bot: update RSS feed
This commit is contained in:
github-actions[bot]
568
feed.xml
568
feed.xml
@@ -7,356 +7,328 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Mon, 13 Oct 2025 00:02:41 +0000</lastBuildDate>
|
||||
<lastBuildDate>Tue, 14 Oct 2025 00:02:33 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.03259</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoonjeon Kim, Doohyuk Jang, Eunho Yang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true rollouts and predicted meta information. We posit that aligning meta-prediction with true rollouts will lead to significant performance gains. To verify this hypothesis, we design a training pipeline that boosts Meta-Awareness via Self-Alignment (MASA), and prove that enhanced meta-awareness directly translates to improved accuracy. Unlike existing meta-cognitive reasoning models, our method does not require external training sources but leverages self-generated signals to train meta-awareness. Moreover, our method enables efficient training by i) filtering out zero-variance prompts that are either trivial or unsolvable and ii) cutting off lengthy rollouts when they are unlikely to lead to correct answers. The results are inspiring: our strategy yields significant improvements in both accuracy and training efficiency on in-domain tasks and shows strong generalization to out-of-domain benchmarks. More specifically, our method can speed up GRPO training by over 1.28x to reach the same performance, and achieve a 19.3% gain in accuracy on AIME25, and a 6.2 % average gain over six mathematics benchmarks. Training with meta-cognitive guidance enhances out-of-domain generalization, giving a 3.87 % boost on GPQA-Diamond and a 2.08 % overall accuracy gain across 13 benchmarks spanning logical, scientific, and coding domains.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03259</guid>
|
||||
<pubDate>Fri, 26 Sep 2025 14:05:48 +0000</pubDate>
|
||||
<title>Instant4D: 4D Gaussian Splatting in Minutes</title>
|
||||
<link>https://arxiv.org/abs/2510.01119</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.01119.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhanpeng Luo, Haoxi Ran, Li Lu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid pruning to optimize scene representation. Our design significantly reduces redundancy while maintaining geometric integrity, cutting model size to under 10% of its original footprint. To handle temporal dynamics efficiently, we introduce a streamlined 4D Gaussian representation, achieving a 30x speed-up and reducing training time to within two minutes, while maintaining competitive performance across several benchmarks. Our method reconstruct a single video within 10 minutes on the Dycheck dataset or for a typical 200-frame video. We further apply our model to in-the-wild videos, showcasing its generalizability. Our project website is published at https://instant4d.github.io/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.01119</guid>
|
||||
<pubDate>Wed, 01 Oct 2025 17:07:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Beyond Outliers: A Study of Optimizers Under Quantization</title>
|
||||
<link>https://arxiv.org/abs/2509.23500</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23500.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Georgios Vlassis, Saleh Ashkboos, Alexandra Volkova, Torsten Hoefler, Dan Alistarh</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As new optimizers gain traction and model quantization becomes standard for efficient deployment, a key question arises: how does the choice of optimizer affect model performance in the presence of quantization? Despite progress in both areas, systematic evidence on optimizer-quantization interactions remains limited. To fill this gap, we study the impact of optimizer choice on model robustness under quantization, considering both post-training quantization (PTQ), and quantization-aware training (QAT). We first train full-precision models, ranging from 50M to 1.5B parameters, with six optimizers, to explore the hyperparameter landscape, and establish well-tuned baselines. We then apply PTQ to evaluate how model performance degrades when trained with different optimizers. We find that outlier-related metrics, such as the max-to-mean ratio (MMR) and Kurtosis, fail to predict the PTQ performance across different optimizers. We show analytically that this is due to the MMR capturing only isolated layer errors, while ignoring how quantization errors accumulate and propagate through the network. To study the QAT degradation, we train quantized models from scratch and compare them to our original-precision baselines. We find that optimizers performing well in the original pretraining setup may not remain optimal under QAT, and that models trained with Shampoo show the lowest accuracy degradation. Finally, we derive scaling laws for quantization-aware training under different optimizers, showing that Shampoo achieves the highest parameter efficiency of all tested optimizers.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.23500</guid>
|
||||
<pubDate>Sat, 27 Sep 2025 21:15:22 +0000</pubDate>
|
||||
<title>One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework</title>
|
||||
<link>https://arxiv.org/abs/2510.02898</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02898.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present , a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense, region-set, and a newly introduced trace captioning task, highlighting the effectiveness of patch-wise semantic representations for scalable caption generation. Project page at https://paciosoft.com/Patch-ioner/ .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.02898</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 11:05:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2509.23768</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.23768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Yang, Jiaxuan Lu, Haiyuan Wan, Junchi Yu, Feiwei Qin</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> The chemical reaction recommendation is to select proper reaction condition parameters for chemical reactions, which is pivotal to accelerating chemical science. With the rapid development of large language models (LLMs), there is growing interest in leveraging their reasoning and planning capabilities for reaction condition recommendation. Despite their success, existing methods rarely explain the rationale behind the recommended reaction conditions, limiting their utility in high-stakes scientific workflows. In this work, we propose ChemMAS, a multi-agent system that reframes condition prediction as an evidence-based reasoning task. ChemMAS decomposes the task into mechanistic grounding, multi-channel recall, constraint-aware agentic debate, and rationale aggregation. Each decision is backed by interpretable justifications grounded in chemical knowledge and retrieved precedents. Experiments show that ChemMAS achieves 20-35% gains over domain-specific baselines and outperforms general-purpose LLMs by 10-15% in Top-1 accuracy, while offering falsifiable, human-trustable rationales, which establishes a new paradigm for explainable AI in scientific discovery.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.23768</guid>
|
||||
<pubDate>Sun, 28 Sep 2025 09:34:35 +0000</pubDate>
|
||||
<title>TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling</title>
|
||||
<link>https://arxiv.org/abs/2510.04533</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04533.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunmin Cho, Donghoon Ahn, Susung Hong, Jee Eun Kim, Seungryong Kim, Kyong Hwan Jin</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Recent diffusion models achieve the state-of-the-art performance in image generation, but often suffer from semantic inconsistencies or hallucinations. While various inference-time guidance methods can enhance generation, they often operate indirectly by relying on external signals or architectural modifications, which introduces additional computational overhead. In this paper, we propose Tangential Amplifying Guidance (TAG), a more efficient and direct guidance method that operates solely on trajectory signals without modifying the underlying diffusion model. TAG leverages an intermediate sample as a projection basis and amplifies the tangential components of the estimated scores with respect to this basis to correct the sampling trajectory. We formalize this guidance process by leveraging a first-order Taylor expansion, which demonstrates that amplifying the tangential component steers the state toward higher-probability regions, thereby reducing inconsistencies and enhancing sample quality. TAG is a plug-and-play, architecture-agnostic module that improves diffusion sampling fidelity with minimal computational addition, offering a new perspective on diffusion guidance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04533</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 06:53:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MemMamba: Rethinking Memory Patterns in State Space Model</title>
|
||||
<link>https://arxiv.org/abs/2510.03279</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03279.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Youjin Wang, Yangjingyi Chen, Jiahao Yan, Jiaxuan Lu, Xiao Sun</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory. Recurrent neural networks suffer from gradient vanishing and explosion, making them hard to scale. Transformers can model global dependencies but are constrained by quadratic complexity. Recently, selective state-space models such as Mamba have demonstrated high efficiency with O(n) time and O(1) recurrent inference, yet their long-range memory decays exponentially. In this work, we conduct mathematical derivations and information-theoretic analysis to systematically uncover the memory decay mechanism of Mamba, answering a fundamental question: what is the nature of Mamba's long-range memory and how does it retain information? To quantify key information loss, we further introduce horizontal-vertical memory fidelity metrics that capture degradation both within and across layers. Inspired by how humans distill and retain salient information when reading long documents, we propose MemMamba, a novel architectural framework that integrates state summarization mechanism together with cross-layer and cross-token attention, which alleviates long-range forgetting while preserving linear complexity. MemMamba achieves significant improvements over existing Mamba variants and Transformers on long-sequence benchmarks such as PG19 and Passkey Retrieval, while delivering a 48% speedup in inference efficiency. Both theoretical analysis and empirical results demonstrate that MemMamba achieves a breakthrough in the complexity-memory trade-off, offering a new paradigm for ultra-long sequence modeling.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03279</guid>
|
||||
<pubDate>Sun, 28 Sep 2025 14:40:58 +0000</pubDate>
|
||||
<title>Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction</title>
|
||||
<link>https://arxiv.org/abs/2510.04759</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.04759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chi Yan, Dan Xu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The 3D occupancy prediction task has witnessed remarkable progress in recent years, playing a crucial role in vision-based autonomous driving systems. While traditional methods are limited to fixed semantic categories, recent approaches have moved towards predicting text-aligned features to enable open-vocabulary text queries in real-world scenes. However, there exists a trade-off in text-aligned scene modeling: sparse Gaussian representation struggles to capture small objects in the scene, while dense representation incurs significant computational overhead. To address these limitations, we present PG-Occ, an innovative Progressive Gaussian Transformer Framework that enables open-vocabulary 3D occupancy prediction. Our framework employs progressive online densification, a feed-forward strategy that gradually enhances the 3D Gaussian representation to capture fine-grained scene details. By iteratively enhancing the representation, the framework achieves increasingly precise and detailed scene understanding. Another key contribution is the introduction of an anisotropy-aware sampling strategy with spatio-temporal fusion, which adaptively assigns receptive fields to Gaussians at different scales and stages, enabling more effective feature aggregation and richer scene information capture. Through extensive evaluations, we demonstrate that PG-Occ achieves state-of-the-art performance with a relative 14.3% mIoU improvement over the previous best performing method. Code and pretrained models will be released upon publication on our project page: https://yanchi-3dv.github.io/PG-Occ</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.04759</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 12:36:07 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Fidelity-Aware Data Composition for Robust Robot Generalization</title>
|
||||
<link>https://arxiv.org/abs/2509.24797</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24797.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zizhao Tong, Di Chen, Sicheng Hu, Hongwei Fan, Liliang Chen, Guanghui Ren, Hao Tang, Hao Dong, Ling Shao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning, which impairs their out-of-distribution (OOD) generalization. While generative data augmentation is a common approach to introduce diversity, it presents a subtle challenge: data composition. Naively mixing real and synthetic data can corrupt the learning signal, as this process often prioritizes visual diversity at the expense of information fidelity. This paper suggests that robust generalization depends on principled, fidelity-aware data composition. We introduce Coherent Information Fidelity Tuning (CIFT), a framework that treats data composition as an optimization problem. CIFT uses a practical proxy for Information Fidelity based on the feature-space geometry of a dataset. This enables the identification of a phase transition, termed the Decoherence Point, where training stability degrades. The framework includes a generative engine, Multi-View Video Augmentation (MVAug), to synthesize a causally disentangled data spectrum for this tuning process. Applying CIFT to policy architectures such as pi_0 and Diffusion Policy improves OOD success rates by over 54\%. These results indicate that fidelity-aware composition, beyond data synthesis alone, is an important component for developing robust, general-purpose robots.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.24797</guid>
|
||||
<pubDate>Mon, 29 Sep 2025 13:48:36 +0000</pubDate>
|
||||
<title>Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization</title>
|
||||
<link>https://arxiv.org/abs/2510.06274</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06274.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Mahdi Samiei Paqaleh, Arash Marioriyad, Arman Tahmasebi-Zadeh, Mohamadreza Fereydooni, Mahdi Ghaznavai, Mahdieh Soleymani Baghshah</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Recent progress has pushed AI frontiers from pattern recognition tasks toward problems that require step by step, System2 style reasoning, especially with large language models. Yet, unlike learning, where generalization and out of distribution (OoD) evaluation concepts are well formalized, there is no clear, consistent definition or metric for reasoning ability. We propose Complexity Out of Distribution (Complexity OoD) generalization as a framework and problem setting to define and measure reasoning. A model exhibits Complexity OoD generalization when it maintains performance on test instances whose minimal required solution complexity, either representational (richer solution structure) or computational (more reasoning steps/program length), exceeds that of all training examples. We formalize complexity via solution description Kolmogorov complexity and operational proxies (e.g., object/relation counts; reasoning step counts), clarifying how Complexity OoD differs from length and compositional OoD. This lens unifies learning and reasoning: many cases solvable with System1 like processing at low complexity become System2 like under complexity pressure, while System2 can be viewed as generalization over solution structures. We translate this perspective into practice with recommendations for operationalizing Complexity OoD across the stack: incorporating complexity into benchmark and evaluation metric design, rethinking supervision to target solution traces, seeking and designing inductive biases for Complexity OoD generalization, addressing learning to reason spillovers such as spurious shortcuts, semantic robustness, catastrophic forgetting, and step wise calibration. Because Complexity OoD cannot be solved by scaling data alone, progress toward robust reasoning will require architectures and training regimes that explicitly model and allocate computation with respect to complexity.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06274</guid>
|
||||
<pubDate>Mon, 06 Oct 2025 13:08:31 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections</title>
|
||||
<link>https://arxiv.org/abs/2509.24817</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.24817.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyu Cai, Ziyang Li, Xiaoben Li, Boqian Li, Zeyu Wang, Zhenyu Zhang, Yuliang Xiu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We present UP2You, the first tuning-free solution for reconstructing high-fidelity 3D clothed portraits from extremely unconstrained in-the-wild 2D photos. Unlike previous approaches that require "clean" inputs (e.g., full-body images with minimal occlusions, or well-calibrated cross-view captures), UP2You directly processes raw, unstructured photographs, which may vary significantly in pose, viewpoint, cropping, and occlusion. Instead of compressing data into tokens for slow online text-to-3D optimization, we introduce a data rectifier paradigm that efficiently converts unconstrained inputs into clean, orthogonal multi-view images in a single forward pass within seconds, simplifying the 3D reconstruction. Central to UP2You is a pose-correlated feature aggregation module (PCFA), that selectively fuses information from multiple reference images w.r.t. target poses, enabling better identity preservation and nearly constant memory footprint, with more observations. We also introduce a perceiver-based multi-reference shape predictor, removing the need for pre-captured body templates. Extensive experiments on 4D-Dress, PuzzleIOI, and in-the-wild captures demonstrate that UP2You consistently surpasses previous methods in both geometric accuracy (Chamfer-15%, P2S-18% on PuzzleIOI) and texture fidelity (PSNR-21%, LPIPS-46% on 4D-Dress). UP2You is efficient (1.5 minutes per person), and versatile (supports arbitrary pose control, and training-free multi-garment 3D virtual try-on), making it practical for real-world scenarios where humans are casually captured. Both models and code will be released to facilitate future research on this underexplored task. Project Page: https://zcai0612.github.io/UP2You</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.24817</guid>
|
||||
<pubDate>Mon, 29 Sep 2025 14:06:00 +0000</pubDate>
|
||||
<title>ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization</title>
|
||||
<link>https://arxiv.org/abs/2510.05528</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lawrence Liu, Alexander Liu, Mengdi Wang, Tuo Zhao, Lin F. Yang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hardware acceleration, existing methods often incur substantial performance degradation. To bridge this gap, we introduce ARMOR: (Adaptive Representation with Matrix-factORization), a novel one-shot post-training pruning algorithm. Instead of directly pruning weights, ARMOR factorizes each weight matrix into a 2:4 sparse core wrapped by two low-overhead, block diagonal matrices. These wrappers act as efficient pre and post-transformation error correctors, offering greater flexibility to preserve model quality compared to conventional 2:4 pruning techniques. The sparse core and block diagonal wrappers are chosen through a block coordinate descent algorithm that minimizes a layer-wise proxy loss. We theoretically prove this optimization is guaranteed to converge to a solution with a proxy loss less than or equal to state-of-the-art pruning algorithms. Experiments on Llama (Touvron et al., 2023; Dubey et al., 2024) and Qwen (Yang et al., 2025) model families demonstrate that ARMOR consistently and significantly outperforms state-of-the-art 2:4 pruning methods across a wide range of downstream tasks and perplexity evaluations. ARMOR achieves this superior performance while retaining the inference speedups and substantial memory usage reductions of 2:4 pruning, establishing a more effective trade-off between model compression and task accuracy</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05528</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 02:39:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction</title>
|
||||
<link>https://arxiv.org/abs/2509.26633</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2509.26633.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lujie Yang, Xiaoyu Huang, Zhen Wu, Angjoo Kanazawa, Pieter Abbeel, Carmelo Sferrazza, C. Karen Liu, Rocky Duan, Guanya Shi</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive locomotion and loco-manipulation. To address this, we introduce OmniRetarget, an interaction-preserving data generation engine based on an interaction mesh that explicitly models and preserves the crucial spatial and contact relationships between an agent, the terrain, and manipulated objects. By minimizing the Laplacian deformation between the human and robot meshes while enforcing kinematic constraints, OmniRetarget generates kinematically feasible trajectories. Moreover, preserving task-relevant interactions enables efficient data augmentation, from a single demonstration to different robot embodiments, terrains, and object configurations. We comprehensively evaluate OmniRetarget by retargeting motions from OMOMO, LAFAN1, and our in-house MoCap datasets, generating over 8-hour trajectories that achieve better kinematic constraint satisfaction and contact preservation than widely used baselines. Such high-quality data enables proprioceptive RL policies to successfully execute long-horizon (up to 30 seconds) parkour and loco-manipulation skills on a Unitree G1 humanoid, trained with only 5 reward terms and simple domain randomization shared by all tasks, without any learning curriculum.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2509.26633</guid>
|
||||
<pubDate>Tue, 30 Sep 2025 17:59:02 +0000</pubDate>
|
||||
<title>A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks</title>
|
||||
<link>https://arxiv.org/abs/2510.05608</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05608.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuzheng Si, Haozhe Zhao, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Agents based on large language models (LLMs) struggle with brainless trial-and-error and generating hallucinatory actions due to a lack of global planning in long-horizon tasks. In this paper, we introduce a plan-and-execute framework and propose EAGLET, an efficient and effective planner training method to enhance the executor agent's planning abilities without human effort. Specifically, we train a plug-and-play global planner through a two-step process: we first synthesize high-quality plans from an advanced LLM using our proposed homologous consensus filtering strategy, and apply fine-tuning as a cold start. Moreover, we further improve the planner with a rule-based reinforcement learning stage using a novel executor capability gain reward, ensuring it can handle task instructions of varying difficulty. Experiments on three long-horizon agent tasks show that executor agents equipped with our planner outperform existing methods, achieving new state-of-the-art performance. Meanwhile, EAGLET reduces training costs by 8x compared to RL-based baselines, and it does not require manual effort or extra training data, offering an efficient and effective solution.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05608</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 06:10:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.02590</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02590.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmed Hendawy, Henrik Metternich, Théo Vincent, Mahdi Kallel, Jan Peters, Carlo D'Eramo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise solution that preserves stability at the cost of slowly moving targets, thus delaying learning. Conversely, using the online network as a bootstrapped target is intuitively appealing, albeit well-known to lead to unstable learning. In this work, we aim to obtain the best out of both worlds by introducing a novel update rule that computes the target using the MINimum estimate between the Target and Online network, giving rise to our method, MINTO. Through this simple, yet effective modification, we show that MINTO enables faster and stable value function learning, by mitigating the potential overestimation bias of using the online network for bootstrapping. Notably, MINTO can be seamlessly integrated into a wide range of value-based and actor-critic algorithms with a negligible cost. We evaluate MINTO extensively across diverse benchmarks, spanning online and offline RL, as well as discrete and continuous action spaces. Across all benchmarks, MINTO consistently improves performance, demonstrating its broad applicability and effectiveness.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.02590</guid>
|
||||
<pubDate>Thu, 02 Oct 2025 21:48:01 +0000</pubDate>
|
||||
<title>D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI</title>
|
||||
<link>https://arxiv.org/abs/2510.05684</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.05684.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Suwhan Choi, Jaeyoon Jung, Haebin Seong, Minchan Kim, Minyeong Kim, Yongjun Cho, Yoonshik Kim, Yubeen Park, Youngjae Yu, Yunsung Lee</p><p><b>Upvotes:</b> 101</p><p><b>Summary:</b> Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming -- offer a compelling alternative: they provide rich sensorimotor interactions at scale while maintaining the structured observation-action coupling essential for embodied learning. We present D2E (Desktop to Embodied AI), a framework that demonstrates desktop interactions can serve as an effective pretraining substrate for robotics embodied AI tasks. Unlike prior work that remained domain-specific (e.g., VPT for Minecraft) or kept data proprietary (e.g., SIMA), D2E establishes a complete pipeline from scalable desktop data collection to verified transfer in embodied domains. Our framework comprises three components: (1) the OWA Toolkit that unifies diverse desktop interactions into a standardized format with 152x compression, (2) the Generalist-IDM that achieves strong zero-shot generalization across unseen games through timestamp-based event prediction, enabling internet-scale pseudo-labeling, and (3) VAPT that transfers desktop-pretrained representations to physical manipulation and navigation. Using 1.3K+ hours of data (259 hours of human demonstrations, and 1K+ hours of pseudo-labeled gameplay), we achieve a total of 96.6% success rate on LIBERO manipulation and 83.3% on CANVAS navigation benchmarks. This validates that sensorimotor primitives in digital interactions exhibit sufficient invariance to transfer meaningfully to physical embodied tasks, establishing desktop pretraining as a practical paradigm for robotics. We will make all our work public, including the OWA toolkit, datasets of human-collected and pseudo-labeled, and VAPT-trained models available at https://worv-ai.github.io/d2e/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.05684</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 08:40:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Towards Scalable and Consistent 3D Editing</title>
|
||||
<link>https://arxiv.org/abs/2510.02994</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.02994.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruihao Xia, Yang Tang, Pan Zhou</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> 3D editing - the task of locally modifying the geometry or appearance of a 3D asset - has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need for cross-view consistency, structural fidelity, and fine-grained controllability. Existing approaches are often slow, prone to geometric distortions, or dependent on manual and accurate 3D masks that are error-prone and impractical. To address these challenges, we advance both the data and model fronts. On the data side, we introduce 3DEditVerse, the largest paired 3D editing benchmark to date, comprising 116,309 high-quality training pairs and 1,500 curated test pairs. Built through complementary pipelines of pose-driven geometric edits and foundation model-guided appearance edits, 3DEditVerse ensures edit locality, multi-view consistency, and semantic alignment. On the model side, we propose 3DEditFormer, a 3D-structure-preserving conditional transformer. By enhancing image-to-3D generation with dual-guidance attention and time-adaptive gating, 3DEditFormer disentangles editable regions from preserved structure, enabling precise and consistent edits without requiring auxiliary 3D masks. Extensive experiments demonstrate that our framework outperforms state-of-the-art baselines both quantitatively and qualitatively, establishing a new standard for practical and scalable 3D editing. Dataset and code will be released. Project: https://www.lv-lab.org/3DEditFormer/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.02994</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 13:34:55 +0000</pubDate>
|
||||
<title>Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels</title>
|
||||
<link>https://arxiv.org/abs/2510.06499</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhepeng Cen, Haolin Chen, Shiyu Wang, Zuxin Liu, Zhiwei Liu, Ding Zhao, Silvio Savarese, Caiming Xiong, Huan Wang, Weiran Yao</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more data-efficient solution capable of bridging this gap, yet its application has been constrained by a critical data bottleneck: existing RL datasets are orders of magnitude smaller and less diverse than web-scale pre-training corpora. To address this, we introduce the Webscale-RL pipeline, a scalable data engine that systematically converts large-scale pre-training documents into millions of diverse, verifiable question-answer pairs for RL. Using this pipeline, we construct the Webscale-RL dataset, containing 1.2 million examples across more than 9 domains. Our experiments show that the model trained on this dataset significantly outperforms continual pretraining and strong data refinement baselines across a suite of benchmarks. Notably, RL training with our dataset proves substantially more efficient, achieving the performance of continual pre-training with up to 100times fewer tokens. Our work presents a viable path toward scaling RL to pre-training levels, enabling more capable and efficient language models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06499</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 22:30:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction</title>
|
||||
<link>https://arxiv.org/abs/2510.03117</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03117.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaisi Guan, Xihua Wang, Zhengfeng Lai, Xin Cheng, Peng Zhang, XiaoJiang Liu, Ruihua Song, Meng Cao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite progress in joint audio-video training, two critical challenges still remain unaddressed: (1) a single, shared text caption where the text for video is equal to the text for audio often creates modal interference, confusing the pretrained backbones, and (2) the optimal mechanism for cross-modal feature interaction remains unclear. To address these challenges, we first propose the Hierarchical Visual-Grounded Captioning (HVGC) framework that generates pairs of disentangled captions, a video caption, and an audio caption, eliminating interference at the conditioning stage. Based on HVGC, we further introduce BridgeDiT, a novel dual-tower diffusion transformer, which employs a Dual CrossAttention (DCA) mechanism that acts as a robust ``bridge" to enable a symmetric, bidirectional exchange of information, achieving both semantic and temporal synchronization. Extensive experiments on three benchmark datasets, supported by human evaluations, demonstrate that our method achieves state-of-the-art results on most metrics. Comprehensive ablation studies further validate the effectiveness of our contributions, offering key insights for the future T2SV task. All the codes and checkpoints will be publicly released.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03117</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 15:43:56 +0000</pubDate>
|
||||
<title>ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL</title>
|
||||
<link>https://arxiv.org/abs/2510.07151</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07151.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose ELMUR (External Layer Memory with Update/Rewrite), a transformer architecture with structured external memory. Each layer maintains memory embeddings, interacts with them via bidirectional cross-attention, and updates them through an Least Recently Used (LRU) memory module using replacement or convex blending. ELMUR extends effective horizons up to 100,000 times beyond the attention window and achieves a 100% success rate on a synthetic T-Maze task with corridors up to one million steps. In POPGym, it outperforms baselines on more than half of the tasks. On MIKASA-Robo sparse-reward manipulation tasks with visual observations, it nearly doubles the performance of strong baselines. These results demonstrate that structured, layer-local external memory offers a simple and scalable approach to decision making under partial observability.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07151</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 15:50:34 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward</title>
|
||||
<link>https://arxiv.org/abs/2510.03222</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where performance plateaus as policy entropy collapses, signaling a loss of exploration. Previous methods typically address this by maintaining high policy entropy, yet the precise mechanisms that govern meaningful exploration have remained underexplored. Our analysis suggests that an unselective focus on entropy risks amplifying irrelevant tokens and destabilizing training. This paper investigates the exploration dynamics within RLVR and identifies a key issue: the gradual elimination of valuable low-probability exploratory tokens, which we term \textit{reasoning sparks}. We find that while abundant in pre-trained models, these sparks are systematically extinguished during RLVR due to over-penalization, leading to a degeneracy in exploration. To address this, we introduce Low-probability Regularization (Lp-Reg). Its core mechanism regularizes the policy towards a heuristic proxy distribution. This proxy is constructed by filtering out presumed noise tokens and re-normalizing the distribution over the remaining candidates. The result is a less-noisy proxy where the probability of reasoning sparks is amplified, which then serves as a soft regularization target to shield these valuable tokens from elimination via KL divergence. Experiments show that Lp-Reg enables stable on-policy training for around 1,000 steps, a regime where baseline entropy-control methods collapse. This sustained exploration leads to state-of-the-art performance, achieving a 60.17% average accuracy on five math benchmarks, an improvement of 2.66% over prior methods. Code is available at https://github.com/CarlanLark/Lp-Reg.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03222</guid>
|
||||
<pubDate>Fri, 03 Oct 2025 17:56:13 +0000</pubDate>
|
||||
<title>Temporal Prompting Matters: Rethinking Referring Video Object Segmentation</title>
|
||||
<link>https://arxiv.org/abs/2510.07319</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07319.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ci-Siang Lin, Min-Hung Chen, I-Jieh Liu, Chien-Yi Wang, Sifei Liu, Yu-Chiang Frank Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence in the video. Most existing methods require end-to-end training with dense mask annotations, which could be computation-consuming and less scalable. In this work, we rethink the RVOS problem and aim to investigate the key to this task. Based on existing foundation segmentation models, we decompose the RVOS task into referring, video, and segmentation factors, and propose a Temporal Prompt Generation and Selection (Tenet) framework to address the referring and video factors while leaving the segmentation problem to foundation models. To efficiently adapt image-based foundation segmentation models to referring video object segmentation, we leverage off-the-shelf object detectors and trackers to produce temporal prompts associated with the referring sentence. While high-quality temporal prompts could be produced, they can not be easily identified from confidence scores. To tackle this issue, we propose Prompt Preference Learning to evaluate the quality of the produced temporal prompts. By taking such prompts to instruct image-based foundation segmentation models, we would be able to produce high-quality masks for the referred object, enabling efficient model adaptation to referring video object segmentation. Experiments on RVOS benchmarks demonstrate the effectiveness of the Tenet framework.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07319</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:59:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG</title>
|
||||
<link>https://arxiv.org/abs/2510.03663</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.03663.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Peng, Cab Qin, Zeyuan Chen, Ran Xu, Caiming Xiong, Chien-Sheng Wu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Multimodal retrieval-augmented generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented, focusing on either text or images in isolation or on simplified multimodal setups that fail to capture document-centric multimodal use cases. In this paper, we introduce UniDoc-Bench, the first large-scale, realistic benchmark for MM-RAG built from 70k real-world PDF pages across eight domains. Our pipeline extracts and links evidence from text, tables, and figures, then generates 1,600 multimodal QA pairs spanning factual retrieval, comparison, summarization, and logical reasoning queries. To ensure reliability, 20% of QA pairs are validated by multiple annotators and expert adjudication. UniDoc-Bench supports apples-to-apples comparison across four paradigms: (1) text-only, (2) image-only, (3) multimodal text-image fusion, and (4) multimodal joint retrieval -- under a unified protocol with standardized candidate pools, prompts, and evaluation metrics. Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval, indicating that neither text nor images alone are sufficient and that current multimodal embeddings remain inadequate. Beyond benchmarking, our analysis reveals when and how visual context complements textual evidence, uncovers systematic failure modes, and offers actionable guidance for developing more robust MM-RAG pipelines.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.03663</guid>
|
||||
<pubDate>Sat, 04 Oct 2025 04:30:13 +0000</pubDate>
|
||||
<title>MONKEY: Masking ON KEY-Value Activation Adapter for Personalization</title>
|
||||
<link>https://arxiv.org/abs/2510.07656</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07656.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> James Baker</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Personalizing diffusion models allows users to generate new images that incorporate a given subject, allowing more control than a text prompt. These models often suffer somewhat when they end up just recreating the subject image, and ignoring the text prompt. We observe that one popular method for personalization, the IP-Adapter automatically generates masks that we definitively segment the subject from the background during inference. We propose to use this automatically generated mask on a second pass to mask the image tokens, thus restricting them to the subject, not the background, allowing the text prompt to attend to the rest of the image. For text prompts describing locations and places, this produces images that accurately depict the subject while definitively matching the prompt. We compare our method to a few other test time personalization methods, and find our method displays high prompt and source image alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07656</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 01:20:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models</title>
|
||||
<link>https://arxiv.org/abs/2510.06209</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06209.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiahao Wang, Zhenpei Yang, Yijing Bai, Yingwei Li, Yuliang Zou, Bo Sun, Abhijit Kundu, Jose Lezama, Luna Yue Huang, Zehao Zhu, Jyh-Jing Hwang, Dragomir Anguelov, Mingxing Tan, Chiyu Max Jiang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in generative models have sparked exciting new possibilities in the field of autonomous vehicles. Specifically, video generation models are now being explored as controllable virtual testing environments. Simultaneously, end-to-end (E2E) driving models have emerged as a streamlined alternative to conventional modular autonomous driving systems, gaining popularity for their simplicity and scalability. However, the application of these techniques to simulation and planning raises important questions. First, while video generation models can generate increasingly realistic videos, can these videos faithfully adhere to the specified conditions and be realistic enough for E2E autonomous planner evaluation? Second, given that data is crucial for understanding and controlling E2E planners, how can we gain deeper insights into their biases and improve their ability to generalize to out-of-distribution scenarios? In this work, we bridge the gap between the driving models and generative world models (Drive&Gen) to address these questions. We propose novel statistical measures leveraging E2E drivers to evaluate the realism of generated videos. By exploiting the controllability of the video generation model, we conduct targeted experiments to investigate distribution gaps affecting E2E planner performance. Finally, we show that synthetic data produced by the video generation model offers a cost-effective alternative to real-world data collection. This synthetic data effectively improves E2E model generalization beyond existing Operational Design Domains, facilitating the expansion of autonomous vehicle services into new operational contexts.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06209</guid>
|
||||
<pubDate>Tue, 07 Oct 2025 17:58:32 +0000</pubDate>
|
||||
<title>Parallel Test-Time Scaling for Latent Reasoning Models</title>
|
||||
<link>https://arxiv.org/abs/2510.07745</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Runyang You, Yongqi Li, Meng Liu, Wenjie Wang, Liqiang Nie, Wenjie Li</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or search. Recent advances in latent reasoning, where intermediate reasoning unfolds in continuous vector spaces, offer a more efficient alternative to explicit Chain-of-Thought, yet whether such latent models can similarly benefit from parallel TTS remains open, mainly due to the absence of sampling mechanisms in continuous space, and the lack of probabilistic signals for advanced trajectory aggregation. \ This work enables parallel TTS for latent reasoning models by addressing the above issues. For sampling, we introduce two uncertainty-inspired stochastic strategies: Monte Carlo Dropout and Additive Gaussian Noise. For aggregation, we design a Latent Reward Model (LatentRM) trained with step-wise contrastive objective to score and guide latent reasoning. Extensive experiments and visualization analyses show that both sampling strategies scale effectively with compute and exhibit distinct exploration dynamics, while LatentRM enables effective trajectory selection. Together, our explorations open a new direction for scalable inference in continuous spaces. Code released at https://github.com/YRYangang/LatentTTS.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07745</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 03:33:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DreamOmni2: Multimodal Instruction-based Editing and Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.06679</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06679.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Xia, Bohao Peng, Yuechen Zhang, Junjia Huang, Jiyang Liu, Jingyao Li, Haoru Tan, Sitong Wu, Chengyao Wang, Yitong Wang, Xinglong Wu, Bei Yu, Jiaya Jia</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on language instructions, which often fail to capture specific editing details, making reference images necessary. Meanwhile, subject-driven generation is limited to combining concrete objects or people, overlooking broader, abstract concepts. To address these challenges, we propose two novel tasks: multimodal instruction-based editing and generation. These tasks support both text and image instructions and extend the scope to include both concrete and abstract concepts, greatly enhancing their practical applications. We introduce DreamOmni2, tackling two primary challenges: data creation and model framework design. Our data synthesis pipeline consists of three steps: (1) using a feature mixing method to create extraction data for both abstract and concrete concepts, (2) generating multimodal instruction-based editing training data using the editing and extraction models, and (3) further applying the extraction model to create training data for multimodal instruction-based editing. For the framework, to handle multi-image input, we propose an index encoding and position encoding shift scheme, which helps the model distinguish images and avoid pixel confusion. Additionally, we introduce joint training with the VLM and our generation/editing model to better process complex instructions. In addition, we have proposed comprehensive benchmarks for these two new tasks to drive their development. Experiments show that DreamOmni2 has achieved impressive results. Models and codes will be released.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06679</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 06:07:14 +0000</pubDate>
|
||||
<title>LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology</title>
|
||||
<link>https://arxiv.org/abs/2510.07793</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07793.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sajib Acharjee Dip, Adrika Zafor, Bikash Kumar Paul, Uddip Acharjee Shuvo, Muhit Islam Emon, Xuan Wang, Liqing Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large language models (LLMs) and emerging agentic frameworks are beginning to transform single-cell biology by enabling natural-language reasoning, generative annotation, and multimodal data integration. However, progress remains fragmented across data modalities, architectures, and evaluation standards. LLM4Cell presents the first unified survey of 58 foundation and agentic models developed for single-cell research, spanning RNA, ATAC, multi-omic, and spatial modalities. We categorize these methods into five families-foundation, text-bridge, spatial, multimodal, epigenomic, and agentic-and map them to eight key analytical tasks including annotation, trajectory and perturbation modeling, and drug-response prediction. Drawing on over 40 public datasets, we analyze benchmark suitability, data diversity, and ethical or scalability constraints, and evaluate models across 10 domain dimensions covering biological grounding, multi-omics alignment, fairness, privacy, and explainability. By linking datasets, models, and evaluation domains, LLM4Cell provides the first integrated view of language-driven single-cell intelligence and outlines open challenges in interpretability, standardization, and trustworthy model development.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07793</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 05:12:09 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling</title>
|
||||
<link>https://arxiv.org/abs/2510.06915</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.06915.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zecheng Tang, Baibei Ji, Quantong Qiu, Haitian Wang, Xiaobo Liang, Juntao Li, Min Zhang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g., LLM agent, it becomes indispensable to evaluate whether a model's responses are not only high-quality but also grounded in and consistent with the provided context. Yet, current RMs remain confined to short-context settings and primarily focus on response-level attributes (e.g., safety or helpfulness), while largely neglecting the critical dimension of long context-response consistency. In this work, we introduce Long-RewardBench, a benchmark specifically designed for long-context RM evaluation, featuring both Pairwise Comparison and Best-of-N tasks. Our preliminary study reveals that even state-of-the-art generative RMs exhibit significant fragility in long-context scenarios, failing to maintain context-aware preference judgments. Motivated by the analysis of failure patterns observed in model outputs, we propose a general multi-stage training strategy that effectively scales arbitrary models into robust Long-context RMs (LongRMs). Experiments show that our approach not only substantially improves performance on long-context evaluation but also preserves strong short-context capability. Notably, our 8B LongRM outperforms much larger 70B-scale baselines and matches the performance of the proprietary Gemini 2.5 Pro model.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.06915</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 11:48:16 +0000</pubDate>
|
||||
<title>Formalizing Style in Personal Narratives</title>
|
||||
<link>https://arxiv.org/abs/2510.08649</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08649.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gustave Cortal, Alain Finkel</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Personal narratives are stories authors construct to make meaning of their experiences. Style, the distinctive way authors use language to express themselves, is fundamental to how these narratives convey subjective experiences. Yet there is a lack of a formal framework for systematically analyzing these stylistic choices. We present a novel approach that formalizes style in personal narratives as patterns in the linguistic choices authors make when communicating subjective experiences. Our framework integrates three domains: functional linguistics establishes language as a system of meaningful choices, computer science provides methods for automatically extracting and analyzing sequential patterns, and these patterns are linked to psychological observations. Using language models, we automatically extract linguistic features such as processes, participants, and circumstances. We apply our framework to hundreds of dream narratives, including a case study on a war veteran with post-traumatic stress disorder. Analysis of his narratives uncovers distinctive patterns, particularly how verbal processes dominate over mental ones, illustrating the relationship between linguistic choices and psychological states.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08649</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 06:48:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.07048</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07048.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuntao Gui, James Cheng</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to generate search embeddings as a direct output of their reasoning process. Our approach exploits LLMs' chain-of-thought capabilities, allowing them to produce more effective embeddings by reasoning step-by-step through complex semantic analyses. We implement this through three complementary mechanisms. (1) a supervised learning stage enables the model's ability to produce quality embeddings, (2) a reinforcement learning (RL) methodology that optimizes embedding generation alongside reasoning, and (3) a specialized RL environment that efficiently handles evolving embedding representations without requiring complete corpus re-encoding at each training iteration. Our extensive evaluations on diverse benchmarks demonstrate that Search-R3 significantly outperforms prior methods by unifying the reasoning and embedding generation processes. This integrated post-training approach represents a substantial advancement in handling complex knowledge-intensive tasks that require both sophisticated reasoning and effective information retrieval. Project page: https://github.com/ytgui/Search-R3</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07048</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 14:16:20 +0000</pubDate>
|
||||
<title>Understanding DeepResearch via Reports</title>
|
||||
<link>https://arxiv.org/abs/2510.07861</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07861.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianyu Fan, Xinyao Niu, Yuxiang Zheng, Fengji Zhang, Chengen Huang, Bei Chen, Junyang Lin, Chao Huang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> DeepResearch agents represent a transformative AI paradigm, conducting expert-level research through sophisticated reasoning and multi-tool integration. However, evaluating these systems remains critically challenging due to open-ended research scenarios and existing benchmarks that focus on isolated capabilities rather than holistic performance. Unlike traditional LLM tasks, DeepResearch systems must synthesize diverse sources, generate insights, and present coherent findings, which are capabilities that resist simple verification. To address this gap, we introduce DeepResearch-ReportEval, a comprehensive framework designed to assess DeepResearch systems through their most representative outputs: research reports. Our approach systematically measures three dimensions: quality, redundancy, and factuality, using an innovative LLM-as-a-Judge methodology achieving strong expert concordance. We contribute a standardized benchmark of 100 curated queries spanning 12 real-world categories, enabling systematic capability comparison. Our evaluation of four leading commercial systems reveals distinct design philosophies and performance trade-offs, establishing foundational insights as DeepResearch evolves from information assistants toward intelligent research partners. Source code and data are available at: https://github.com/HKUDS/DeepResearch-Eval.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07861</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 07:03:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents</title>
|
||||
<link>https://arxiv.org/abs/2510.07172</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07172.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. Our design mitigates the evaluation trilemma by using metaphysical shifts - systematic alterations of canonical laws - to generate a vast suite of problems that are scalable, scientifically relevant, and memorization-resistant. Moreover, we elevate the evaluation from static function fitting to interactive model discovery, requiring agents to experimentally probe simulated complex systems to uncover hidden principles. Our extensive experiment reveals a clear but fragile capability for discovery in frontier LLMs: this ability degrades precipitously with increasing system complexity and exhibits extreme sensitivity to observational noise. Notably, we uncover a paradoxical effect of tool assistance: providing a code interpreter can hinder more capable models by inducing a premature shift from exploration to exploitation, causing them to satisfice on suboptimal solutions. These results demonstrate that robust, generalizable discovery in complex, interactive environments remains the core challenge. By providing a scalable, robust, and scientifically authentic testbed, NewtonBench offers a crucial tool for measuring true progress and guiding the development of next-generation AI agents capable of genuine scientific discovery.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07172</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 16:12:11 +0000</pubDate>
|
||||
<title>ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall</title>
|
||||
<link>https://arxiv.org/abs/2510.07896</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07896.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayu Yang, Yuxuan Fan, Songning Lai, Shengen Wu, Jiaqi Tang, Chun Kang, Zhijiang Guo, Yutao Yue</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits involve intermediate implicit subjects within reasoning chains. Through causal analysis, we reveal that this limitation stems from an oversight of how chained knowledge is dynamically represented and utilized at the neuron level. We discover that during multi hop reasoning, implicit subjects function as query neurons, which sequentially activate corresponding value neurons across transformer layers to accumulate information toward the final answer, a dynamic prior KE work has overlooked. Guided by this insight, we propose ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall, a framework that leverages neuron-level attribution to identify and edit these critical query-value (Q-V) pathways. ACE provides a mechanistically grounded solution for multi-hop KE, empirically outperforming state-of-the-art methods by 9.44% on GPT-J and 37.46% on Qwen3-8B. Our analysis further reveals more fine-grained activation patterns in Qwen3 and demonstrates that the semantic interpretability of value neurons is orchestrated by query-driven accumulation. These findings establish a new pathway for advancing KE capabilities based on the principled understanding of internal reasoning mechanisms.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07896</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 07:46:08 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense</title>
|
||||
<link>https://arxiv.org/abs/2510.07242</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07242.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Leitian Tao, Ilia Kulikov, Swarnadeep Saha, Tianlu Wang, Jing Xu, Yixuan Li, Jason E Weston, Ping Yu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable, such binary feedback is brittle--many tasks admit partially correct or alternative answers that verifiers under-credit, and the resulting all-or-nothing supervision limits learning. Reward models offer richer, continuous feedback, which can serve as a complementary supervisory signal to verifiers. We introduce HERO (Hybrid Ensemble Reward Optimization), a reinforcement learning framework that integrates verifier signals with reward-model scores in a structured way. HERO employs stratified normalization to bound reward-model scores within verifier-defined groups, preserving correctness while refining quality distinctions, and variance-aware weighting to emphasize challenging prompts where dense signals matter most. Across diverse mathematical reasoning benchmarks, HERO consistently outperforms RM-only and verifier-only baselines, with strong gains on both verifiable and hard-to-verify tasks. Our results show that hybrid reward design retains the stability of verifiers while leveraging the nuance of reward models to advance reasoning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07242</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:09:41 +0000</pubDate>
|
||||
<title>DISCO: Diversifying Sample Condensation for Efficient Model Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2510.07959</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07959.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Alexander Rubinstein, Benjamin Raible, Martin Gubri, Seong Joon Oh</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens environmental impact. The typical approach follows two steps. First, select an anchor subset of data. Second, train a mapping from the accuracy on this subset to the final test result. The drawback is that anchor selection depends on clustering, which can be complex and sensitive to design choices. We argue that promoting diversity among samples is not essential; what matters is to select samples that maximise diversity in model responses. Our method, Diversifying Sample Condensation (DISCO), selects the top-k samples with the greatest model disagreements. This uses greedy, sample-wise statistics rather than global clustering. The approach is conceptually simpler. From a theoretical view, inter-model disagreement provides an information-theoretically optimal rule for such greedy selection. DISCO shows empirical gains over prior methods, achieving state-of-the-art results in performance prediction across MMLU, Hellaswag, Winogrande, and ARC. Code is available here: https://github.com/arubique/disco-public.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07959</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 08:53:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations</title>
|
||||
<link>https://arxiv.org/abs/2510.07314</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07314.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fabian Paischer, Gianluca Galletti, William Hornsby, Paul Setinek, Lorenzo Zanisi, Naomi Carey, Stanislas Pamela, Johannes Brandstetter</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Nuclear fusion plays a pivotal role in the quest for reliable and sustainable energy production. A major roadblock to viable fusion power is understanding plasma turbulence, which significantly impairs plasma confinement, and is vital for next-generation reactor design. Plasma turbulence is governed by the nonlinear gyrokinetic equation, which evolves a 5D distribution function over time. Due to its high computational cost, reduced-order models are often employed in practice to approximate turbulent transport of energy. However, they omit nonlinear effects unique to the full 5D dynamics. To tackle this, we introduce GyroSwin, the first scalable 5D neural surrogate that can model 5D nonlinear gyrokinetic simulations, thereby capturing the physical phenomena neglected by reduced models, while providing accurate estimates of turbulent heat transport.GyroSwin (i) extends hierarchical Vision Transformers to 5D, (ii) introduces cross-attention and integration modules for latent 3Dleftrightarrow5D interactions between electrostatic potential fields and the distribution function, and (iii) performs channelwise mode separation inspired by nonlinear physics. We demonstrate that GyroSwin outperforms widely used reduced numerics on heat flux prediction, captures the turbulent energy cascade, and reduces the cost of fully resolved nonlinear gyrokinetics by three orders of magnitude while remaining physically verifiable. GyroSwin shows promising scaling laws, tested up to one billion parameters, paving the way for scalable neural surrogates for gyrokinetic simulations of plasma turbulence.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07314</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 17:59:10 +0000</pubDate>
|
||||
<title>LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?</title>
|
||||
<link>https://arxiv.org/abs/2510.07962</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07962.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyuan Wang, Yankai Chen, Zhonghang Li, Chao Huang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable progress in reasoning, often through supervised fine-tuning (SFT). However, SFT is resource-intensive, relying on large curated datasets, rejection-sampled demonstrations, and uniform optimization across all tokens, even though only a fraction carry meaningful learning value. In this work, we explore a counterintuitive idea: can smaller language models (SLMs) teach larger language models (LLMs) by revealing high-value reasoning moments that reflect the latter's unique strength? We propose LightReasoner, a novel framework that leverages the behavioral divergence between a stronger expert model (LLM) and a weaker amateur model (SLM). LightReasoner operates in two stages: (1) a sampling stage that pinpoints critical reasoning moments and constructs supervision examples capturing the expert's advantage through expert-amateur contrast, and (2) a fine-tuning stage that aligns the expert model with these distilled examples, amplifying its reasoning strengths. Across seven mathematical benchmarks, LightReasoner improves accuracy by up to 28.1%, while reducing time consumption by 90%, sampled problems by 80%, and tuned token usage by 99%, all without relying on ground-truth labels. By turning weaker SLMs into effective teaching signals, LightReasoner offers a scalable and resource-efficient approach for advancing LLM reasoning. Code is available at: https://github.com/HKUDS/LightReasoner</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07962</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 08:55:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs</title>
|
||||
<link>https://arxiv.org/abs/2510.07429</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07429.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wang Wei, Tiankai Yang, Hongjie Chen, Yue Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Efficient use of large language models (LLMs) is critical for deployment at scale: without adaptive routing, systems either overpay for strong models or risk poor performance from weaker ones. Selecting the right LLM for each query is fundamentally an online decision problem: models differ in strengths, prices fluctuate, and users value accuracy and cost differently. Yet most routers are trained offline with labels for all candidate models, an assumption that breaks in deployment, where only the outcome of the chosen model is observed. We bridge this gap with BaRP, a Bandit-feedback Routing with Preferences approach that trains under the same partial-feedback restriction as deployment, while supporting preference-tunable inference: operators can dial the performance/cost trade-off at test time without retraining. Framed as a contextual bandit over prompt features and a user preference vector, our method simulates an online feedback setting during training and adapts its routing decisions to each new prompt, rather than depending on full-information offline supervision. Comprehensive experiments show that our method consistently outperforms strong offline routers by at least 12.46% and the largest LLM by at least 2.45%, and generalizes robustly for unseen tasks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07429</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 18:24:59 +0000</pubDate>
|
||||
<title>Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition</title>
|
||||
<link>https://arxiv.org/abs/2510.08047</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08047.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su, Tzu-Quan Lin, Shang-Tse Chen, Yun-Nung Chen, Hung-yi Lee</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific errors that filtering fails to fix. We ask: How can we correct these recurring biases without target ground truth? We propose a simple parameter-space correction: in a source domain containing both real and pseudo-labeled data, two ASR models are fine-tuned from the same initialization, one on ground-truth labels and the other on pseudo-labels, and their weight difference forms a correction vector that captures pseudo-label biases. When applied to a pseudo-labeled target model, this vector enhances recognition, achieving up to a 35% relative Word Error Rate (WER) reduction on AfriSpeech-200 across ten African accents with the Whisper tiny model.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08047</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 10:31:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs</title>
|
||||
<link>https://arxiv.org/abs/2510.07499</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07499.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Soyeong Jeong, Taehee Jung, Sung Ju Hwang, Joo-Kyung Kim, Dongyeop Kang</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, which recast reasoning as reusable thought caches, derived from prior problem solving traces, structuring how evidence is combined and guiding multi-hop inference with factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into smaller open-source models, demonstrating its broad applicability and transparent reasoning reuse. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07499</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 19:52:35 +0000</pubDate>
|
||||
<title>R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?</title>
|
||||
<link>https://arxiv.org/abs/2510.08189</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08189.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi Lu, Jianing Wang, Linsen Guo, Wei He, Hongyin Tang, Tao Gui, Xuanjing Huang, Xuezhi Cao, Wei Wang, Xunliang Cai</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek-R1) have led to remarkable improvements through long Chain-of-Thought (CoT). However, existing benchmarks mainly focus on immediate, single-horizon tasks, failing to adequately evaluate models' ability to understand and respond to complex, long-horizon scenarios. To address this incomplete evaluation of Large Reasoning Models (LRMs), we propose R-HORIZON, a method designed to stimulate long-horizon reasoning behaviors in LRMs through query composition. Based on R-HORIZON, we construct a long-horizon reasoning benchmark, comprising complex multi-step reasoning tasks with interdependent problems that span long reasoning horizons. Through comprehensive evaluation of LRMs using the R-HORIZON benchmark, we find that even the most advanced LRMs suffer significant performance degradation. Our analysis reveals that LRMs exhibit limited effective reasoning length and struggle to allocate thinking budget across multiple problems appropriately. Recognizing these limitations, we use R-HORIZON to construct long-horizon reasoning data for reinforcement learning with verified rewards (RLVR). Compared to training with single-horizon data, RLVR with R-HORIZON not only substantially improves performance on the multi-horizon reasoning tasks, but also promotes accuracy on standard reasoning tasks, with an increase of 7.5 on AIME2024. These results position R-HORIZON as a scalable, controllable, and low-cost paradigm for enhancing and evaluating the long-horizon reasoning capabilities of LRMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08189</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 13:16:22 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PickStyle: Video-to-Video Style Transfer with Context-Style Adapters</title>
|
||||
<link>https://arxiv.org/abs/2510.07546</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Soroush Mehraban, Vida Adeli, Jacob Rommann, Babak Taati, Kyryl Truskovskyi</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in a target style specified by a text prompt. A major challenge is the lack of paired video data for supervision. We propose PickStyle, a video-to-video style transfer framework that augments pretrained video diffusion backbones with style adapters and benefits from paired still image data with source-style correspondences for training. PickStyle inserts low-rank adapters into the self-attention layers of conditioning modules, enabling efficient specialization for motion-style transfer while maintaining strong alignment between video content and style. To bridge the gap between static image supervision and dynamic video, we construct synthetic training clips from paired images by applying shared augmentations that simulate camera motion, ensuring temporal priors are preserved. In addition, we introduce Context-Style Classifier-Free Guidance (CS-CFG), a novel factorization of classifier-free guidance into independent text (style) and video (context) directions. CS-CFG ensures that context is preserved in generated video while the style is effectively transferred. Experiments across benchmarks show that our approach achieves temporally coherent, style-faithful, and content-preserving video translations, outperforming existing baselines both qualitatively and quantitatively.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07546</guid>
|
||||
<pubDate>Wed, 08 Oct 2025 21:02:55 +0000</pubDate>
|
||||
<title>ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping</title>
|
||||
<link>https://arxiv.org/abs/2510.08457</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuang Chen, Yue Guo, Yimeng Ye, Shijue Huang, Wenbo Hu, Haoxi Li, Manyuan Zhang, Jiayu Chen, Song Guo, Nanyun Peng</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy reasoning traces, while under-exploring on challenging ones, leading to missed solutions. To address this imbalance, we propose ARES, a unified open-source framework for adaptive reasoning that dynamically allocates exploration effort based on task difficulty. Our approach is motivated by two key empirical findings: (i) while single-token entropy is noisy, high window-entropy (HWE) tokens (token-level entropies averaged under a sliding window) can reliably capture reasoning-critical moments; and (ii) reducing HWE usage benefits easy problems, while increasing it is essential for solving hard ones. Building on these insights, ARES introduces a two-stage training pipeline. In the Adaptive Cold-Start stage, we curate multimodal and textual data paired with reasoning traces of length proportional to problem difficulty, equipping the model with initial difficulty awareness. In the second stage, we develop Adaptive Entropy Policy Optimization (AEPO), which uses HWE tokens as exploration triggers to decide when to explore, and a hierarchical entropy reward with dynamic KL control to decide how much to explore. Extensive experiments demonstrate that ARES achieves superior performance and reasoning efficiency across diverse mathematical, logical, and multimodal benchmarks, while closing the gap to leading commercial systems under significantly lower inference costs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08457</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:03:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment</title>
|
||||
<link>https://arxiv.org/abs/2510.07743</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07743.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianci Liu, Ran Xu, Tony Yu, Ilgee Hong, Carl Yang, Tuo Zhao, Haoyu Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies have explored rubrics-as-rewards (RaR) that uses structured natural language criteria that capture multiple dimensions of response quality. However, producing rubrics that are both reliable and scalable remains a key challenge. In this work, we introduce OpenRubrics, a diverse, large-scale collection of (prompt, rubric) pairs for training rubric-generation and rubric-based reward models. To elicit discriminative and comprehensive evaluation signals, we introduce Contrastive Rubric Generation (CRG), which derives both hard rules (explicit constraints) and principles (implicit qualities) by contrasting preferred and rejected responses. We further improve reliability by enforcing preference-label consistency via rejection sampling to remove noisy rubrics. Across multiple reward-modeling benchmarks, our rubric-based reward model, Rubric-RM, surpasses strong size-matched baselines by 6.8%. These gains transfer to policy models on instruction-following and biomedical benchmarks. Our results show that rubrics provide scalable alignment signals that narrow the gap between costly human evaluation and automated reward modeling, enabling a new principle-driven paradigm for LLM alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07743</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 03:31:26 +0000</pubDate>
|
||||
<title>Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models</title>
|
||||
<link>https://arxiv.org/abs/2510.08492</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08492.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired multimodal data to directly enhance representation learning in a target modality? We introduce UML: Unpaired Multimodal Learner, a modality-agnostic training paradigm in which a single model alternately processes inputs from different modalities while sharing parameters across them. This design exploits the assumption that different modalities are projections of a shared underlying reality, allowing the model to benefit from cross-modal structure without requiring explicit pairs. Theoretically, under linear data-generating assumptions, we show that unpaired auxiliary data can yield representations strictly more informative about the data-generating process than unimodal training. Empirically, we show that using unpaired data from auxiliary modalities -- such as text, audio, or images -- consistently improves downstream performance across diverse unimodal targets such as image and audio. Our project page: https://unpaired-multimodal.github.io/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08492</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:32:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GCPO: When Contrast Fails, Go Gold</title>
|
||||
<link>https://arxiv.org/abs/2510.07790</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07790.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao Wu, Wei Liu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reinforcement learning has been widely applied to enhance the reasoning capabilities of large language models. Extending the inference limits of smaller models has become a prominent research focus. However, algorithms such as Group Relative Policy Optimization (GRPO) suffer from a clear drawback: the upper bound of a model's rollout responses is entirely determined by the model itself, preventing the acquisition of knowledge from samples that are either all incorrect or all correct. In this paper, we introduce Group Contrastive Policy Optimization (GCPO), a method that incorporates external standard reference answers. When the model cannot solve a problem, the reference answer supplies the correct response, steering the model toward an unequivocally accurate update direction. This approach offers two main advantages: (1) it improves training efficiency by fully utilizing every sample; (2) it enables the model to emulate the problem solving strategy of the reference answer during training, thereby enhancing generalization in reasoning. GCPO achieves outstanding results across multiple benchmark datasets, yielding substantial improvements over the baseline model. Our code is available at: https://github.com/AchoWu/GCPO.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07790</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 05:09:06 +0000</pubDate>
|
||||
<title>Which Heads Matter for Reasoning? RL-Guided KV Cache Compression</title>
|
||||
<link>https://arxiv.org/abs/2510.08525</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08525.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenjie Du, Li Jiang, Keda Tao, Xue Liu, Huan Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Reasoning large language models exhibit complex reasoning behaviors through the extended chain-of-thought generation, creating unprecedented Key-Value (KV) cache overhead during the decoding phase. Existing KV cache compression methods underperform on reasoning models: token-dropping methods break reasoning integrity by discarding critical information, while head-reallocating methods mistakenly compress reasoning-critical heads since they are designed for retrieval tasks, resulting in significant performance degradation as compression rates increase. We hypothesize that KV heads exhibit functional heterogeneity in reasoning models-some heads are critical for chain-of-thought consistency while others are compressible. To validate and exploit this insight, we propose RLKV, a novel reasoning-critical head identification framework, which uses reinforcement learning to directly optimize the relationship between each head's cache usage and reasoning quality. As RLKV produces rewards from actual generated samples during training, it naturally identifies heads relevant to reasoning behaviors. We then allocate full KV cache to these heads while applying compressed constant KV cache to others for efficient inference. Our experiments reveal that only a small fraction of attention heads is essential for reasoning, enabling our KV compression approach to outperform baseline methods while achieving 20-50% cache reduction with near lossless performance compared to uncompressed results.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08525</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:50:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2510.07958</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.07958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fengji Zhang, Xinyao Niu, Chengyang Ying, Guancheng Lin, Zhongkai Hao, Zhou Fan, Chengen Huang, Jacky Keung, Bei Chen, Junyang Lin</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers. Standard QA benchmarks, which typically assume a single gold answer, overlook this reality and thus produce inappropriate training signals. Existing attempts to handle ambiguity often rely on costly manual annotation, which is difficult to scale to multi-hop datasets such as HotpotQA and MuSiQue. In this paper, we present A^2Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. At its core is an automated pipeline that detects ambiguous questions and gathers alternative answers via trajectory sampling and evidence verification. The model is then optimized with RL using a carefully designed AnsF1 reward, which naturally accommodates multiple answers. Experiments on eight open-domain QA benchmarks demonstrate that A^2Search achieves new state-of-the-art performance. With only a single rollout, A^2Search-7B yields an average AnsF1@1 score of 48.4% across four multi-hop benchmarks, outperforming all strong baselines, including the substantially larger ReSearch-32B (46.2%). Extensive analyses further show that A^2Search resolves ambiguity and generalizes across benchmarks, highlighting that embracing ambiguity is essential for building more reliable QA systems. Our code, data, and model weights can be found at https://github.com/zfj1998/A2Search</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.07958</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 08:53:31 +0000</pubDate>
|
||||
<title>Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.08673</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08673.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kang Liao, Size Wu, Zhonghua Wu, Linyi Jin, Chao Wang, Yikai Wang, Fei Wang, Wei Li, Chen Change Loy</p><p><b>Upvotes:</b> 86</p><p><b>Summary:</b> Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric multimodal model that extends spatial awareness along the camera dimension. Puffin integrates language regression and diffusion-based generation to interpret and create scenes from arbitrary viewpoints. To bridge the modality gap between cameras and vision-language, we introduce a novel paradigm that treats camera as language, enabling thinking with camera. This guides the model to align spatially grounded visual cues with photographic terminology while reasoning across geometric context. Puffin is trained on Puffin-4M, a large-scale dataset of 4 million vision-language-camera triplets. We incorporate both global camera parameters and pixel-wise camera maps, yielding flexible and reliable spatial generation. Experiments demonstrate Puffin superior performance over specialized models for camera-centric generation and understanding. With instruction tuning, Puffin generalizes to diverse cross-view tasks such as spatial imagination, world exploration, and photography guidance. We will release the code, models, dataset pipeline, and benchmark to advance multimodal spatial intelligence research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08673</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:59:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks</title>
|
||||
<link>https://arxiv.org/abs/2510.08002</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08002.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu, Jianbiao Mei, Rong Wu, Pinlong Cai, Yufan Shen, Nianchen Deng, Botian Shi, Yu Qiao, Haifeng Li</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical limitation: they are test-time static and cannot learn from experience, lacking the ability to accumulate knowledge and continuously improve on the job. To address this challenge, we propose MUSE, a novel agent framework that introduces an experience-driven, self-evolving system centered around a hierarchical Memory Module. MUSE organizes diverse levels of experience and leverages them to plan and execute long-horizon tasks across multiple applications. After each sub-task execution, the agent autonomously reflects on its trajectory, converting the raw trajectory into structured experience and integrating it back into the Memory Module. This mechanism enables the agent to evolve beyond its static pretrained parameters, fostering continuous learning and self-evolution. We evaluate MUSE on the long-horizon productivity benchmark TAC. It achieves new SOTA performance by a significant margin using only a lightweight Gemini-2.5 Flash model. Sufficient Experiments demonstrate that as the agent autonomously accumulates experience, it exhibits increasingly superior task completion capabilities, as well as robust continuous learning and self-evolution capabilities. Moreover, the accumulated experience from MUSE exhibits strong generalization properties, enabling zero-shot improvement on new tasks. MUSE establishes a new paradigm for AI agents capable of real-world productivity task automation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08002</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 09:40:34 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Recycling Pretrained Checkpoints: Orthogonal Growth of Mixture-of-Experts for Efficient Large Language Model Pre-Training</title>
|
||||
<link>https://arxiv.org/abs/2510.08008</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruizhe Wang, Yucheng Ding, Xiao Liu, Yaoxiang Wang, Peng Cheng, Baining Guo, Zhengjun Zha, Yeyun Gong</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The rapidly increasing computational cost of pretraining Large Language Models necessitates more efficient approaches. Numerous computational costs have been invested in existing well-trained checkpoints, but many of them remain underutilized due to engineering constraints or limited model capacity. To efficiently reuse this "sunk" cost, we propose to recycle pretrained checkpoints by expanding their parameter counts and continuing training. We propose orthogonal growth method well-suited for converged Mixture-of-Experts model: interpositional layer copying for depth growth and expert duplication with injected noise for width growth. To determine the optimal timing for such growth across checkpoints sequences, we perform comprehensive scaling experiments revealing that the final accuracy has a strong positive correlation with the amount of sunk cost, indicating that greater prior investment leads to better performance. We scale our approach to models with 70B parameters and over 1T training tokens, achieving 10.66% accuracy gain over training from scratch under the same additional compute budget. Our checkpoint recycling approach establishes a foundation for economically efficient large language model pretraining.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08008</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 09:45:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution</title>
|
||||
<link>https://arxiv.org/abs/2510.08143</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08143.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shian Du, Menghan Xia, Chang Liu, Quande Liu, Xintao Wang, Pengfei Wan, Xiangyang Ji</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Cascaded video super-resolution has emerged as a promising technique for decoupling the computational burden associated with generating high-resolution videos using large foundation models. Existing studies, however, are largely confined to text-to-video tasks and fail to leverage additional generative conditions beyond text, which are crucial for ensuring fidelity in multi-modal video generation. We address this limitation by presenting UniMMVSR, the first unified generative video super-resolution framework to incorporate hybrid-modal conditions, including text, images, and videos. We conduct a comprehensive exploration of condition injection strategies, training schemes, and data mixture techniques within a latent video diffusion model. A key challenge was designing distinct data construction and condition utilization methods to enable the model to precisely utilize all condition types, given their varied correlations with the target video. Our experiments demonstrate that UniMMVSR significantly outperforms existing methods, producing videos with superior detail and a higher degree of conformity to multi-modal conditions. We also validate the feasibility of combining UniMMVSR with a base model to achieve multi-modal guided generation of 4K video, a feat previously unattainable with existing techniques.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08143</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 12:25:16 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Training-Free Group Relative Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.08191</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08191.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuzheng Cai, Siqi Cai, Yuchen Shi, Zihan Xu, Lichao Chen, Yulei Qin, Xiaoyu Tan, Gang Li, Zongyi Li, Haojia Lin, Yong Mao, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external tools and specific prompting strategies. While methods like agentic reinforcement learning have been proposed to address this, they typically rely on costly parameter updates, for example, through a process that uses Supervised Fine-Tuning (SFT) followed by a Reinforcement Learning (RL) phase with Group Relative Policy Optimization (GRPO) to alter the output distribution. However, we argue that LLMs can achieve a similar effect on the output distribution by learning experiential knowledge as a token prior, which is a far more lightweight approach that not only addresses practical data scarcity but also avoids the common issue of overfitting. To this end, we propose Training-Free Group Relative Policy Optimization (Training-Free GRPO), a cost-effective solution that enhances LLM agent performance without any parameter updates. Our method leverages the group relative semantic advantage instead of numerical ones within each group of rollouts, iteratively distilling high-quality experiential knowledge during multi-epoch learning on a minimal ground-truth data. Such knowledge serves as the learned token prior, which is seamlessly integrated during LLM API calls to guide model behavior. Experiments on mathematical reasoning and web searching tasks demonstrate that Training-Free GRPO, when applied to DeepSeek-V3.1-Terminus, significantly improves out-of-domain performance. With just a few dozen training samples, Training-Free GRPO outperforms fine-tuned small LLMs with marginal training data and cost.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08191</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 13:18:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Memory Retrieval and Consolidation in Large Language Models through Function Tokens</title>
|
||||
<link>https://arxiv.org/abs/2510.08203</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08203.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaohua Zhang, Yuan Lin, Hang Li</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities such as knowledge memorization, instruction-following and reasoning. However, the mechanisms of memory retrieval and consolidation in LLMs remain poorly understood. In this paper, we propose the function token hypothesis to explain the workings of LLMs: During inference, function tokens activate the most predictive features from context and govern next token prediction (memory retrieval). During pre-training, predicting the next tokens (usually content tokens) that follow function tokens increases the number of learned features of LLMs and updates the model parameters (memory consolidation). Function tokens here roughly correspond to function words in linguistics, including punctuation marks, articles, prepositions, and conjunctions, in contrast to content tokens. We provide extensive experimental evidence supporting this hypothesis. Using bipartite graph analysis, we show that a small number of function tokens activate the majority of features. Case studies further reveal how function tokens activate the most predictive features from context to direct next token prediction. We also find that during pre-training, the training loss is dominated by predicting the next content tokens following function tokens, which forces the function tokens to select the most predictive features from context.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08203</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 13:31:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions</title>
|
||||
<link>https://arxiv.org/abs/2510.08211</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08211.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> XuHao Hu, Peng Wang, Xiaoya Lu, Dongrui Liu, Xuanjing Huang, Jing Shao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called emergent misalignment. In this work, we investigate whether this phenomenon can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios (e.g., lying under pressure and deceptive behavior). To explore this, we finetune open-sourced LLMs on misaligned completions across diverse domains. Experimental results demonstrate that LLMs show broadly misaligned behavior in dishonesty. Additionally, we further explore this phenomenon in a downstream combined finetuning setting, and find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%. Furthermore, we consider a more practical human-AI interaction environment where we simulate both benign and biased users to interact with the assistant LLM. Notably, we find that the assistant can be misaligned unintentionally to exacerbate its dishonesty with only 10% biased user population. In summary, we extend the study of emergent misalignment to the domain of dishonesty and deception under high-stakes scenarios, and demonstrate that this risk arises not only through direct finetuning, but also in downstream mixture tasks and practical human-AI interactions.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08211</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 13:35:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>The Alignment Waltz: Jointly Training Agents to Collaborate for Safety</title>
|
||||
<link>https://arxiv.org/abs/2510.08240</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08240.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingyu Zhang, Haozhu Wang, Eric Michael Smith, Sid Wang, Amr Sharaf, Mahesh Pasupuleti, Benjamin Van Durme, Daniel Khashabi, Jason Weston, Hongyuan Zhan</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency for overrefusal on benign but sensitive prompts. Current approaches often navigate this dance with safeguard models that completely reject any content that contains unsafe portions. This approach cuts the music entirely-it may exacerbate overrefusals and fails to provide nuanced guidance for queries it refuses. To teach models a more coordinated choreography, we propose WaltzRL, a novel multi-agent reinforcement learning framework that formulates safety alignment as a collaborative, positive-sum game. WaltzRL jointly trains a conversation agent and a feedback agent, where the latter is incentivized to provide useful suggestions that improve the safety and helpfulness of the conversation agent's responses. At the core of WaltzRL is a Dynamic Improvement Reward (DIR) that evolves over time based on how well the conversation agent incorporates the feedback. At inference time, unsafe or overrefusing responses from the conversation agent are improved rather than discarded. The feedback agent is deployed together with the conversation agent and only engages adaptively when needed, preserving helpfulness and low latency on safe queries. Our experiments, conducted across five diverse datasets, demonstrate that WaltzRL significantly reduces both unsafe responses (e.g., from 39.0% to 4.6% on WildJailbreak) and overrefusals (from 45.3% to 9.9% on OR-Bench) compared to various baselines. By enabling the conversation and feedback agents to co-evolve and adaptively apply feedback, WaltzRL enhances LLM safety without degrading general capabilities, thereby advancing the Pareto front between helpfulness and harmlessness.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08240</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 14:03:05 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SViM3D: Stable Video Material Diffusion for Single Image 3D Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.08271</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08271.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andreas Engelhardt, Mark Boss, Vikram Voletti, Chun-Han Yao, Hendrik P. A. Lensch, Varun Jampani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently. However, reflectance is still represented by simple material models or needs to be estimated in additional steps to enable relighting and controlled appearance edits. We extend a latent video diffusion model to output spatially varying PBR parameters and surface normals jointly with each generated view based on explicit camera control. This unique setup allows for relighting and generating a 3D asset using our model as neural prior. We introduce various mechanisms to this pipeline that improve quality in this ill-posed setting. We show state-of-the-art relighting and novel view synthesis performance on multiple object-centric datasets. Our method generalizes to diverse inputs, enabling the generation of relightable 3D assets useful in AR/VR, movies, games and other visual media.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08271</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 14:29:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window</title>
|
||||
<link>https://arxiv.org/abs/2510.08276</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08276.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiaoyu Tang, Hao Xiang, Le Yu, Bowen Yu, Yaojie Lu, Xianpei Han, Le Sun, WenJuan Zhang, Pengbo Wang, Shixuan Liu, Zhenru Zhang, Jianhong Tu, Hongyu Lin, Junyang Lin</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities in multi-turn agents with long-horizon interactions. We propose DeepMiner, a novel framework that elicits such abilities by introducing high-difficulty training tasks and dynamic context window. DeepMiner presents a reverse construction method to generate complex but verifiable question-answer pairs from authentic web sources, which ensures the challenge and reliability of training data while injecting cognitive capabilities into multi-turn reasoning scenarios. We further design an elegant yet effective dynamic context management strategy for both training and inference, utilizing sliding window mechanisms while eliminating the dependency on external summarization models, thereby efficiently empowering the model to handle continuously expanding long-horizon contexts. Through reinforcement learning on Qwen3-32B, we develop DeepMiner-32B, which achieves substantial performance improvements across multiple search agent benchmarks. DeepMiner attains 33.5% accuracy on BrowseComp-en, surpassing the previous best open-source agent by almost 20 percentage points, and demonstrates consistent improvements on BrowseComp-zh, XBench-DeepSearch, and GAIA. Notably, our dynamic context management enables sustained interactions of nearly 100 turns within standard 32k context length, effectively addressing the context limitations that constrain existing multi-turn interaction systems.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08276</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 14:31:39 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>First Try Matters: Revisiting the Role of Reflection in Reasoning Models</title>
|
||||
<link>https://arxiv.org/abs/2510.08308</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08308.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liwei Kang, Yue Deng, Yao Xiao, Zhanfeng Mo, Wee Sun Lee, Lidong Bing</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to performance improvement remains unclear. In this paper, we systematically analyze the rollouts of eight reasoning models on five mathematical datasets. We focus on reflective behaviours where the model has already produced an answer but continues reflecting before finalizing its output. Our analysis reveals that reflections are predominantly confirmatory and rarely alter the model's initial answer, a pattern consistent across models and datasets. To understand the role of reflections in training, we construct supervised fine-tuning (SFT) datasets with varying amounts of reflection steps. We observe that training models on rollouts with more reflection steps primarily enhances first-answer correctness rather than the ability to correct initially wrong answers through reflections. This motivates us to propose a question-aware early-stopping method that enhances inference-time token efficiency by stopping the reasoning process once a few plausible candidate answers are generated, thereby reducing unnecessary reflection steps. Motivated by this, we further propose to dynamically truncate the reflections after a candidate answer has appeared during generation, which reduces reasoning tokens by 24.5% across five mathematical datasets, within a 2.9% drop in accuracy.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08308</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 14:57:10 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>UniVideo: Unified Understanding, Generation, and Editing for Videos</title>
|
||||
<link>https://arxiv.org/abs/2510.08377</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhu Chen</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design enables accurate interpretation of complex multimodal instructions while preserving visual consistency. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as green-screening characters or changing materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we will release our model and code.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08377</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 16:01:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Reinforcing Diffusion Models by Direct Group Preference Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.08425</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08425.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yihong Luo, Tianyang Hu, Jing Tang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic policy, yet the most cost-effective diffusion samplers are based on deterministic ODEs. Recent work addresses this issue by using inefficient SDE-based samplers to induce stochasticity, but this reliance on model-agnostic Gaussian noise leads to slow convergence. To resolve this conflict, we propose Direct Group Preference Optimization (DGPO), a new online RL algorithm that dispenses with the policy-gradient framework entirely. DGPO learns directly from group-level preferences, which utilize relative information of samples within groups. This design eliminates the need for inefficient stochastic policies, unlocking the use of efficient deterministic ODE samplers and faster training. Extensive results show that DGPO trains around 20 times faster than existing state-of-the-art methods and achieves superior performance on both in-domain and out-of-domain reward metrics. Code is available at https://github.com/Luo-Yihong/DGPO.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08425</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 16:40:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency</title>
|
||||
<link>https://arxiv.org/abs/2510.08431</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08431.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaiwen Zheng, Yuji Wang, Qianli Ma, Huayu Chen, Jintao Zhang, Yogesh Balaji, Jianfei Chen, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> This work represents the first effort to scale up continuous-time consistency distillation to general application-level image and video diffusion models. Although continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of standard evaluation benchmarks. We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks. Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the "mode-covering" nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. This integration complements sCM with the "mode-seeking" reverse divergence, effectively improving visual quality while maintaining high generation diversity. Validated on large-scale models (Cosmos-Predict2, Wan2.1) up to 14B parameters and 5-second videos, rCM matches or surpasses the state-of-the-art distillation method DMD2 on quality metrics while offering notable advantages in diversity, all without GAN tuning or extensive hyperparameter searches. The distilled models generate high-fidelity samples in only 1sim4 steps, accelerating diffusion sampling by 15timessim50times. These results position rCM as a practical and theoretically grounded framework for advancing large-scale diffusion distillation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08431</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 16:45:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DeepPrune: Parallel Scaling without Inter-trace Redundancy</title>
|
||||
<link>https://arxiv.org/abs/2510.08483</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08483.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-of-Thought (CoT) traces simultaneously. However, this approach introduces significant computational inefficiency due to inter-trace redundancy -- our analysis reveals that over 80% of parallel reasoning traces yield identical final answers, representing substantial wasted computation. To address this critical efficiency bottleneck, we propose DeepPrune, a novel framework that enables efficient parallel scaling through dynamic pruning. Our method features a specialized judge model trained with focal loss and oversampling techniques to accurately predict answer equivalence from partial reasoning traces which realizes 0.87 AUROC on equivalence prediction, combined with an online greedy clustering algorithm that dynamically prunes redundant paths while preserving answer diversity. Comprehensive evaluations across three challenging benchmarks (AIME 2024, AIME 2025, and GPQA) and multiple reasoning models demonstrate that DeepPrune achieves remarkable token reduction by over 80% compared to conventional consensus sampling on most cases, while maintaining competitive accuracy within 3 percentage points. Our work establishes a new standard for efficient parallel reasoning, making high-performance reasoning more efficient. Our code and data are here: https://deepprune.github.io/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08483</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:24:54 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>InstructX: Towards Unified Visual Editing with MLLM Guidance</title>
|
||||
<link>https://arxiv.org/abs/2510.08485</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08485.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chong Mou, Qichao Sun, Yanze Wu, Pengze Zhang, Xinghui Li, Fulong Ye, Songtao Zhao, Qian He</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most studies lack an in-depth analysis of MLLM design choices. Moreover, the integration of MLLMs and diffusion models remains an open challenge in some difficult tasks, such as video editing. In this paper, we present InstructX, a unified framework for image and video editing. Specifically, we conduct a comprehensive study on integrating MLLMs and diffusion models for instruction-driven editing across diverse tasks. Building on this study, we analyze the cooperation and distinction between images and videos in unified modeling. (1) We show that training on image data can lead to emergent video editing capabilities without explicit supervision, thereby alleviating the constraints imposed by scarce video training data. (2) By incorporating modality-specific MLLM features, our approach effectively unifies image and video editing tasks within a single model. Extensive experiments demonstrate that our method can handle a broad range of image and video editing tasks and achieves state-of-the-art performance.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08485</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:26:09 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards</title>
|
||||
<link>https://arxiv.org/abs/2510.08529</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08529.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyuan Xue, Yifan Zhou, Guibin Zhang, Zaibin Zhang, Yijiang Li, Chen Zhang, Zhenfei Yin, Philip Torr, Wanli Ouyang, Lei Bai</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witnessed a transition from reinforcement learning (RL)-free to RL-based methods. Current RL-based methods either rely on dense external reward signals or extract intrinsic reward signals from LLMs themselves. However, these approaches diverge from the self-evolution mechanisms observed in human intelligence, where individuals learn and improve through mutual discussion and collaboration. In this work, we introduce Co-Evolving Multi-Agent Systems (CoMAS), a novel framework that enables agents to improve autonomously by learning from inter-agent interactions without external supervision. CoMAS generates intrinsic rewards from rich discussion dynamics, employs an LLM-as-a-judge mechanism to formulate these rewards, and optimizes each agent's policy through RL, thereby enabling decentralized and scalable co-evolution. Experimental results demonstrate that CoMAS consistently outperforms untrained agents and achieves state-of-the-art performance across most evaluation settings. Ablation studies confirm the necessity of interaction-based reward signals and reveal promising scalability as the number and diversity of agents increase. These findings establish CoMAS as a novel and effective paradigm for self-evolution in LLM-based agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08529</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:50:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2510.08540</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiangyu Zhao, Junming Lin, Tianhao Liang, Yifan Zhou, Wenhao Chai, Yuzhe Gu, Weiyun Wang, Kai Chen, Gen Luo, Wenwei Zhang, Junchi Yan, Hua Yang, Haodong Duan, Xue Yang</p><p><b>Upvotes:</b> 98</p><p><b>Summary:</b> While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world problems, remains largely underexplored. In this work, we first conduct an extensive empirical investigation to evaluate this capability. Leveraging a carefully designed data synthesis engine, we construct MM-HELIX, a multimodal benchmark consisting 1,260 samples of 42 challenging synthetic tasks that require iterative thinking and backtracking. Empirical results on this benchmark reveal that existing MLLMs exhibit significant performance deficits in long-chain reflective reasoning. To address this limitation, we generate post-training data and further explore learning paradigms for exploiting such data. We first develop the Step-Elicited Response Generation pipeline to create MM-HELIX-100K, a large-scale dataset of 100k high-quality, reflective reasoning traces for instruction-tuning stage. Given that standard Reinforcement Learning fails on complex tasks due to sparse reward signals and catastrophic forgetting after Supervised Fine-Tuning, we propose Adaptive Hybrid Policy Optimization (AHPO), a novel training strategy that dynamically unifies offline supervision and online optimization into a single stage. This strategy enables the model to learn from expert data when rewards are sparse and conduct independent exploration once proficient. When applied to the Qwen2.5-VL-7B baseline, our method achieves a +18.6\% accuracy improvement on MM-HELIX benchmark and demonstrates strong generalization with a +5.7\% average performance gain on general mathematic and logic tasks. Our work demonstrate that reflective reasoning in MLLMs can be effectively learned and generalized, paving the way for developing more capable MLLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08540</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:53:58 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation</title>
|
||||
<link>https://arxiv.org/abs/2510.08547</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08547.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiuwei Xu, Angyuan Ma, Hankun Li, Bingyao Yu, Zheng Zhu, Jie Zhou, Jiwen Lu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To achieve this, substantial human demonstrations need to be collected to cover different spatial configurations for training a generalized visuomotor policy via imitation learning. Prior works explore a promising direction that leverages data generation to acquire abundant spatially diverse data from minimal source demonstrations. However, most approaches face significant sim-to-real gap and are often limited to constrained settings, such as fixed-base scenarios and predefined camera viewpoints. In this paper, we propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data. R2RGen is simulator- and rendering-free, thus being efficient and plug-and-play. Specifically, given a single source demonstration, we introduce an annotation mechanism for fine-grained parsing of scene and trajectory. A group-wise augmentation strategy is proposed to handle complex multi-object compositions and diverse task constraints. We further present camera-aware processing to align the distribution of generated data with real-world 3D sensor. Empirically, R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08547</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:55:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints</title>
|
||||
<link>https://arxiv.org/abs/2510.08549</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08549.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zilin Kang, Chonghua Liao, Tingqiang Xu, Huazhe Xu</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonstrates broad effectiveness across different domains: 1) for large language models(LLMs), boosting the AIME 2025 score for Qwen2.5-Math-7B by 37.4%; 2) for continuous control reinforcement learning agents, improving performance by more than 30% over strong baselines such as SAC on the challenging HumanoidBench; 3) for image classification, enhancing ImageNet top-1 accuracy by 0.69% for ResNet-50. These gains are achieved with a computational overhead of less than 7%. Our work validates output activation as a powerful tool for entropy control, opening a new direction for designing simpler and more robust algorithms.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08549</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:56:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation</title>
|
||||
<link>https://arxiv.org/abs/2510.08551</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08551.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Bo Dai, Jian Pu, Mulin Yu, Jiangmiao Pang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> On-the-fly 3D reconstruction from monocular image sequences is a long-standing challenge in computer vision, critical for applications such as real-to-sim, AR/VR, and robotics. Existing methods face a major tradeoff: per-scene optimization yields high fidelity but is computationally expensive, whereas feed-forward foundation models enable real-time inference but struggle with accuracy and robustness. In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forward models with the reliability of SLAM-based pipelines. ARTDECO uses 3D foundation models for pose estimation and point prediction, coupled with a Gaussian decoder that transforms multi-scale features into structured 3D Gaussians. To sustain both fidelity and efficiency at scale, we design a hierarchical Gaussian representation with a LoD-aware rendering strategy, which improves rendering fidelity while reducing redundancy. Experiments on eight diverse indoor and outdoor benchmarks show that ARTDECO delivers interactive performance comparable to SLAM, robustness similar to feed-forward systems, and reconstruction quality close to per-scene optimization, providing a practical path toward on-the-fly digitization of real-world environments with both accurate geometry and high visual fidelity. Explore more demos on our project page: https://city-super.github.io/artdeco/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08551</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:57:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning</title>
|
||||
<link>https://arxiv.org/abs/2510.08555</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08555.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghong Cai, Qiulin Wang, Zongli Ye, Wenze Liu, Quande Liu, Weicai Ye, Xintao Wang, Pengfei Wan, Kun Gai, Xiangyu Yue</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> We introduce the task of arbitrary spatio-temporal video completion, where a video is generated from arbitrary, user-specified patches placed at any spatial location and timestamp, akin to painting on a video canvas. This flexible formulation naturally unifies many existing controllable video generation tasks--including first-frame image-to-video, inpainting, extension, and interpolation--under a single, cohesive paradigm. Realizing this vision, however, faces a fundamental obstacle in modern latent video diffusion models: the temporal ambiguity introduced by causal VAEs, where multiple pixel frames are compressed into a single latent representation, making precise frame-level conditioning structurally difficult. We address this challenge with VideoCanvas, a novel framework that adapts the In-Context Conditioning (ICC) paradigm to this fine-grained control task with zero new parameters. We propose a hybrid conditioning strategy that decouples spatial and temporal control: spatial placement is handled via zero-padding, while temporal alignment is achieved through Temporal RoPE Interpolation, which assigns each condition a continuous fractional position within the latent sequence. This resolves the VAE's temporal ambiguity and enables pixel-frame-aware control on a frozen backbone. To evaluate this new capability, we develop VideoCanvasBench, the first benchmark for arbitrary spatio-temporal video completion, covering both intra-scene fidelity and inter-scene creativity. Experiments demonstrate that VideoCanvas significantly outperforms existing conditioning paradigms, establishing a new state of the art in flexible and unified video generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08555</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:58:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model</title>
|
||||
<link>https://arxiv.org/abs/2510.08556</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08556.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xueyi Liu, He Wang, Li Yi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Achieving generalized in-hand object rotation remains a significant challenge in robotics, largely due to the difficulty of transferring policies from simulation to the real world. The complex, contact-rich dynamics of dexterous manipulation create a "reality gap" that has limited prior work to constrained scenarios involving simple geometries, limited object sizes and aspect ratios, constrained wrist poses, or customized hands. We address this sim-to-real challenge with a novel framework that enables a single policy, trained in simulation, to generalize to a wide variety of objects and conditions in the real world. The core of our method is a joint-wise dynamics model that learns to bridge the reality gap by effectively fitting limited amount of real-world collected data and then adapting the sim policy's actions accordingly. The model is highly data-efficient and generalizable across different whole-hand interaction distributions by factorizing dynamics across joints, compressing system-wide influences into low-dimensional variables, and learning each joint's evolution from its own dynamic profile, implicitly capturing these net effects. We pair this with a fully autonomous data collection strategy that gathers diverse, real-world interaction data with minimal human intervention. Our complete pipeline demonstrates unprecedented generality: a single policy successfully rotates challenging objects with complex shapes (e.g., animals), high aspect ratios (up to 5.33), and small sizes, all while handling diverse wrist orientations and rotation axes. Comprehensive real-world evaluations and a teleoperation application for complex tasks validate the effectiveness and robustness of our approach. Website: https://meowuu7.github.io/DexNDM/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08556</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:59:11 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Agent Learning via Early Experience</title>
|
||||
<link>https://arxiv.org/abs/2510.08558</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu</p><p><b>Upvotes:</b> 175</p><p><b>Summary:</b> A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to scale and generalizes poorly. This limitation stems from the nature of expert demonstrations: they capture only a narrow range of scenarios and expose the agent to limited environment diversity. We address this limitation with a middle-ground paradigm we call early experience: interaction data generated by the agent's own actions, where the resulting future states serve as supervision without reward signals. Within this paradigm we study two strategies of using such data: (1) Implicit world modeling, which uses collected states to ground the policy in environment dynamics; and (2) Self-reflection, where the agent learns from its suboptimal actions to improve reasoning and decision-making. We evaluate across eight diverse environments and multiple model families. Our approaches consistently improve effectiveness and out-of-domain generalization, highlighting the value of early experience. Moreover, in environments with verifiable rewards, our results provide promising signals that early experience offers a strong foundation for subsequent reinforcement learning, positioning it as a practical bridge between imitation learning and fully experience-driven agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08558</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:59:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models</title>
|
||||
<link>https://arxiv.org/abs/2510.08559</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08559.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly target general scenarios where perception/recognition is heavily relied on, while with relatively simple reasoning tasks, leading to saturation and thus failing to effectively evaluate advanced multimodal cognitive skills. To address this critical gap, we introduce SciVideoBench, a rigorous benchmark specifically designed to assess advanced video reasoning in scientific contexts. SciVideoBench consists of 1,000 carefully crafted multiple-choice questions derived from cutting-edge scientific experimental videos spanning over 25 specialized academic subjects and verified by a semi-automatic system. Each question demands sophisticated domain-specific knowledge, precise spatiotemporal perception, and intricate logical reasoning, effectively challenging models' higher-order cognitive abilities. Our evaluation highlights significant performance deficits in state-of-the-art proprietary and open-source LMMs, including Gemini 2.5 Pro and Qwen2.5-VL, indicating substantial room for advancement in video reasoning capabilities. Detailed analyses of critical factors such as reasoning complexity and visual grounding provide valuable insights and clear direction for future developments in LMMs, driving the evolution of truly capable multimodal AI co-scientists. We hope SciVideoBench could fit the interests of the community and help to push the boundary of cutting-edge AI for border science.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08559</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:59:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints</title>
|
||||
<link>https://arxiv.org/abs/2510.08565</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li, Jifeng Dai</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training. However, the multimodal scaling property of this paradigm remains difficult to explore due to the separated training. In this paper, we focus on the native training of MLLMs in an end-to-end manner and systematically study its design space and scaling property under a practical setting, i.e., data constraint. Through careful study of various choices in MLLM, we obtain the optimal meta-architecture that best balances performance and training cost. After that, we further explore the scaling properties of the native MLLM and indicate the positively correlated scaling relationship between visual encoders and LLMs. Based on these findings, we propose a native MLLM called NaViL, combined with a simple and cost-effective recipe. Experimental results on 14 multimodal benchmarks confirm the competitive performance of NaViL against existing MLLMs. Besides that, our findings and results provide in-depth insights for the future study of native MLLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08565</guid>
|
||||
<title>How to Teach Large Multimodal Models New Skills</title>
|
||||
<link>https://arxiv.org/abs/2510.08564</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Zhu, Yiming Gong, Yao Xiao, Yaoyao Liu, Derek Hoiem</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. We observe that apparent "forgetting" on held-out tasks after narrow fine-tuning can partly recover at later stages. We trace this behavior to a measurable shift in the output token distribution, manifested through a simple counting-bias probe that co-varies with forgetting. Guided by this picture, we identify two simple, robust tuning recipes that learn strongly while limiting drift: (i) updating only the self-attention projection layers, and (ii) updating only the MLP Gate&Up while freezing the Down projection. Across models and tasks, these choices deliver strong target gains while largely preserving held-out performance. Code is available at https://github.com/jessemelpolio/LMM_CL</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08564</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 17:59:37 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting</title>
|
||||
<link>https://arxiv.org/abs/2510.08696</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunzhen Feng, Parag Jain, Anthony Hartshorn, Yaqi Duan, Julia Kempe</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for improving large language models (LLMs) on reasoning tasks, with Group Relative Policy Optimization (GRPO) widely used in practice. Yet GRPO wastes substantial compute on negative groups: groups in which no sampled response is correct yield zero advantage and thus no gradient. We ask whether negative groups can be leveraged without extra supervision. Starting from a maximum-likelihood (MLE) objective in reward modeling, we show that the MLE gradient is equivalent to a policy gradient for a modified value function. This value function adds a confidence-weighted penalty on incorrect responses, imposing larger penalties on more confident mistakes. We refer to this as Likelihood Estimation with Negative Samples (LENS). LENS modifies GRPO to assign non-zero, confidence-dependent rewards to incorrect generations, making negative groups informative and converting previously wasted samples into useful gradient updates. On the MATH benchmark with Llama-3.1-8B and Qwen-2.5-3B, the proposed variant consistently outperforms GRPO baseline, with significant gains on harder items. These results demonstrate a principled and practical way to "rescue" negative groups, improving efficiency and performance in RLVR.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08696</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 18:01:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution</title>
|
||||
<link>https://arxiv.org/abs/2510.08697</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08697.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra, Marek Suppa, Noah Ziems, Saiteja Utpala, Ming Xu, Guangyu Song, Kaixin Li, Yuhan Cao, Bo Liu, Zheng Liu, Sabina Abdurakhmanova, Wenhao Yu, Mengzhao Jia, Jihan Yao, Kenneth Hamilton, Kumar Shridhar, Minh Chien Vu, Dingmin Wang, Jiawei Liu, Zijian Wang, Qian Liu, Binyuan Hui, Meg Risdal, Ahsen Khaliq, Atin Sood, Zhenchang Xing, Wasi Uddin Ahmad, John Grundy, David Lo, Banghua Zhu, Xiaoning Du, Torsten Scholak, Leandro von Werra</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08697</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 18:01:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities</title>
|
||||
<link>https://arxiv.org/abs/2510.08759</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08759.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Shiji Xin, Yijian Huang, Kai Cheng, Peiheng Wang, Jiazheng Liu, Jiayi Zhang, Yizhe Zhu, Wenqing Wang, Yiran Qin, Xupeng Zhu, Haojie Huang, Lawson L. S. Wong</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Embodied capabilities refer to a suite of fundamental abilities for an agent to perceive, comprehend, and interact with the physical world. While multimodal large language models (MLLMs) show promise as embodied agents, a thorough and systematic evaluation of their embodied capabilities remains underexplored, as existing benchmarks primarily focus on specific domains such as planning or spatial understanding. To bridge this gap, we introduce BEAR, a comprehensive and fine-grained benchmark that evaluates MLLMs on atomic embodied capabilities. BEAR comprises 4,469 interleaved image-video-text entries across 14 domains in 6 categories, including tasks from low-level pointing, trajectory understanding, spatial reasoning, to high-level planning. Extensive evaluation results of 20 representative MLLMs reveal their persistent limitations across all domains of embodied capabilities. To tackle the shortfall, we propose BEAR-Agent, a multimodal conversable agent that integrates pretrained vision models to strengthen MLLM perception, 3D understanding, and planning capabilities. It substantially enhances MLLM performance across diverse embodied capabilities on BEAR, yielding a 9.12% absolute gain and a relative improvement of 17.5% on GPT-5. Furthermore, our experiments indicate that improving MLLM embodied capabilities can benefit embodied tasks in simulated environments. Project website: https://bear-official66.github.io/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08759</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 19:18:36 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review</title>
|
||||
<link>https://arxiv.org/abs/2510.08867</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08867.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gaurav Sahu, Hugo Larochelle, Laurent Charlin, Christopher Pal</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Peer review is the cornerstone of scientific publishing, yet it suffers from inconsistencies, reviewer subjectivity, and scalability challenges. We introduce ReviewerToo, a modular framework for studying and deploying AI-assisted peer review to complement human judgment with systematic and consistent assessments. ReviewerToo supports systematic experiments with specialized reviewer personas and structured evaluation criteria, and can be partially or fully integrated into real conference workflows. We validate ReviewerToo on a carefully curated dataset of 1,963 paper submissions from ICLR 2025, where our experiments with the gpt-oss-120b model achieves 81.8% accuracy for the task of categorizing a paper as accept/reject compared to 83.9% for the average human reviewer. Additionally, ReviewerToo-generated reviews are rated as higher quality than the human average by an LLM judge, though still trailing the strongest expert contributions. Our analysis highlights domains where AI reviewers excel (e.g., fact-checking, literature coverage) and where they struggle (e.g., assessing methodological novelty and theoretical contributions), underscoring the continued need for human expertise. Based on these findings, we propose guidelines for integrating AI into peer-review pipelines, showing how AI can enhance consistency, coverage, and fairness while leaving complex evaluative judgments to domain experts. Our work provides a foundation for systematic, hybrid peer-review systems that scale with the growth of scientific publishing.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08867</guid>
|
||||
<pubDate>Thu, 09 Oct 2025 23:53:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare</title>
|
||||
<link>https://arxiv.org/abs/2510.08872</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08872.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siqi Zhu, David Zhang, Pedro Cisneros-Velarde, Jiaxuan You</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble the prisoner's dilemma, where individually rational choices lead to socially suboptimal outcomes. The fundamental challenge is the lack of a principled decision making mechanism that mutually benefits both the LLM and the user. We propose Game-Theoretic Alignment (GTAlign), an alignment framework that integrates game-theoretic decision making into both reasoning and training. During reasoning, the model explicitly treats user-LLM interaction as a strategic game: it constructs payoff matrices within its reasoning chain to estimate welfare for both itself and the user, and then selects actions that are mutually beneficial. During training, we introduce a mutual welfare reward that reinforces cooperative responses, aligning model behavior with socially efficient outcomes. In addition, we introduce an inference technique that leverages game-theoretic reasoning to dynamically adapt LLM's response when pricing policies of LLM service change. Extensive experiments demonstrate that GTAlign substantially improves reasoning efficiency, answer quality, and mutual welfare compared to baselines across diverse tasks. The code is available at https://github.com/ulab-uiuc/GTAlign .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08872</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 00:05:14 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation</title>
|
||||
<link>https://arxiv.org/abs/2510.08994</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.08994.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yao Teng, Fuyun Wang, Xian Liu, Zhekai Chen, Han Shi, Yu Wang, Zhenguo Li, Weiyang Liu, Difan Zou, Xihui Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to generate a single image. To address this inefficiency, we propose Speculative Jacobi-Denoising Decoding (SJD2), a framework that incorporates the denoising process into Jacobi iterations to enable parallel token generation in autoregressive models. Our method introduces a next-clean-token prediction paradigm that enables the pre-trained autoregressive models to accept noise-perturbed token embeddings and predict the next clean tokens through low-cost fine-tuning. This denoising paradigm guides the model towards more stable Jacobi trajectories. During inference, our method initializes token sequences with Gaussian noise and performs iterative next-clean-token-prediction in the embedding space. We employ a probabilistic criterion to verify and accept multiple tokens in parallel, and refine the unaccepted tokens for the next iteration with the denoising trajectory. Experiments show that our method can accelerate generation by reducing model forward passes while maintaining the visual quality of generated images.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.08994</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 04:30:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs</title>
|
||||
<link>https://arxiv.org/abs/2510.09201</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09201.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yumin Choi, Dongki Kim, Jinheon Baek, Sung Ju Hwang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Large Language Models (LLMs) have shown remarkable success, and their multimodal expansions (MLLMs) further unlock capabilities spanning images, videos, and other modalities beyond text. However, despite this shift, prompt optimization approaches, designed to reduce the burden of manual prompt crafting while maximizing performance, remain confined to text, ultimately limiting the full potential of MLLMs. Motivated by this gap, we introduce the new problem of multimodal prompt optimization, which expands the prior definition of prompt optimization to the multimodal space defined by the pairs of textual and non-textual prompts. To tackle this problem, we then propose the Multimodal Prompt Optimizer (MPO), a unified framework that not only performs the joint optimization of multimodal prompts through alignment-preserving updates but also guides the selection process of candidate prompts by leveraging earlier evaluations as priors in a Bayesian-based selection strategy. Through extensive experiments across diverse modalities that go beyond text, such as images, videos, and even molecules, we demonstrate that MPO outperforms leading text-only optimization methods, establishing multimodal prompt optimization as a crucial step to realizing the potential of MLLMs.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09201</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 09:41:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation</title>
|
||||
<link>https://arxiv.org/abs/2510.09320</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenyao Zhang, Hongsi Liu, Bohan Li, Jiawei He, Zekun Qi, Yunnan Wang, Shengyang Zhao, Xinqiang Yu, Wenjun Zeng, Xin Jin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Current self-supervised monocular depth estimation (MDE) approaches encounter performance limitations due to insufficient semantic-spatial knowledge extraction. To address this challenge, we propose Hybrid-depth, a novel framework that systematically integrates foundation models (e.g., CLIP and DINO) to extract visual priors and acquire sufficient contextual information for MDE. Our approach introduces a coarse-to-fine progressive learning framework: 1) Firstly, we aggregate multi-grained features from CLIP (global semantics) and DINO (local spatial details) under contrastive language guidance. A proxy task comparing close-distant image patches is designed to enforce depth-aware feature alignment using text prompts; 2) Next, building on the coarse features, we integrate camera pose information and pixel-wise language alignment to refine depth predictions. This module seamlessly integrates with existing self-supervised MDE pipelines (e.g., Monodepth2, ManyDepth) as a plug-and-play depth encoder, enhancing continuous depth estimation. By aggregating CLIP's semantic context and DINO's spatial details through language guidance, our method effectively addresses feature granularity mismatches. Extensive experiments on the KITTI benchmark demonstrate that our method significantly outperforms SOTA methods across all metrics, which also indeed benefits downstream tasks like BEV perception. Code is available at https://github.com/Zhangwenyao1/Hybrid-depth.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09320</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 12:20:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>KORMo: Korean Open Reasoning Model for Everyone</title>
|
||||
<link>https://arxiv.org/abs/2510.09426</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minjun Kim, Hyeonseok Lim, Hangyeol Yoo, Inho Won, Seungwoo Song, Minkyung Cho, Junhun Yuk, Changsu Choi, Dongjae Shin, Huige Lee, Hoyun Song, Alice Oh, Kyungtae Lim</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> This work presents the first large-scale investigation into constructing a fully open bilingual large language model (LLM) for a non-English language, specifically Korean, trained predominantly on synthetic data. We introduce KORMo-10B, a 10.8B-parameter model trained from scratch on a Korean-English corpus in which 68.74% of the Korean portion is synthetic. Through systematic experimentation, we demonstrate that synthetic data, when carefully curated with balanced linguistic coverage and diverse instruction styles, does not cause instability or degradation during large-scale pretraining. Furthermore, the model achieves performance comparable to that of contemporary open-weight multilingual baselines across a wide range of reasoning, knowledge, and instruction-following benchmarks. Our experiments reveal two key findings: (1) synthetic data can reliably sustain long-horizon pretraining without model collapse, and (2) bilingual instruction tuning enables near-native reasoning and discourse coherence in Korean. By fully releasing all components including data, code, training recipes, and logs, this work establishes a transparent framework for developing synthetic data-driven fully open models (FOMs) in low-resource settings and sets a reproducible precedent for future multilingual LLM research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09426</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 14:31:25 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols</title>
|
||||
<link>https://arxiv.org/abs/2510.09462</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09462.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study adaptive attacks by an untrusted model that knows the protocol and the monitor model, which is plausible if the untrusted model was trained with a later knowledge cutoff or can search for this information autonomously. We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs. Using this tactic, frontier models consistently evade diverse monitors and complete malicious tasks on two main AI control benchmarks. The attack works universally against current protocols that rely on a monitor. Furthermore, the recent Defer-to-Resample protocol even backfires, as its resampling amplifies the prompt injection and effectively reframes it as a best-of-n attack. In general, adaptive attacks on monitor models represent a major blind spot in current control protocols and should become a standard component of evaluations for future AI control mechanisms.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09462</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 15:12:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs</title>
|
||||
<link>https://arxiv.org/abs/2510.09507</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Zhang, Kanghao Chen, Xingwang Lin, Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Litao Guo, Yinchuan Li, Ying-Cong Chen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysToolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. It assesses capabilities across three distinct difficulty levels: (1) Tool Recognition: Requiring the recognition of a tool's primary function. (2) Tool Understanding: Testing the ability to grasp the underlying principles of a tool's operation. (3) Tool Creation: Challenging the model to fashion a new tool from surrounding objects when conventional options are unavailable. Our comprehensive evaluation of 32 MLLMs-spanning proprietary, open-source, specialized embodied, and backbones in VLAs-reveals a significant deficiency in tool understanding. Furthermore, we provide an in-depth analysis and propose preliminary solutions. Code and dataset are publicly available.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09507</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 16:10:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval</title>
|
||||
<link>https://arxiv.org/abs/2510.09510</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09510.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyue Zhang, Yuan Gao, Xiao Zhou, Yilun Zhao, Tingyu Song, Arman Cohan, Anh Tuan Luu, Chen Zhao</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce MRMR, the first expert-level multidisciplinary multimodal retrieval benchmark requiring intensive reasoning. MRMR contains 1,502 queries spanning 23 domains, with positive documents carefully verified by human experts. Compared to prior benchmarks, MRMR introduces three key advancements. First, it challenges retrieval systems across diverse areas of expertise, enabling fine-grained model comparison across domains. Second, queries are reasoning-intensive, with images requiring deeper interpretation such as diagnosing microscopic slides. We further introduce Contradiction Retrieval, a novel task requiring models to identify conflicting concepts. Finally, queries and documents are constructed as image-text interleaved sequences. Unlike earlier benchmarks restricted to single images or unimodal documents, MRMR offers a realistic setting with multi-image queries and mixed-modality corpus documents. We conduct an extensive evaluation of 4 categories of multimodal retrieval systems and 14 frontier models on MRMR. The text embedding model Qwen3-Embedding with LLM-generated image captions achieves the highest performance, highlighting substantial room for improving multimodal retrieval models. Although latest multimodal models such as Ops-MM-Embedding perform competitively on expert-domain queries, they fall short on reasoning-intensive tasks. We believe that MRMR paves the way for advancing multimodal retrieval in more realistic and challenging scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09510</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 16:14:56 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>StatEval: A Comprehensive Benchmark for Large Language Models in Statistics</title>
|
||||
<link>https://arxiv.org/abs/2510.09517</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09517.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuchen Lu, Run Yang, Yichen Zhang, Shuguang Yu, Runpeng Dai, Ziwei Wang, Jiayi Xiang, Wenxin E, Siran Gao, Xinyao Ruan, Yirui Huang, Chenjing Xi, Haibo Hu, Yueming Fu, Qinglan Yu, Xiaobing Wei, Jiani Gu, Rui Sun, Jiaxuan Jia, Fan Zhou</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable advances in mathematical and logical reasoning, yet statistics, as a distinct and integrative discipline, remains underexplored in benchmarking efforts. To address this gap, we introduce StatEval, the first comprehensive benchmark dedicated to statistics, spanning both breadth and depth across difficulty levels. StatEval consists of 13,817 foundational problems covering undergraduate and graduate curricula, together with 2374 research-level proof tasks extracted from leading journals. To construct the benchmark, we design a scalable multi-agent pipeline with human-in-the-loop validation that automates large-scale problem extraction, rewriting, and quality control, while ensuring academic rigor. We further propose a robust evaluation framework tailored to both computational and proof-based tasks, enabling fine-grained assessment of reasoning ability. Experimental results reveal that while closed-source models such as GPT5-mini achieve below 57\% on research-level problems, with open-source models performing significantly lower. These findings highlight the unique challenges of statistical reasoning and the limitations of current LLMs. We expect StatEval to serve as a rigorous benchmark for advancing statistical intelligence in large language models. All data and code are available on our web platform: https://stateval.github.io/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09517</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 16:28:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Mitigating Overthinking through Reasoning Shaping</title>
|
||||
<link>https://arxiv.org/abs/2510.09535</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09535.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Feifan Song, Shaohang Wei, Bofei Gao, Yejie Wang, Wen Luo, Wei Li, Linli Yao, Weimin Xiong, Liang Chen, Tianyu Liu, Houfeng Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large reasoning models (LRMs) boosted by Reinforcement Learning from Verifier Reward (RLVR) have shown great power in problem solving, yet they often cause overthinking: excessive, meandering reasoning that inflates computational cost. Prior designs of penalization in RLVR manage to reduce token consumption while often harming model performance, which arises from the oversimplicity of token-level supervision. In this paper, we argue that the granularity of supervision plays a crucial role in balancing efficiency and accuracy, and propose Group Relative Segment Penalization (GRSP), a step-level method to regularize reasoning. Since preliminary analyses show that reasoning segments are strongly correlated with token consumption and model performance, we design a length-aware weighting mechanism across segment clusters. Extensive experiments demonstrate that GRSP achieves superior token efficiency without heavily compromising accuracy, especially the advantages with harder problems. Moreover, GRSP stabilizes RL training and scales effectively across model sizes.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09535</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 16:49:03 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AutoPR: Let's Automate Your Academic Promotion!</title>
|
||||
<link>https://arxiv.org/abs/2510.09558</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09558.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiguang Chen, Zheng Yan, Mingda Yang, Libo Qin, Yixin Yuan, Hanjing Li, Jinhao Liu, Yiyan Ji, Dengyun Peng, Jiannan Guan, Mengkang Hu, Yantao Du, Wanxiang Che</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> As the volume of peer-reviewed research surges, scholars increasingly rely on social platforms for discovery, while authors invest considerable effort in promoting their work to ensure visibility and citations. To streamline this process and reduce the reliance on human effort, we introduce Automatic Promotion (AutoPR), a novel task that transforms research papers into accurate, engaging, and timely public content. To enable rigorous evaluation, we release PRBench, a multimodal benchmark that links 512 peer-reviewed articles to high-quality promotional posts, assessing systems along three axes: Fidelity (accuracy and tone), Engagement (audience targeting and appeal), and Alignment (timing and channel optimization). We also introduce PRAgent, a multi-agent framework that automates AutoPR in three stages: content extraction with multimodal preparation, collaborative synthesis for polished outputs, and platform-specific adaptation to optimize norms, tone, and tagging for maximum reach. When compared to direct LLM pipelines on PRBench, PRAgent demonstrates substantial improvements, including a 604% increase in total watch time, a 438% rise in likes, and at least a 2.9x boost in overall engagement. Ablation studies show that platform modeling and targeted promotion contribute the most to these gains. Our results position AutoPR as a tractable, measurable research problem and provide a roadmap for scalable, impactful automated scholarly communication.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09558</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:08:36 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control</title>
|
||||
<link>https://arxiv.org/abs/2510.09561</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09561.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minkyoung Cho, Ruben Ohana, Christian Jacobsen, Adityan Jothi, Min-Hung Chen, Z. Morley Mao, Ethem Can</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Current controllable diffusion models typically rely on fixed architectures that modify intermediate activations to inject guidance conditioned on a new modality. This approach uses a static conditioning strategy for a dynamic, multi-stage denoising process, limiting the model's ability to adapt its response as the generation evolves from coarse structure to fine detail. We introduce TC-LoRA (Temporally Modulated Conditional LoRA), a new paradigm that enables dynamic, context-aware control by conditioning the model's weights directly. Our framework uses a hypernetwork to generate LoRA adapters on-the-fly, tailoring weight modifications for the frozen backbone at each diffusion step based on time and the user's condition. This mechanism enables the model to learn and execute an explicit, adaptive strategy for applying conditional guidance throughout the entire generation process. Through experiments on various data domains, we demonstrate that this dynamic, parametric control significantly enhances generative fidelity and adherence to spatial conditions compared to static, activation-based methods. TC-LoRA establishes an alternative approach in which the model's conditioning strategy is modified through a deeper functional adaptation of its weights, allowing control to align with the dynamic demands of the task and generative stage.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09561</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:13:02 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Dyna-Mind: Learning to Simulate from Experience for Better AI Agents</title>
|
||||
<link>https://arxiv.org/abs/2510.09577</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09577.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiao Yu, Baolin Peng, Michel Galley, Hao Cheng, Qianhui Wu, Janardhan Kulkarni, Suman Nath, Zhou Yu, Jianfeng Gao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web navigation and computer/phone-use. Inspired by literature on human cognition, we argue that current AI agents need ''vicarious trial and error'' - the capacity to mentally simulate alternative futures before acting - in order to enhance their understanding and performance in complex interactive environments. We introduce Dyna-Mind, a two-stage training framework that explicitly teaches (V)LM agents to integrate such simulation into their reasoning. In stage 1, we introduce Reasoning with Simulations (ReSim), which trains the agent to generate structured reasoning traces from expanded search trees built from real experience gathered through environment interactions. ReSim thus grounds the agent's reasoning in faithful world dynamics and equips it with the ability to anticipate future states in its reasoning. In stage 2, we propose Dyna-GRPO, an online reinforcement learning method to further strengthen the agent's simulation and decision-making ability by using both outcome rewards and intermediate states as feedback from real rollouts. Experiments on two synthetic benchmarks (Sokoban and ALFWorld) and one realistic benchmark (AndroidWorld) demonstrate that (1) ReSim effectively infuses simulation ability into AI agents, and (2) Dyna-GRPO leverages outcome and interaction-level signals to learn better policies for long-horizon, planning-intensive tasks. Together, these results highlight the central role of simulation in enabling AI agents to reason, plan, and act more effectively in the ever more challenging environments.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09577</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:30:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models</title>
|
||||
<link>https://arxiv.org/abs/2510.09592</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Donghang Wu, Haoyang Zhang, Jun Chen, Xiangyu, Zhang, Hexin Liu, Eng Siong Chng, Fei Tian, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially. Enabling SLMs to think while speaking, similar to humans, is attracting increasing attention. We present, for the first time, Mind-Paced Speaking (MPS), a brain-inspired framework that enables high-fidelity, real-time reasoning. Similar to how humans utilize distinct brain regions for thinking and responding, we propose a novel dual-brain approach, employing a "Formulation Brain" for high-level reasoning to pace and guide a separate "Articulation Brain" for fluent speech generation. This division of labor eliminates mode-switching, preserving the integrity of the reasoning process. Experiments show that MPS significantly outperforms existing think-while-speaking methods and achieves reasoning performance comparable to models that pre-compute the full CoT before speaking, while drastically reducing latency. Under a zero-latency configuration, the proposed method achieves an accuracy of 92.8% on the mathematical reasoning task Spoken-MQA and attains a score of 82.5 on the speech conversation task URO-Bench. Our work effectively bridges the gap between high-quality reasoning and real-time interaction.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09592</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:50:59 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SpaceVista: All-Scale Visual Spatial Reasoning from mm to km</title>
|
||||
<link>https://arxiv.org/abs/2510.09606</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peiwen Sun, Shiqiang Lang, Dongming Wu, Yi Ding, Kaituo Feng, Huadai Liu, Zhen Ye, Rui Liu, Yun-Hui Liu, Jianan Wang, Xiangyu Yue</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often leads to overfitting to individual scenes. In this paper, we introduce a holistic solution that integrates a structured spatial reasoning knowledge system, scale-aware modeling, and a progressive training paradigm, as the first attempt to broaden the all-scale spatial intelligence of MLLMs to the best of our knowledge. Using a task-specific, specialist-driven automated pipeline, we curate over 38K video scenes across 5 spatial scales to create SpaceVista-1M, a dataset comprising approximately 1M spatial QA pairs spanning 19 diverse task types. While specialist models can inject useful domain knowledge, they are not reliable for evaluation. We then build an all-scale benchmark with precise annotations by manually recording, retrieving, and assembling video-based data. However, naive training with SpaceVista-1M often yields suboptimal results due to the potential knowledge conflict. Accordingly, we introduce SpaceVista-7B, a spatial reasoning model that accepts dense inputs beyond semantics and uses scale as an anchor for scale-aware experts and progressive rewards. Finally, extensive evaluations across 5 benchmarks, including our SpaceVista-Bench, demonstrate competitive performance, showcasing strong generalization across all scales and scenarios. Our dataset, model, and benchmark will be released on https://peiwensun2000.github.io/mm2km .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09606</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:59:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>StreamingVLM: Real-Time Understanding for Infinite Video Streams</title>
|
||||
<link>https://arxiv.org/abs/2510.09608</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.09608.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, Song Han</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we introduce StreamingVLM, a model designed for real-time, stable understanding of infinite visual input. Our approach is a unified framework that aligns training with streaming inference. During inference, we maintain a compact KV cache by reusing states of attention sinks, a short window of recent vision tokens, and a long window of recent text tokens. This streaming ability is instilled via a simple supervised fine-tuning (SFT) strategy that applies full attention on short, overlapped video chunks, which effectively mimics the inference-time attention pattern without training on prohibitively long contexts. For evaluation, we build Inf-Streams-Eval, a new benchmark with videos averaging over two hours that requires dense, per-second alignment between frames and text. On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100. Notably, our SFT strategy also enhances general VQA abilities without any VQA-specific fine-tuning, improving performance on LongVideoBench by +4.30 and OVOBench Realtime by +5.96. Code is available at https://github.com/mit-han-lab/streaming-vlm.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2510.09608</guid>
|
||||
<pubDate>Fri, 10 Oct 2025 17:59:58 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user