in large language models (LLMs) have successfully enabled generative recommenders with natural language interactions, their recommendation behavior is limited, leaving other simpler yet crucial components such as metadata or attribute filtering underutilized in the system. We propose an LLM-based music recommendation system with tool calling to serve as a unified retrieval-reranking pipeline. Our system positions an LLM as an end-to-end recommendation system that interprets user intent, plans tool invocations, and orchestrates specialized components: boolean filters (SQL), sparse retrieval (BM25), dense retrieval (embedding similarity), and generative retrieval (semantic IDs). Through tool planning, the system predicts which types of tools to use, their execution order, and the arguments needed to find music matching user preferences, supporting diverse modalities while seamlessly integrating multiple database filtering methods. We demonstrate that this unified tool-calling framework achieves competitive performance across diverse recommendation scenarios by selectively employing appropriate retrieval methods based on user queries, envisioning a new paradigm for conversational music recommendation systems.</p> + https://arxiv.org/abs/2510.01698 + Thu, 02 Oct 2025 06:08:54 +0000 - ModernVBERT: Towards Smaller Visual Document Retrievers - https://arxiv.org/abs/2510.01149 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01149.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Paul Teiletche, Quentin Macé, Max Conti, Antonio Loison, Gautier Viaud, Pierre Colombo, Manuel Faysse</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Multimodal embedding models are gaining prevalence, notably for document retrieval as efficient alternatives to text-only pipelines. These models are typically built by finetuning large vision-language decoders (VLMs) with contrastive losses on text-image pairs. In this work, we show that, while cost-efficient, this repurposing approach often bottlenecks retrieval performance. Through controlled experiments, we establish a principled recipe for improving visual document retrieval models. We notably measure the impact of attention masking, image resolution, modality alignment data regimes, and late interaction centered contrastive objectives which emerge as central performance factors. Building on these insights, we release ModernVBERT, a compact 250M-parameter vision-language encoder that outperforms models up to 10 times larger when finetuned on document retrieval tasks. Models and code are made available at https://huggingface.co/ModernVBERT.</p> - https://arxiv.org/abs/2510.01149 - Wed, 01 Oct 2025 17:41:17 +0000 + OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data + https://arxiv.org/abs/2510.02410 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02410.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Patrick Langer, Thomas Kaar, Max Rosenblattl, Maxwell A. Xu, Winnie Chow, Martin Maritsch, Aradhana Verma, Brian Han, Daniel Seung Kim, Henry Chubb, Scott Ceresnak, Aydin Zahedivash, Alexander Tarlochan Singh Sandhu, Fatima Rodriguez, Daniel McDuff, Elgar Fleisch, Oliver Aalami, Filipe Barata, Paul Schmiedmayer</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> LLMs have emerged as powerful tools for interpreting multimodal data. In medicine, they hold particular promise for synthesizing large volumes of clinical information into actionable insights and digital health applications. Yet, a major limitation remains their inability to handle time series. To overcome this gap, we present OpenTSLM, a family of Time Series Language Models (TSLMs) created by integrating time series as a native modality to pretrained LLMs, enabling reasoning over multiple time series of any length. We investigate two architectures for OpenTSLM. The first, OpenTSLM-SoftPrompt, models time series implicitly by concatenating learnable time series tokens with text tokens via soft prompting. Although parameter-efficient, we hypothesize that explicit time series modeling scales better and outperforms implicit approaches. We thus introduce OpenTSLM-Flamingo, which integrates time series with text via cross-attention. We benchmark both variants against baselines that treat time series as text tokens or plots, across a suite of text-time-series Chain-of-Thought (CoT) reasoning tasks. We introduce three datasets: HAR-CoT, Sleep-CoT, and ECG-QA-CoT. Across all, OpenTSLM models outperform baselines, reaching 69.9 F1 in sleep staging and 65.4 in HAR, compared to 9.05 and 52.2 for finetuned text-only models. Notably, even 1B-parameter OpenTSLM models surpass GPT-4o (15.47 and 2.95). OpenTSLM-Flamingo matches OpenTSLM-SoftPrompt in performance and outperforms on longer sequences, while maintaining stable memory requirements. By contrast, SoftPrompt grows exponentially in memory with sequence length, requiring around 110 GB compared to 40 GB VRAM when training on ECG-QA with LLaMA-3B. Expert reviews by clinicians find strong reasoning capabilities exhibited by OpenTSLMs on ECG-QA. To facilitate further research, we provide all code, datasets, and models open-source.</p> + https://arxiv.org/abs/2510.02410 + Thu, 02 Oct 2025 09:58:23 +0000 - TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments - https://arxiv.org/abs/2510.01179 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01179.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhangchen Xu, Adriana Meza Soria, Shawn Tan, Anurag Roy, Ashish Sunil Agrawal, Radha Poovendran, Rameswar Panda</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack of high quality permissively licensed tool-agentic training data. Existing datasets are often limited in diversity, realism, and complexity, particularly regarding multi-tool and multi-turn interactions. To address this gap, we introduce Toucan, the largest publicly available tool-agentic dataset to date, containing 1.5 million trajectories synthesized from nearly 500 real-world Model Context Protocols (MCPs). Unlike prior work, Toucan leverages authentic MCP environments to generate diverse, realistic, and challenging tasks with trajectories involving real tool execution. Our pipeline first produces a broad spectrum of tool-use queries using five distinct models, applies model-based quality filtering, and then generates agentic trajectories with three teacher models using two agentic frameworks. Rigorous rule-based and model-based validation ensures high-quality outputs. We also introduce three extension mechanisms to further diversify tasks and simulate multi-turn conversations. Models fine-tuned on Toucan outperform larger closed-source counterparts on the BFCL V3 benchmark and push the Pareto frontier forward on MCP-Universe Bench.</p> - https://arxiv.org/abs/2510.01179 - Wed, 01 Oct 2025 17:58:03 +0000 + REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration + https://arxiv.org/abs/2510.01879 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01879.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yisu Wang, Ming Wang, Haoyuan Song, Wenjie Huang, Chaozheng Wang, Yi Xie, Xuming Ran</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce REPAIR (Robust Editing via Progressive Adaptive Intervention and Reintegration), a lifelong editing framework designed to support precise and low-cost model updates while preserving non-target knowledge. REPAIR mitigates the instability and conflicts of large-scale sequential edits through a closed-loop feedback mechanism coupled with dynamic memory management. Furthermore, by incorporating frequent knowledge fusion and enforcing strong locality guards, REPAIR effectively addresses the shortcomings of traditional distribution-agnostic approaches that often overlook unintended ripple effects. Our experiments demonstrate that REPAIR boosts editing accuracy by 10%-30% across multiple model families and significantly reduces knowledge forgetting. This work introduces a robust framework for developing reliable, scalable, and continually evolving LLMs.</p> + https://arxiv.org/abs/2510.01879 + Thu, 02 Oct 2025 10:35:39 +0000 - Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models - https://arxiv.org/abs/2510.01304 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01304.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zeng, Wenxuan Huang, Shiting Huang, Xikun Bao, Yukun Qi, Yiming Zhao, Qiuchen Wang, Lin Chen, Zehui Chen, Huaian Chen, Wanli Ouyang, Feng Zhao</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Although current large Vision-Language Models (VLMs) have advanced in multimodal understanding and reasoning, their fundamental perceptual and reasoning abilities remain limited. Specifically, even on simple jigsaw tasks, existing VLMs perform near randomly, revealing deficiencies in core perception and reasoning capabilities. While high-quality vision-language data can enhance these capabilities, its scarcity and limited scalability impose significant constraints. To address this, we propose AGILE, an Agentic jiGsaw Interaction Learning for Enhancing visual perception and reasoning in VLMs. AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment. At each step, the model generates executable code to perform an action based on the current state, while the environment provides fine-grained visual feedback to guide task completion. Through this iterative cycle of observation and interaction, the model incrementally improves its perceptual and reasoning capabilities via exploration and feedback. Experimental results show that AGILE not only substantially boosts performance on jigsaw tasks of varying complexity (e.g., increasing accuracy from 9.5% to 82.8% under the 2 times 2 setting) but also demonstrates strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%. These results indicate notable enhancements in both perceptual and reasoning abilities. This work opens a new avenue for advancing reasoning and generalization in multimodal models and provides an efficient, scalable solution to the scarcity of multimodal reinforcement learning data. The code and datasets is available at https://github.com/yuzeng0-0/AGILE .</p> - https://arxiv.org/abs/2510.01304 - Wed, 01 Oct 2025 17:58:05 +0000 + SoundReactor: Frame-level Online Video-to-Audio Generation + https://arxiv.org/abs/2510.02110 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Koichi Saito, Julian Tanke, Christian Simon, Masato Ishii, Kazuki Shimada, Zachary Novack, Zhi Zhong, Akio Hayakawa, Takashi Shibuya, Yuki Mitsufuji</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Prevailing Video-to-Audio (V2A) generation models operate offline, assuming an entire video sequence or chunks of frames are available beforehand. This critically limits their use in interactive applications such as live content creation and emerging generative world models. To address this gap, we introduce the novel task of frame-level online V2A generation, where a model autoregressively generates audio from video without access to future video frames. Furthermore, we propose SoundReactor, which, to the best of our knowledge, is the first simple yet effective framework explicitly tailored for this task. Our design enforces end-to-end causality and targets low per-frame latency with audio-visual synchronization. Our model's backbone is a decoder-only causal transformer over continuous audio latents. For vision conditioning, it leverages grid (patch) features extracted from the smallest variant of the DINOv2 vision encoder, which are aggregated into a single token per frame to maintain end-to-end causality and efficiency. The model is trained through a diffusion pre-training followed by consistency fine-tuning to accelerate the diffusion head decoding. On a benchmark of diverse gameplay videos from AAA titles, our model successfully generates semantically and temporally aligned, high-quality full-band stereo audio, validated by both objective and human evaluations. Furthermore, our model achieves low per-frame waveform-level latency (26.3ms with the head NFE=1, 31.5ms with NFE=4) on 30FPS, 480p videos using a single H100. Demo samples are available at https://koichi-saito-sony.github.io/soundreactor/.</p> + https://arxiv.org/abs/2510.02110 + Thu, 02 Oct 2025 15:18:00 +0000 - Aristotle: IMO-level Automated Theorem Proving - https://arxiv.org/abs/2510.01346 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01346.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tudor Achim, Alex Best, Kevin Der, Mathïs Fédérico, Sergei Gukov, Daniel Halpern-Leister, Kirsten Henningsgard, Yury Kudryashov, Alexander Meiburg, Martin Michelsen, Riley Patterson, Eric Rodriguez, Laura Scharff, Vikram Shanker, Vladmir Sicca, Hari Sowrirajan, Aidan Swope, Matyas Tamas, Vlad Tenev, Jonathan Thomm, Harold Williams, Lawrence Wu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We introduce Aristotle, an AI system that combines formal verification with informal reasoning, achieving gold-medal-equivalent performance on the 2025 International Mathematical Olympiad problems. Aristotle integrates three main components: a Lean proof search system, an informal reasoning system that generates and formalizes lemmas, and a dedicated geometry solver. Our system demonstrates state-of-the-art performance with favorable scaling properties for automated theorem proving.</p> - https://arxiv.org/abs/2510.01346 - Wed, 01 Oct 2025 18:21:13 +0000 + How Confident are Video Models? Empowering Video Models to Express their Uncertainty + https://arxiv.org/abs/2510.02571 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiting Mei, Ola Shorinwa, Anirudha Majumdar</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Generative video models demonstrate impressive text-to-video capabilities, spurring widespread adoption in many real-world applications. However, like large language models (LLMs), video generation models tend to hallucinate, producing plausible videos even when they are factually wrong. Although uncertainty quantification (UQ) of LLMs has been extensively studied in prior work, no UQ method for video models exists, raising critical safety concerns. To our knowledge, this paper represents the first work towards quantifying the uncertainty of video models. We present a framework for uncertainty quantification of generative video models, consisting of: (i) a metric for evaluating the calibration of video models based on robust rank correlation estimation with no stringent modeling assumptions; (ii) a black-box UQ method for video models (termed S-QUBED), which leverages latent modeling to rigorously decompose predictive uncertainty into its aleatoric and epistemic components; and (iii) a UQ dataset to facilitate benchmarking calibration in video models. By conditioning the generation task in the latent space, we disentangle uncertainty arising due to vague task specifications from that arising from lack of knowledge. Through extensive experiments on benchmark video datasets, we demonstrate that S-QUBED computes calibrated total uncertainty estimates that are negatively correlated with the task accuracy and effectively computes the aleatoric and epistemic constituents.</p> + https://arxiv.org/abs/2510.02571 + Thu, 02 Oct 2025 21:20:41 +0000 - VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning - https://arxiv.org/abs/2510.01444 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01444.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rui Liu, Dian Yu, Tong Zheng, Runpeng Dai, Zongxia Li, Wenhao Yu, Zhenwen Liang, Linfeng Song, Haitao Mi, Pratap Tokekar, Dong Yu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration, an issue that still persists for multimodal LLMs (MLLMs). Current methods treat the visual input as a fixed, deterministic condition, overlooking a critical source of ambiguity and struggling to build policies robust to plausible visual variations. We introduce VOGUE (Visual Uncertainty Guided Exploration), a novel method that shifts exploration from the output (text) to the input (visual) space. By treating the image as a stochastic context, VOGUE quantifies the policy's sensitivity to visual perturbations using the symmetric KL divergence between a "raw" and "noisy" branch, creating a direct signal for uncertainty-aware exploration. This signal shapes the learning objective via an uncertainty-proportional bonus, which, combined with a token-entropy bonus and an annealed sampling schedule, effectively balances exploration and exploitation. Implemented within GRPO on two model scales (Qwen2.5-VL-3B/7B), VOGUE boosts pass@1 accuracy by an average of 2.6% on three visual math benchmarks and 3.7% on three general-domain reasoning benchmarks, while simultaneously increasing pass@4 performance and mitigating the exploration decay commonly observed in RL fine-tuning. Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.</p> - https://arxiv.org/abs/2510.01444 - Wed, 01 Oct 2025 20:32:08 +0000 + Less LLM, More Documents: Searching for Improved RAG + https://arxiv.org/abs/2510.02657 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02657.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingjie Ning, Yibo Kong, Yunfan Long, Jamie Callan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators improves accuracy, it also raises cost and limits deployability. We explore an orthogonal axis: enlarging the retriever's corpus to reduce reliance on large LLMs. Experimental results show that corpus scaling consistently strengthens RAG and can often serve as a substitute for increasing model size, though with diminishing returns at larger scales. Small- and mid-sized generators paired with larger corpora often rival much larger models with smaller corpora; mid-sized models tend to gain the most, while tiny and large models benefit less. Our analysis shows that improvements arise primarily from increased coverage of answer-bearing passages, while utilization efficiency remains largely unchanged. These findings establish a principled corpus-generator trade-off: investing in larger corpora offers an effective path to stronger RAG, often comparable to enlarging the LLM itself.</p> + https://arxiv.org/abs/2510.02657 + Fri, 03 Oct 2025 01:26:13 +0000 - TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis - https://arxiv.org/abs/2510.01538 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01538.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haokun Zhao, Xiang Zhang, Jiaqi Wei, Yiwei Xu, Yuting He, Siqi Sun, Chenyu You</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Time series forecasting is central to decision-making in domains as diverse as energy, finance, climate, and public health. In practice, forecasters face thousands of short, noisy series that vary in frequency, quality, and horizon, where the dominant cost lies not in model fitting, but in the labor-intensive preprocessing, validation, and ensembling required to obtain reliable predictions. Prevailing statistical and deep learning models are tailored to specific datasets or domains and generalize poorly. A general, domain-agnostic framework that minimizes human intervention is urgently in demand. In this paper, we introduce TimeSeriesScientist (TSci), the first LLM-driven agentic framework for general time series forecasting. The framework comprises four specialized agents: Curator performs LLM-guided diagnostics augmented by external tools that reason over data statistics to choose targeted preprocessing; Planner narrows the hypothesis space of model choice by leveraging multi-modal diagnostics and self-planning over the input; Forecaster performs model fitting and validation and, based on the results, adaptively selects the best model configuration as well as ensemble strategy to make final predictions; and Reporter synthesizes the whole process into a comprehensive, transparent report. With transparent natural-language rationales and comprehensive reports, TSci transforms the forecasting workflow into a white-box system that is both interpretable and extensible across tasks. Empirical results on eight established benchmarks demonstrate that TSci consistently outperforms both statistical and LLM-based baselines, reducing forecast error by an average of 10.4% and 38.2%, respectively. Moreover, TSci produces a clear and rigorous report that makes the forecasting workflow more transparent and interpretable.</p> - https://arxiv.org/abs/2510.01538 - Thu, 02 Oct 2025 00:18:59 +0000 + Self-Improvement in Multimodal Large Language Models: A Survey + https://arxiv.org/abs/2510.02665 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02665.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijian Deng, Kai Wang, Tianyu Yang, Harsh Singh, Yapeng Tian</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms of human effort. While this area is still relatively young, its extension to the multimodal domain holds immense potential for leveraging diverse data sources and developing more general self-improving models. This survey is the first to provide a comprehensive overview of self-improvement in Multimodal LLMs (MLLMs). We provide a structured overview of the current literature and discuss methods from three perspectives: 1) data collection, 2) data organization, and 3) model optimization, to facilitate the further development of self-improvement in MLLMs. We also include commonly used evaluations and downstream applications. Finally, we conclude by outlining open challenges and future research directions.</p> + https://arxiv.org/abs/2510.02665 + Fri, 03 Oct 2025 01:48:26 +0000 - Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression - https://arxiv.org/abs/2510.01581 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01581.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad, Elias Stengel-Eskin, Akshay Nambi, Mohit Bansal</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent thinking models solve complex reasoning tasks by scaling test-time compute, but this scaling must be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require extended reasoning steps; but, excessively long reasoning (overthinking) can be token-inefficient, generating unnecessary steps even after reaching a correct intermediate solution. We refer to this as under-adaptivity, where the model fails to modulate its response length appropriately given problems of varying difficulty. To address under-adaptivity and strike a balance between under- and overthinking, we propose TRAAC (Think Right with Adaptive, Attentive Compression), an online post-training RL method that leverages the model's self-attention over a long reasoning trajectory to identify important steps and prune redundant ones. TRAAC also estimates difficulty and incorporates it into training rewards, thereby learning to allocate reasoning budget commensurate with example difficulty. Our approach improves accuracy, reduces reasoning steps, and enables adaptive thinking compared to base models and other RL baselines. Across a variety of tasks (AIME, AMC, GPQA-D, BBEH), TRAAC (Qwen3-4B) achieves an average absolute accuracy gain of 8.4% with a relative reduction in reasoning length of 36.8% compared to the base model, and a 7.9% accuracy gain paired with a 29.4% length drop compared to the best RL baseline. TRAAC also shows strong generalization: although our models are trained on math datasets, they show accuracy and efficiency gains on out-of-distribution non-math datasets like GPQA-D, BBEH, and OptimalThinkingBench. Our analysis further verifies that TRAAC provides fine-grained adjustments to thinking budget based on difficulty and that a combination of task-difficulty calibration and attention-based compression yields gains across diverse tasks.</p> - https://arxiv.org/abs/2510.01581 - Thu, 02 Oct 2025 02:00:20 +0000 + Dale meets Langevin: A Multiplicative Denoising Diffusion Model + https://arxiv.org/abs/2510.02730 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nishanth Shetty, Madhava Prasath, Chandra Sekhar Seelamantula</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Gradient descent has proven to be a powerful and effective technique for optimization in numerous machine learning applications. Recent advances in computational neuroscience have shown that learning in standard gradient descent optimization formulation is not consistent with learning in biological systems. This has opened up interesting avenues for building biologically inspired learning techniques. One such approach is inspired by Dale's law, which states that inhibitory and excitatory synapses do not swap roles during the course of learning. The resulting exponential gradient descent optimization scheme leads to log-normally distributed synaptic weights. Interestingly, the density that satisfies the Fokker-Planck equation corresponding to the stochastic differential equation (SDE) with geometric Brownian motion (GBM) is the log-normal density. Leveraging this connection, we start with the SDE governing geometric Brownian motion, and show that discretizing the corresponding reverse-time SDE yields a multiplicative update rule, which surprisingly, coincides with the sampling equivalent of the exponential gradient descent update founded on Dale's law. Furthermore, we propose a new formalism for multiplicative denoising score-matching, subsuming the loss function proposed by Hyvaerinen for non-negative data. Indeed, log-normally distributed data is positive and the proposed score-matching formalism turns out to be a natural fit. This allows for training of score-based models for image data and results in a novel multiplicative update scheme for sample generation starting from a log-normal density. Experimental results on MNIST, Fashion MNIST, and Kuzushiji datasets demonstrate generative capability of the new scheme. To the best of our knowledge, this is the first instance of a biologically inspired generative model employing multiplicative updates, founded on geometric Brownian motion.</p> + https://arxiv.org/abs/2510.02730 + Fri, 03 Oct 2025 05:23:33 +0000 - CLUE: Non-parametric Verification from Experience via Hidden-State Clustering - https://arxiv.org/abs/2510.01591 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01591.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenwen Liang, Ruosen Li, Yujun Zhou, Linfeng Song, Dian Yu, Xinya Du, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Assessing the quality of Large Language Model (LLM) outputs presents a critical challenge. Previous methods either rely on text-level information (e.g., reward models, majority voting), which can overfit to superficial cues, or on calibrated confidence from token probabilities, which would fail on less-calibrated models. Yet both of these signals are, in fact, partial projections of a richer source of information: the model's internal hidden states. Early layers, closer to token embeddings, preserve semantic and lexical features that underpin text-based judgments, while later layers increasingly align with output logits, embedding confidence-related information. This paper explores hidden states directly as a unified foundation for verification. We show that the correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations. To validate this, we present Clue (Clustering and Experience-based Verification), a deliberately minimalist, non-parametric verifier. With no trainable parameters, CLUE only summarizes each reasoning trace by an hidden state delta and classifies correctness via nearest-centroid distance to ``success'' and ``failure'' clusters formed from past experience. The simplicity of this method highlights the strength of the underlying signal. Empirically, CLUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates, improving both top-1 and majority-vote accuracy across AIME 24/25 and GPQA. As a highlight, on AIME 24 with a 1.5B model, CLUE boosts accuracy from 56.7% (majority@64) to 70.0% (top-maj@16).</p> - https://arxiv.org/abs/2510.01591 - Thu, 02 Oct 2025 02:14:33 +0000 + Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models + https://arxiv.org/abs/2510.02880 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify the theoretical foundation for DDMs, which facilitates building an importance estimator that captures valuable token fluctuation for gradient updates. We then delicately tailored the rollout method for visual sequences, which yields diverse completions and reliable optimization gradients. Upon math reasoning, coding, and visual generation benchmarks, MaskGRPO brings more stable and efficient updates, leading to stronger reasoning performance and better generation quality. This study establishes MaskGRPO as a systematic policy optimization approach and the first practical way for discretized visual diffusion.</p> + https://arxiv.org/abs/2510.02880 + Fri, 03 Oct 2025 10:36:24 +0000 - VLA-R1: Enhancing Reasoning in Vision-Language-Action Models - https://arxiv.org/abs/2510.01623 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01623.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Angen Ye, Zeyu Zhang, Boyuan Wang, Xiaofeng Wang, Dapeng Zhang, Zheng Zhu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack explicit step-by-step reasoning, instead emitting final actions without considering affordance constraints or geometric relations. Their post-training pipelines also rarely reinforce reasoning quality, relying primarily on supervised fine-tuning with weak reward design. To address these challenges, we present VLA-R1, a reasoning-enhanced VLA that integrates Reinforcement Learning from Verifiable Rewards (RLVR) with Group Relative Policy Optimization (GRPO) to systematically optimize both reasoning and execution. Specifically, we design an RLVR-based post-training strategy with verifiable rewards for region alignment, trajectory consistency, and output formatting, thereby strengthening reasoning robustness and execution accuracy. Moreover, we develop VLA-CoT-13K, a high-quality dataset that provides chain-of-thought supervision explicitly aligned with affordance and trajectory annotations. Furthermore, extensive evaluations on in-domain, out-of-domain, simulation, and real-robot platforms demonstrate that VLA-R1 achieves superior generalization and real-world performance compared to prior VLA methods. We plan to release the model, code, and dataset following the publication of this work. Code: https://github.com/GigaAI-research/VLA-R1. Website: https://gigaai-research.github.io/VLA-R1.</p> - https://arxiv.org/abs/2510.01623 - Thu, 02 Oct 2025 02:54:03 +0000 + SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys? + https://arxiv.org/abs/2510.03120 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaojun Sun, Xuzhou Zhu, Xuanhe Zhou, Xin Tong, Shuo Wang, Jie Fu, Guoliang Li, Zhiyuan Liu, Fan Wu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Academic survey writing, which distills vast literature into a coherent and insightful narrative, remains a labor-intensive and intellectually demanding task. While recent approaches, such as general DeepResearch agents and survey-specialized methods, can generate surveys automatically (a.k.a. LLM4Survey), their outputs often fall short of human standards and there lacks a rigorous, reader-aligned benchmark for thoroughly revealing their deficiencies. To fill the gap, we propose a fine-grained, quiz-driven evaluation framework SurveyBench, featuring (1) typical survey topics source from recent 11,343 arXiv papers and corresponding 4,947 high-quality surveys; (2) a multifaceted metric hierarchy that assesses the outline quality (e.g., coverage breadth, logical coherence), content quality (e.g., synthesis granularity, clarity of insights), and non-textual richness; and (3) a dual-mode evaluation protocol that includes content-based and quiz-based answerability tests, explicitly aligned with readers' informational needs. Results show SurveyBench effectively challenges existing LLM4Survey approaches (e.g., on average 21% lower than human in content-based evaluation).</p> + https://arxiv.org/abs/2510.03120 + Fri, 03 Oct 2025 15:49:09 +0000 - Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness - https://arxiv.org/abs/2510.01670 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01670.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erfan Shayegani, Keegan Hines, Yue Dong, Nael Abu-Ghazaleh, Roman Lutz, Spencer Whitehead, Vidhisha Balachandran, Besmira Nushi, Vibhav Vineet</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Blind Goal-Directedness (BGD): a bias to pursue goals regardless of feasibility, safety, reliability, or context. We characterize three prevalent patterns of BGD: (i) lack of contextual reasoning, (ii) assumptions and decisions under ambiguity, and (iii) contradictory or infeasible goals. We develop BLIND-ACT, a benchmark of 90 tasks capturing these three patterns. Built on OSWorld, BLIND-ACT provides realistic environments and employs LLM-based judges to evaluate agent behavior, achieving 93.75% agreement with human annotations. We use BLIND-ACT to evaluate nine frontier models, including Claude Sonnet and Opus 4, Computer-Use-Preview, and GPT-5, observing high average BGD rates (80.8%) across them. We show that BGD exposes subtle risks that arise even when inputs are not directly harmful. While prompting-based interventions lower BGD levels, substantial risk persists, highlighting the need for stronger training- or inference-time interventions. Qualitative analysis reveals observed failure modes: execution-first bias (focusing on how to act over whether to act), thought-action disconnect (execution diverging from reasoning), and request-primacy (justifying actions due to user request). Identifying BGD and introducing BLIND-ACT establishes a foundation for future research on studying and mitigating this fundamental risk and ensuring safe CUA deployment.</p> - https://arxiv.org/abs/2510.01670 - Thu, 02 Oct 2025 04:52:15 +0000 + SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus + https://arxiv.org/abs/2510.03160 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03160.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Zhao, Wenhui Dong, Yang Zhang, Xiang Zheng, Zhonghao Zhang, Zian Zhou, Yunzhi Guan, Liukun Xu, Wei Peng, Zhaoyang Gong, Zhicheng Zhang, Dachuan Li, Xiaosheng Ma, Yuli Ma, Jianing Ni, Changjiang Jiang, Lixia Tian, Qixin Chen, Kaishun Xia, Pingping Liu, Tongshun Zhang, Zhiqiang Liu, Zhongan Bi, Chenyang Si, Tiansheng Sun, Caifeng Shan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Spine disorders affect 619 million people globally and are a leading cause of disability, yet AI-assisted diagnosis remains limited by the lack of level-aware, multimodal datasets. Clinical decision-making for spine disorders requires sophisticated reasoning across X-ray, CT, and MRI at specific vertebral levels. However, progress has been constrained by the absence of traceable, clinically-grounded instruction data and standardized, spine-specific benchmarks. To address this, we introduce SpineMed, an ecosystem co-designed with practicing spine surgeons. It features SpineMed-450k, the first large-scale dataset explicitly designed for vertebral-level reasoning across imaging modalities with over 450,000 instruction instances, and SpineBench, a clinically-grounded evaluation framework. SpineMed-450k is curated from diverse sources, including textbooks, guidelines, open datasets, and ~1,000 de-identified hospital cases, using a clinician-in-the-loop pipeline with a two-stage LLM generation method (draft and revision) to ensure high-quality, traceable data for question-answering, multi-turn consultations, and report generation. SpineBench evaluates models on clinically salient axes, including level identification, pathology assessment, and surgical planning. Our comprehensive evaluation of several recently advanced large vision-language models (LVLMs) on SpineBench reveals systematic weaknesses in fine-grained, level-specific reasoning. In contrast, our model fine-tuned on SpineMed-450k demonstrates consistent and significant improvements across all tasks. Clinician assessments confirm the diagnostic clarity and practical utility of our model's outputs.</p> + https://arxiv.org/abs/2510.03160 + Fri, 03 Oct 2025 16:32:02 +0000 - MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs - https://arxiv.org/abs/2510.01691 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01691.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Xinzhe Luo, Pengcheng Chen, Xin Gao, Ming Hu, Huihui Xu, Xin Wang, Shujian Gao, Dingkang Yang, Zhongying Deng, Jin Ye, Lihao Liu, Junjun He, Ningsheng Xu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Medical Image Quality Assessment (IQA) serves as the first-mile safety gate for clinical AI, yet existing approaches remain constrained by scalar, score-based metrics and fail to reflect the descriptive, human-like reasoning process central to expert evaluation. To address this gap, we introduce MedQ-Bench, a comprehensive benchmark that establishes a perception-reasoning paradigm for language-based evaluation of medical image quality with Multi-modal Large Language Models (MLLMs). MedQ-Bench defines two complementary tasks: (1) MedQ-Perception, which probes low-level perceptual capability via human-curated questions on fundamental visual attributes; and (2) MedQ-Reasoning, encompassing both no-reference and comparison reasoning tasks, aligning model evaluation with human-like reasoning on image quality. The benchmark spans five imaging modalities and over forty quality attributes, totaling 2,600 perceptual queries and 708 reasoning assessments, covering diverse image sources including authentic clinical acquisitions, images with simulated degradations via physics-based reconstructions, and AI-generated images. To evaluate reasoning ability, we propose a multi-dimensional judging protocol that assesses model outputs along four complementary axes. We further conduct rigorous human-AI alignment validation by comparing LLM-based judgement with radiologists. Our evaluation of 14 state-of-the-art MLLMs demonstrates that models exhibit preliminary but unstable perceptual and reasoning skills, with insufficient accuracy for reliable clinical use. These findings highlight the need for targeted optimization of MLLMs in medical IQA. We hope that MedQ-Bench will catalyze further exploration and unlock the untapped potential of MLLMs for medical image quality evaluation.</p> - https://arxiv.org/abs/2510.01691 - Thu, 02 Oct 2025 05:42:00 +0000 + CoDA: Agentic Systems for Collaborative Data Visualization + https://arxiv.org/abs/2510.03194 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03194.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichen Chen, Jiefeng Chen, Sercan Ö. Arik, Misha Sra, Tomas Pfister, Jinsung Yoon</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity, code errors, or final visualization quality. In this paper, we reframe this challenge as a collaborative multi-agent problem. We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection. We formalize this pipeline, demonstrating how metadata-focused analysis bypasses token limits and quality-driven refinement ensures robustness. Extensive evaluations show CoDA achieves substantial gains in the overall score, outperforming competitive baselines by up to 41.5%. This work demonstrates that the future of visualization automation lies not in isolated code generation but in integrated, collaborative agentic workflows.</p> + https://arxiv.org/abs/2510.03194 + Fri, 03 Oct 2025 17:30:16 +0000 - Rethinking the shape convention of an MLP - https://arxiv.org/abs/2510.01796 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01796.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meng-Hsi Chen, Yu-Ang Lee, Feng-Ting Liao, Da-shan Shiu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Multi-layer perceptrons (MLPs) conventionally follow a narrow-wide-narrow design where skip connections operate at the input/output dimensions while processing occurs in expanded hidden spaces. We challenge this convention by proposing wide-narrow-wide (Hourglass) MLP blocks where skip connections operate at expanded dimensions while residual computation flows through narrow bottlenecks. This inversion leverages higher-dimensional spaces for incremental refinement while maintaining computational efficiency through parameter-matched designs. Implementing Hourglass MLPs requires an initial projection to lift input signals to expanded dimensions. We propose that this projection can remain fixed at random initialization throughout training, enabling efficient training and inference implementations. We evaluate both architectures on generative tasks over popular image datasets, characterizing performance-parameter Pareto frontiers through systematic architectural search. Results show that Hourglass architectures consistently achieve superior Pareto frontiers compared to conventional designs. As parameter budgets increase, optimal Hourglass configurations favor deeper networks with wider skip connections and narrower bottlenecks-a scaling pattern distinct from conventional MLPs. Our findings suggest reconsidering skip connection placement in modern architectures, with potential applications extending to Transformers and other residual networks.</p> - https://arxiv.org/abs/2510.01796 - Thu, 02 Oct 2025 08:38:15 +0000 + FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents + https://arxiv.org/abs/2510.03204 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03204.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Léo Boisvert, Massimo Caccia, Jérémy Espinas, Alexandre Aussem, Véronique Eglin, Alexandre Lacoste</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost processing; moreover, processing full pages exposes agents to security risks such as prompt injection. Existing pruning strategies either discard relevant content or retain irrelevant context, leading to suboptimal action prediction. We introduce FocusAgent, a simple yet effective approach that leverages a lightweight LLM retriever to extract the most relevant lines from accessibility tree (AxTree) observations, guided by task goals. By pruning noisy and irrelevant content, FocusAgent enables efficient reasoning while reducing vulnerability to injection attacks. Experiments on WorkArena and WebArena benchmarks show that FocusAgent matches the performance of strong baselines, while reducing observation size by over 50%. Furthermore, a variant of FocusAgent significantly reduces the success rate of prompt-injection attacks, including banner and pop-up attacks, while maintaining task success performance in attack-free settings. Our results highlight that targeted LLM-based retrieval is a practical and robust strategy for building web agents that are efficient, effective, and secure.</p> + https://arxiv.org/abs/2510.03204 + Fri, 03 Oct 2025 17:41:30 +0000 - Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction - https://arxiv.org/abs/2510.01817 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adam Filipek</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with respect to sequence length presents a significant barrier to scaling, particularly for applications involving long contexts. Prevailing solutions, such as Multi-Query Attention (MQA) and Grouped-Query Attention (GQA), have effectively addressed the memory bandwidth bottleneck that dominates autoregressive inference latency by sharing Key and Value projections. While highly successful, these methods do not reduce the fundamental number of floating-point operations (FLOPs) required for the attention score computation, which remains a critical bottleneck for training and full-sequence processing. This paper introduces Sparse Query Attention (SQA), a novel attention architecture that pursues an alternative and complementary optimization path. Instead of reducing Key/Value heads, SQA reduces the number of Query heads. This architectural modification directly decreases the computational complexity of the attention mechanism by a factor proportional to the reduction in query heads, thereby lowering the overall FLOPs. This work presents the theoretical foundation of SQA, its mathematical formulation, and a family of architectural variants. Empirical benchmarks on long sequences (32k-200k tokens) demonstrate that SQA can achieve significant throughput improvements of up to 3x in computation-bound scenarios such as model pre-training, fine-tuning, and encoder-based tasks, with only a minimal impact on model quality in preliminary smallscale experiments. SQA was discovered serendipitously during the development of the upcoming Reactive Transformer architecture, suggesting its potential as a powerful tool for building more efficient and scalable models</p> - https://arxiv.org/abs/2510.01817 - Thu, 02 Oct 2025 09:01:38 +0000 + Improving GUI Grounding with Explicit Position-to-Coordinate Mapping + https://arxiv.org/abs/2510.03230 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03230.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suyuchen Wang, Tianyu Zhang, Ahmed Masry, Christopher Pal, Spandana Gella, Bang Liu, Perouz Taslakian</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck is reliable patch-to-pixel mapping, which breaks when extrapolating to high-resolution displays unseen during training. Current approaches generate coordinates as text tokens directly from visual features, forcing the model to infer complex position-to-pixel mappings implicitly; as a result, accuracy degrades and failures proliferate on new resolutions. We address this with two complementary innovations. First, RULER tokens serve as explicit coordinate markers, letting the model reference positions similar to gridlines on a map and adjust rather than generate coordinates from scratch. Second, Interleaved MRoPE (I-MRoPE) improves spatial encoding by ensuring that width and height dimensions are represented equally, addressing the asymmetry of standard positional schemes. Experiments on ScreenSpot, ScreenSpot-V2, and ScreenSpot-Pro show consistent gains in grounding accuracy, with the largest improvements on high-resolution interfaces. By providing explicit spatial guidance rather than relying on implicit learning, our approach enables more reliable GUI automation across diverse resolutions and platforms.</p> + https://arxiv.org/abs/2510.03230 + Fri, 03 Oct 2025 17:59:34 +0000 - Learning to Reason for Hallucination Span Detection - https://arxiv.org/abs/2510.02173 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02173.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula, Kundan Krishna, Hadi Pouransari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja Vemulapalli</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large language models (LLMs) often generate hallucinations -- unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task, many real-world applications require identifying hallucinated spans, which is a multi-step decision making process. This naturally raises the question of whether explicit reasoning can help the complex task of detecting hallucination spans. To answer this question, we first evaluate pretrained models with and without Chain-of-Thought (CoT) reasoning, and show that CoT reasoning has the potential to generate at least one correct answer when sampled multiple times. Motivated by this, we propose RL4HS, a reinforcement learning framework that incentivizes reasoning with a span-level reward function. RL4HS builds on Group Relative Policy Optimization and introduces Class-Aware Policy Optimization to mitigate reward imbalance issue. Experiments on the RAGTruth benchmark (summarization, question answering, data-to-text) show that RL4HS surpasses pretrained reasoning models and supervised fine-tuning, demonstrating the necessity of reinforcement learning with span-level rewards for detecting hallucination spans.</p> - https://arxiv.org/abs/2510.02173 - Thu, 02 Oct 2025 16:24:28 +0000 - - - A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports - https://arxiv.org/abs/2510.02190 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02190.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Yao, Yixu Wang, Yuxuan Zhang, Yi Lu, Tianle Gu, Lingyu Li, Dingyi Zhao, Keming Wu, Haozhe Wang, Ping Nie, Yan Teng, Yingchun Wang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Artificial intelligence is undergoing the paradigm shift from closed language models to interconnected agent systems capable of external perception and information integration. As a representative embodiment, Deep Research Agents (DRAs) systematically exhibit the capabilities for task decomposition, cross-source retrieval, multi-stage reasoning, and structured output, which markedly enhance performance on complex and open-ended tasks. However, existing benchmarks remain deficient in evaluation dimensions, response formatting, and scoring mechanisms, limiting their capacity to assess such systems effectively. This paper introduces a rigorous benchmark and a multidimensional evaluation framework tailored to DRAs and report-style responses. The benchmark comprises 214 expert-curated challenging queries distributed across 10 broad thematic domains, each accompanied by manually constructed reference bundles to support composite evaluation. The framework enables comprehensive evaluation of long-form reports generated by DRAs, incorporating integrated scoring metrics for semantic quality, topical focus, and retrieval trustworthiness. Extensive experimentation confirms the superior performance of mainstream DRAs over web-search-tool-augmented reasoning models, yet reveals considerable scope for further improvement. This study provides a robust foundation for capability assessment, architectural refinement, and paradigm advancement in DRA systems.</p> - https://arxiv.org/abs/2510.02190 - Thu, 02 Oct 2025 16:40:02 +0000 - - - StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? - https://arxiv.org/abs/2510.02209 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanxu Chen, Zijun Yao, Yantao Liu, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, but they fall short of capturing the dynamic and iterative nature of trading. To address this gap, we introduce StockBench, a contamination-free benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments. Agents receive daily market signals -- including prices, fundamentals, and news -- and must make sequential buy, sell, or hold decisions. Performance is assessed using financial metrics such as cumulative return, maximum drawdown, and the Sortino ratio. Our evaluation of state-of-the-art proprietary (e.g., GPT-5, Claude-4) and open-weight (e.g., Qwen3, Kimi-K2, GLM-4.5) models shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively. These findings highlight both the challenges and opportunities in developing LLM-powered financial agents, showing that excelling at static financial knowledge tasks does not necessarily translate into successful trading strategies. We release StockBench as an open-source resource to support reproducibility and advance future research in this domain.</p> - https://arxiv.org/abs/2510.02209 - Thu, 02 Oct 2025 16:54:57 +0000 - - - RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning - https://arxiv.org/abs/2510.02240 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sicheng Feng, Kaiwen Tuo, Song Wang, Lingdong Kong, Jianke Zhu, Huan Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and information-rich settings such as transit maps, a task of clear practical and scientific importance. However, standard reinforcement learning (RL) on such tasks is impeded by sparse rewards and unstable optimization. To address this, we first construct ReasonMap-Plus, an extended dataset that introduces dense reward signals through Visual Question Answering (VQA) tasks, enabling effective cold-start training of fine-grained visual understanding skills. Next, we propose RewardMap, a multi-stage RL framework designed to improve both visual understanding and reasoning capabilities of MLLMs. RewardMap incorporates two key designs. First, we introduce a difficulty-aware reward design that incorporates detail rewards, directly tackling the sparse rewards while providing richer supervision. Second, we propose a multi-stage RL scheme that bootstraps training from simple perception to complex reasoning tasks, offering a more effective cold-start strategy than conventional Supervised Fine-Tuning (SFT). Experiments on ReasonMap and ReasonMap-Plus demonstrate that each component of RewardMap contributes to consistent performance gains, while their combination yields the best results. Moreover, models trained with RewardMap achieve an average improvement of 3.47% across 6 benchmarks spanning spatial reasoning, fine-grained visual reasoning, and general tasks beyond transit maps, underscoring enhanced visual understanding and reasoning capabilities.</p> - https://arxiv.org/abs/2510.02240 - Thu, 02 Oct 2025 17:29:46 +0000 - - - ExGRPO: Learning to Reason from Experience - https://arxiv.org/abs/2510.02245 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runzhe Zhan, Yafu Li, Zhi Wang, Xiaoye Qu, Dongrui Liu, Jing Shao, Derek F. Wong, Yu Cheng</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability. While prior work on RL has highlighted the benefits of reusing past experience, the role of experience characteristics in shaping learning dynamics of large reasoning models remains underexplored. In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value. Based on these insights, we propose ExGRPO (Experiential Group Relative Policy Optimization), a framework that organizes and prioritizes valuable experiences, and employs a mixed-policy objective to balance exploration with experience exploitation. Experiments on five backbone models (1.5B-8B parameters) show that ExGRPO consistently improves reasoning performance on mathematical/general benchmarks, with an average gain of +3.5/7.6 points over on-policy RLVR. Moreover, ExGRPO stabilizes training on both stronger and weaker models where on-policy methods fail. These results highlight principled experience management as a key ingredient for efficient and scalable RLVR.</p> - https://arxiv.org/abs/2510.02245 - Thu, 02 Oct 2025 17:31:30 +0000 - - - The Unreasonable Effectiveness of Scaling Agents for Computer Use - https://arxiv.org/abs/2510.02250 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02250.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gonzalo Gonzalez-Pumariega, Vincent Tu, Chih-Lun Lee, Jiachen Yang, Ang Li, Xin Eric Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their unreliability and high variance hinder their application to long-horizon, complex tasks. We introduce Behavior Best-of-N (bBoN), a method that scales over agents by generating multiple rollouts and selecting among them using behavior narratives that describe the agents' rollouts. It enables both wide exploration and principled trajectory selection, substantially improving robustness and success rates. On OSWorld, our bBoN scaling method establishes a new state of the art (SoTA) at 69.9%, significantly outperforming prior methods and approaching human-level performance at 72%, with comprehensive ablations validating key design choices. We further demonstrate strong generalization results to different operating systems on WindowsAgentArena and AndroidWorld. Crucially, our results highlight the unreasonable effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and bBoN provides a practical framework to achieve this.</p> - https://arxiv.org/abs/2510.02250 - Thu, 02 Oct 2025 17:37:08 +0000 - - - DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing - https://arxiv.org/abs/2510.02253 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02253.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Wai-Kin Kong</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with flow matching (e.g., SD3.5, FLUX), generative priors have become significantly stronger, enabling advances across diverse editing tasks. However, drag-based editing has yet to benefit from these stronger priors. This work proposes the first framework to effectively harness FLUX's rich prior for drag-based editing, dubbed DragFlow, achieving substantial gains over baselines. We first show that directly applying point-based drag editing to DiTs performs poorly: unlike the highly compressed features of UNets, DiT features are insufficiently structured to provide reliable guidance for point-wise motion supervision. To overcome this limitation, DragFlow introduces a region-based editing paradigm, where affine transformations enable richer and more consistent feature supervision. Additionally, we integrate pretrained open-domain personalization adapters (e.g., IP-Adapter) to enhance subject consistency, while preserving background fidelity through gradient mask-based hard constraints. Multimodal large language models (MLLMs) are further employed to resolve task ambiguities. For evaluation, we curate a novel Region-based Dragging benchmark (ReD Bench) featuring region-level dragging instructions. Extensive experiments on DragBench-DR and ReD Bench show that DragFlow surpasses both point-based and region-based baselines, setting a new state-of-the-art in drag-based image editing. Code and datasets will be publicly available upon publication.</p> - https://arxiv.org/abs/2510.02253 - Thu, 02 Oct 2025 17:39:13 +0000 - - - Transformers Discover Molecular Structure Without Graph Priors - https://arxiv.org/abs/2510.02259 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tobias Kreiman, Yutong Bai, Fadi Atieh, Elizabeth Weaver, Eric Qu, Aditi S. Krishnapriyan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Graph Neural Networks (GNNs) are the dominant architecture for molecular machine learning, particularly for molecular property prediction and machine learning interatomic potentials (MLIPs). GNNs perform message passing on predefined graphs often induced by a fixed radius cutoff or k-nearest neighbor scheme. While this design aligns with the locality present in many molecular tasks, a hard-coded graph can limit expressivity due to the fixed receptive field and slows down inference with sparse graph operations. In this work, we investigate whether pure, unmodified Transformers trained directly on Cartesian coordinatesx2013without predefined graphs or physical priorsx2013can approximate molecular energies and forces. As a starting point for our analysis, we demonstrate how to train a Transformer to competitive energy and force mean absolute errors under a matched training compute budget, relative to a state-of-the-art equivariant GNN on the OMol25 dataset. We discover that the Transformer learns physically consistent patternsx2013such as attention weights that decay inversely with interatomic distancex2013and flexibly adapts them across different molecular environments due to the absence of hard-coded biases. The use of a standard Transformer also unlocks predictable improvements with respect to scaling training resources, consistent with empirical scaling laws observed in other domains. Our results demonstrate that many favorable properties of GNNs can emerge adaptively in Transformers, challenging the necessity of hard-coded graph inductive biases and pointing toward standardized, scalable architectures for molecular modeling.</p> - https://arxiv.org/abs/2510.02259 - Thu, 02 Oct 2025 17:42:10 +0000 - - - RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems - https://arxiv.org/abs/2510.02263 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02263.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Ruslan Salakhutdinov, Chelsea Finn, Aviral Kumar</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems. Doing so requires realizing the most relevant primitives, intermediate results, or shared procedures, and building upon them. While RL post-training on long chains of thought ultimately aims to uncover this kind of algorithmic behavior, most reasoning traces learned by large models fail to consistently capture or reuse procedures, instead drifting into verbose and degenerate exploration. To address more effective reasoning, we introduce reasoning abstractions: concise natural language descriptions of procedural and factual knowledge that guide the model toward learning successful reasoning. We train models to be capable of proposing multiple abstractions given a problem, followed by RL that incentivizes building a solution while using the information provided by these abstractions. This results in a two-player RL training paradigm, abbreviated as RLAD, that jointly trains an abstraction generator and a solution generator. This setup effectively enables structured exploration, decouples learning signals of abstraction proposal and solution generation, and improves generalization to harder problems. We also show that allocating more test-time compute to generating abstractions is more beneficial for performance than generating more solutions at large test budgets, illustrating the role of abstractions in guiding meaningful exploration.</p> - https://arxiv.org/abs/2510.02263 - Thu, 02 Oct 2025 17:44:23 +0000 - - - Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective - https://arxiv.org/abs/2510.02272 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02272.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wen Yang, Junhong Wu, Chong Li, Chengqing Zong, Jiajun Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advancements in Reinforcement Post-Training (RPT) have significantly enhanced the capabilities of Large Reasoning Models (LRMs), sparking increased interest in the generalization of RL-based reasoning. While existing work has primarily focused on investigating its generalization across tasks or modalities, this study proposes a novel cross-linguistic perspective to investigate reasoning generalization. This raises a crucial question: Does the reasoning capability achieved from English RPT effectively transfer to other languages? We address this by systematically evaluating English-centric LRMs on multilingual reasoning benchmarks and introducing a metric to quantify cross-lingual transferability. Our findings reveal that cross-lingual transferability varies significantly across initial model, target language, and training paradigm. Through interventional studies, we find that models with stronger initial English capabilities tend to over-rely on English-specific patterns, leading to diminished cross-lingual generalization. To address this, we conduct a thorough parallel training study. Experimental results yield three key findings: First-Parallel Leap, a substantial leap in performance when transitioning from monolingual to just a single parallel language, and a predictable Parallel Scaling Law, revealing that cross-lingual reasoning transfer follows a power-law with the number of training parallel languages. Moreover, we identify the discrepancy between actual monolingual performance and the power-law prediction as Monolingual Generalization Gap, indicating that English-centric LRMs fail to fully generalize across languages. Our study challenges the assumption that LRM reasoning mirrors human cognition, providing critical insights for the development of more language-agnostic LRMs.</p> - https://arxiv.org/abs/2510.02272 - Thu, 02 Oct 2025 17:49:49 +0000 - - - Self-Forcing++: Towards Minute-Scale High-Quality Video Generation - https://arxiv.org/abs/2510.02283 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02283.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh</p><p><b>Upvotes:</b> 70</p><p><b>Summary:</b> Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive formulations for long video generation, typically by distilling from short-horizon bidirectional teachers. Nevertheless, given that teacher models cannot synthesize long videos, the extrapolation of student models beyond their training horizon often leads to pronounced quality degradation, arising from the compounding of errors within the continuous latent space. In this paper, we propose a simple yet effective approach to mitigate quality degradation in long-horizon video generation without requiring supervision from long-video teachers or retraining on long video datasets. Our approach centers on exploiting the rich knowledge of teacher models to provide guidance for the student model through sampled segments drawn from self-generated long videos. Our method maintains temporal consistency while scaling video length by up to 20x beyond teacher's capability, avoiding common issues such as over-exposure and error-accumulation without recomputing overlapping frames like previous methods. When scaling up the computation, our method shows the capability of generating videos up to 4 minutes and 15 seconds, equivalent to 99.9% of the maximum span supported by our base model's position embedding and more than 50x longer than that of our baseline model. Experiments on standard benchmarks and our proposed improved benchmark demonstrate that our approach substantially outperforms baseline methods in both fidelity and consistency. Our long-horizon videos demo can be found at https://self-forcing-plus-plus.github.io/</p> - https://arxiv.org/abs/2510.02283 - Thu, 02 Oct 2025 17:55:42 +0000 - - - Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks - https://arxiv.org/abs/2510.02286 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02286.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human experts or employ automated methods using pre-defined templates and human-curated attack data, with most focusing on single-turn attacks. However, these methods did not explore the vast space of possible multi-turn attacks, failing to consider novel attack trajectories that emerge from complex dialogue dynamics and strategic conversation planning. This gap is particularly critical given recent findings that LLMs exhibit significantly higher vulnerability to multi-turn attacks compared to single-turn attacks. We propose DialTree-RPO, an on-policy reinforcement learning framework integrated with tree search that autonomously discovers diverse multi-turn attack strategies by treating the dialogue as a sequential decision-making problem, enabling systematic exploration without manually curated data. Through extensive experiments, our approach not only achieves more than 25.9% higher ASR across 10 target models compared to previous state-of-the-art approaches, but also effectively uncovers new attack strategies by learning optimal dialogue policies that maximize attack success across multiple turns.</p> - https://arxiv.org/abs/2510.02286 - Thu, 02 Oct 2025 17:57:05 +0000 - - - F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data - https://arxiv.org/abs/2510.02294 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02294.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.</p> - https://arxiv.org/abs/2510.02294 - Thu, 02 Oct 2025 17:58:49 +0000 - - - VideoNSA: Native Sparse Attention Scales Video Understanding - https://arxiv.org/abs/2510.02295 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enxin Song, Wenhao Chai, Shusheng Yang, Ethan Armand, Xiaojun Shan, Haiyang Xu, Jianwen Xie, Zhuowen Tu</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time scales. To address this, we adapt Native Sparse Attention (NSA) to video-language models. Our method, VideoNSA, adapts Qwen2.5-VL through end-to-end training on a 216K video instruction dataset. We employ a hardware-aware hybrid approach to attention, preserving dense attention for text, while employing NSA for video. Compared to token-compression and training-free sparse baselines, VideoNSA achieves improved performance on long-video understanding, temporal reasoning, and spatial benchmarks. Further ablation analysis reveals four key findings: (1) reliable scaling to 128K tokens; (2) an optimal global-local attention allocation at a fixed budget; (3) task-dependent branch usage patterns; and (4) the learnable combined sparse attention help induce dynamic attention sinks.</p> - https://arxiv.org/abs/2510.02295 - Thu, 02 Oct 2025 17:58:54 +0000 - - - Interactive Training: Feedback-Driven Neural Network Optimization - https://arxiv.org/abs/2510.02297 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02297.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wentao Zhang, Yang Young Lu, Yuntian Deng</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an open-source framework that enables real-time, feedback-driven intervention during neural network training by human experts or automated AI agents. At its core, Interactive Training uses a control server to mediate communication between users or agents and the ongoing training process, allowing users to dynamically adjust optimizer hyperparameters, training data, and model checkpoints. Through three case studies, we demonstrate that Interactive Training achieves superior training stability, reduced sensitivity to initial hyperparameters, and improved adaptability to evolving user needs, paving the way toward a future training paradigm where AI agents autonomously monitor training logs, proactively resolve instabilities, and optimize training dynamics.</p> - https://arxiv.org/abs/2510.02297 - Thu, 02 Oct 2025 17:59:00 +0000 - - - Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation - https://arxiv.org/abs/2510.02306 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02306.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Raphael Tang, Crystina Zhang, Wenyan Li, Carmen Lai, Pontus Stenetorp, Yao Lu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an adjustment to the ratings of both models. The prevailing approach for modeling these rating dynamics is to view battles as two-player game matches, as in chess, and apply the Elo rating system and its derivatives. In this paper, we critically examine this paradigm. Specifically, we question whether a draw genuinely means that the two models are equal and hence whether their ratings should be equalized. Instead, we conjecture that draws are more indicative of query difficulty: if the query is too easy, then both models are more likely to succeed equally. On three real-world arena datasets, we show that ignoring rating updates for draws yields a 1-3% relative increase in battle outcome prediction accuracy (which includes draws) for all four rating systems studied. Further analyses suggest that draws occur more for queries rated as very easy and those as highly objective, with risk ratios of 1.37 and 1.35, respectively. We recommend future rating systems to reconsider existing draw semantics and to account for query properties in rating updates.</p> - https://arxiv.org/abs/2510.02306 - Thu, 02 Oct 2025 17:59:41 +0000 - - - StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions - https://arxiv.org/abs/2510.02314 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02314.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> 3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We analyze 3DGS robustness against image-level poisoning attacks and propose a novel density-guided poisoning method. Our method strategically injects Gaussian points into low-density regions identified via Kernel Density Estimation (KDE), embedding viewpoint-dependent illusory objects clearly visible from poisoned views while minimally affecting innocent views. Additionally, we introduce an adaptive noise strategy to disrupt multi-view consistency, further enhancing attack effectiveness. We propose a KDE-based evaluation protocol to assess attack difficulty systematically, enabling objective benchmarking for future research. Extensive experiments demonstrate our method's superior performance compared to state-of-the-art techniques. Project page: https://hentci.github.io/stealthattack/</p> - https://arxiv.org/abs/2510.02314 - Thu, 02 Oct 2025 17:59:57 +0000 - - - Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity - https://arxiv.org/abs/2510.02315 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02315.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Eric Tillmann Bill, Enis Simsar, Thomas Hofmann</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-subject descriptions, often showing attribute leakage, identity entanglement, and subject omissions. We introduce the first theoretical framework with a principled, optimizable objective for steering sampling dynamics toward multi-subject fidelity. Viewing flow matching (FM) through stochastic optimal control (SOC), we formulate subject disentanglement as control over a trained FM sampler. This yields two architecture-agnostic algorithms: (i) a training-free test-time controller that perturbs the base velocity with a single-pass update, and (ii) Adjoint Matching, a lightweight fine-tuning rule that regresses a control network to a backward adjoint signal while preserving base-model capabilities. The same formulation unifies prior attention heuristics, extends to diffusion models via a flow-diffusion correspondence, and provides the first fine-tuning route explicitly designed for multi-subject fidelity. Empirically, on Stable Diffusion 3.5, FLUX, and Stable Diffusion XL, both algorithms consistently improve multi-subject alignment while maintaining base-model style. Test-time control runs efficiently on commodity GPUs, and fine-tuned controllers trained on limited prompts generalize to unseen ones. We further highlight FOCUS (Flow Optimal Control for Unentangled Subjects), which achieves state-of-the-art multi-subject fidelity across models.</p> - https://arxiv.org/abs/2510.02315 - Thu, 02 Oct 2025 17:59:58 +0000 + LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models + https://arxiv.org/abs/2510.03232 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03232.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ci-Siang Lin, Min-Hung Chen, Yu-Yang Sheng, Yu-Chiang Frank Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and expensive. We introduce LEAML, a label-efficient adaptation framework that leverages both scarce labeled VQA samples and abundant unlabeled images. Our approach generates domain-relevant pseudo question-answer pairs for unlabeled data using a QA generator regularized by caption distillation. Importantly, we selectively update only those neurons most relevant to question-answering, enabling the QA Generator to efficiently acquire domain-specific knowledge during distillation. Experiments on gastrointestinal endoscopy and sports VQA demonstrate that LEAML consistently outperforms standard fine-tuning under minimal supervision, highlighting the effectiveness of our proposed LEAML framework.</p> + https://arxiv.org/abs/2510.03232 + Fri, 03 Oct 2025 17:59:56 +0000