diff --git a/feed.xml b/feed.xml index ca8c48c..01db13c 100644 --- a/feed.xml +++ b/feed.xml @@ -7,209 +7,167 @@ http://www.rssboard.org/rss-specification python-feedgen en - Wed, 05 Nov 2025 00:02:46 +0000 + Thu, 06 Nov 2025 00:02:34 +0000 - Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation - https://arxiv.org/abs/2510.22115 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.22115.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ling-Team, Ang Li, Ben Liu, Binbin Hu, Bing Li, Bingwei Zeng, Borui Ye, Caizhi Tang, Changxin Tian, Chao Huang, Chao Zhang, Chen Qian, Chenchen Ju, Chenchen Li, Chengfu Tang, Chili Fu, Chunshao Ren, Chunwei Wu, Cong Zhang, Cunyin Peng, Dafeng Xu, Daixin Wang, Dalong Zhang, Dingnan Jin, Dingyuan Zhu, Dongke Hu, Fangzheng Zhao, Feifan Wu, Feng Zhu, Gangshan Wang, Haitao Zhang, Hailin Zhao, Hanxiao Zhang, Hanzi Wang, Hao Qian, Haoyi Yu, Heng Zhang, Hongliang Zhang, Hongzhi Luan, Huirong Dong, Huizhong Li, Jia Li, Jia Liu, Jialong Zhu, Jian Sha, Jianping Wei, Jiaolong Yang, Jieyue Ma, Jiewei Wu, Jinjing Huang, Jingyun Tian, Jingyuan Zhang, Jinquan Sun, Juanhui Tu, Jun Liu, Jun Xu, Jun Zhou, Junjie Ou, Junpeng Fang, Kaihong Zhang, Kaiqin Hu, Ke Shi, Kun Tang, Kunlong Chen, Lanyin Mei, Lei Liang, Lei Xu, Libo Zhang, Lin Ju, Lin Yuan, Ling Zhong, Lintao Ma, Lu Liu, Lu Yu, Lun Cai, Meiqi Zhu, Mengying Li, Min Chen, Minghao Xue, Minghong Cai, Mingming Yin, Peijie Jiang, Peilong Zhao, Pingping Liu, Qian Zhao, Qing Cui, Qingxiang Huang, Qingyuan Yang, Quankun Yu, Shaowei Wei, Shijie Lian, Shoujian Zheng, Shun Song, Shungen Zhang, Shuo Zhang, Siyuan Li, Song Liu, Ting Guo, Tong Zhao, Wanli Gu, Weichang Wu, Weiguang Han, Wenjing Fang, Wubin Wang, Xiang Shu, Xiao Shi, Xiaoshun Lan, Xiaolu Zhang, Xiaqing Sun, Xin Zhao, Xingyu Lu, Xiong Xu, Xudong Wang, Xudong Wang, Xuemin Yang, Yajie Yang, Yang Xiang, Yanzhe Li, Yi Zhang, Yilong Wang, Yingxue Li, Yongzhen Guo, Yuzhuo Fu, Yuanyuan Wang, Yue Yang, Yue Yu, Yufeng Deng, Yun Zhang, Yunfei Xu, Yuqi Zhang, Yuxiao He, Zengke Gui, Zhaoxin Huan, Zhaoyang Wang, Zhibo Zhu, Zhihao Wang, Zhiqiang Zhang, Zhoufei Wang, Zihang Zeng, Ziqi Liu, Zitao Xuan, Zuoli Tang</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.</p> - https://arxiv.org/abs/2510.22115 - Sat, 25 Oct 2025 01:51:37 +0000 + RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies + https://arxiv.org/abs/2510.17950 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.17950.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adina Yakefu, Bin Xie, Chongyang Xu, Enwen Zhang, Erjin Zhou, Fan Jia, Haitao Yang, Haoqiang Fan, Haowei Zhang, Hongyang Peng, Jing Tan, Junwen Huang, Kai Liu, Kaixin Liu, Kefan Gu, Qinglun Zhang, Ruitao Zhang, Saike Huang, Shen Cheng, Shuaicheng Liu, Tiancai Wang, Tiezhen Wang, Wei Sun, Wenbin Tang, Yajun Wei, Yang Chen, Youqiang Gui, Yucheng Zhao, Yunchao Ma, Yunfei Wei, Yunhuan Yang, Yutong Guo, Ze Chen, Zhengyuan Du, Ziheng Zhang, Ziming Liu, Ziwei Yan</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Testing on real machines is indispensable for robotic control algorithms. In the context of learning-based algorithms, especially VLA models, demand for large-scale evaluation, i.e. testing a large number of models on a large number of tasks, is becoming increasingly urgent. However, doing this right is highly non-trivial, especially when scalability and reproducibility is taken into account. In this report, we describe our methodology for constructing RoboChallenge, an online evaluation system to test robotic control algorithms, and our survey of recent state-of-the-art VLA models using our initial benchmark Table30.</p> + https://arxiv.org/abs/2510.17950 + Mon, 20 Oct 2025 17:59:14 +0000 - The Underappreciated Power of Vision Models for Graph Structural Understanding - https://arxiv.org/abs/2510.24788 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24788.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinjian Zhao, Wei Pang, Zhongkai Xue, Xiangru Jian, Lei Zhang, Yaoyao Xu, Xiaozhuang Song, Shu Wu, Tianshu Yu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Graph Neural Networks operate through bottom-up message-passing, fundamentally differing from human visual perception, which intuitively captures global structures first. We investigate the underappreciated potential of vision models for graph understanding, finding they achieve performance comparable to GNNs on established benchmarks while exhibiting distinctly different learning patterns. These divergent behaviors, combined with limitations of existing benchmarks that conflate domain features with topological understanding, motivate our introduction of GraphAbstract. This benchmark evaluates models' ability to perceive global graph properties as humans do: recognizing organizational archetypes, detecting symmetry, sensing connectivity strength, and identifying critical elements. Our results reveal that vision models significantly outperform GNNs on tasks requiring holistic structural understanding and maintain generalizability across varying graph scales, while GNNs struggle with global pattern abstraction and degrade with increasing graph size. This work demonstrates that vision models possess remarkable yet underutilized capabilities for graph structural understanding, particularly for problems requiring global topological awareness and scale-invariant reasoning. These findings open new avenues to leverage this underappreciated potential for developing more effective graph foundation models for tasks dominated by holistic pattern recognition.</p> - https://arxiv.org/abs/2510.24788 - Mon, 27 Oct 2025 05:11:44 +0000 + D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation + https://arxiv.org/abs/2510.19278 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.19278.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nobline Yoo, Olga Russakovsky, Ye Zhu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary counting networks as external critics to enhance numeracy. However, since these critics must provide gradient guidance during generation, they are restricted to regression-based models that are inherently differentiable, thus excluding detector-based models with superior counting ability, whose count-via-enumeration nature is non-differentiable. To overcome this limitation, we propose Detector-to-Differentiable (D2D), a novel framework that transforms non-differentiable detection models into differentiable critics, thereby leveraging their superior counting ability to guide numeracy generation. Specifically, we design custom activation functions to convert detector logits into soft binary indicators, which are then used to optimize the noise prior at inference time with pre-trained T2I models. Our extensive experiments on SDXL-Turbo, SD-Turbo, and Pixart-DMD across four benchmarks of varying complexity (low-density, high-density, and multi-object scenarios) demonstrate consistent and substantial improvements in object counting accuracy (e.g., boosting up to 13.7% on D2D-Small, a 400-prompt, low-density benchmark), with minimal degradation in overall image quality and computational overhead.</p> + https://arxiv.org/abs/2510.19278 + Wed, 22 Oct 2025 06:27:05 +0000 - MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models - https://arxiv.org/abs/2510.24794 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24794.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, Hongzhu Yi, Yi Chen, Yingjian Zhu, Boran Wang, Hongming Yang, Han Hu, Xu-Yao Zhang, Cheng-Lin Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap, where the model identifies the correct facts during reasoning but fails to incorporate them into the final response, thereby reducing factual fidelity. To address this issue, we propose MR-ALIGN, a Meta-Reasoning informed alignment framework that enhances factuality without relying on external verifiers. MR-ALIGN quantifies state transition probabilities along the model's thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. This re-weighting reshapes token-level signals into probability-aware segment scores, encouraging coherent reasoning trajectories that are more conducive to factual correctness. Empirical evaluations across four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. These results highlight that aligning the reasoning process itself, rather than merely the outputs, is pivotal for advancing factuality in LRMs.</p> - https://arxiv.org/abs/2510.24794 - Mon, 27 Oct 2025 15:00:54 +0000 + RiddleBench: A New Generative Reasoning Benchmark for LLMs + https://arxiv.org/abs/2510.24932 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.24932.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Deepon Halder, Alan Saji, Thanmay Jayakumar, Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models have demonstrated strong performance on many established reasoning benchmarks. However, these benchmarks primarily evaluate structured skills like quantitative problem-solving, leaving a gap in assessing flexible, multifaceted reasoning abilities that are central to human intelligence. These abilities require integrating logical deduction with spatial awareness and constraint satisfaction, which current evaluations do not measure well. To address this, we introduce RiddleBench, a benchmark of 1,737 challenging puzzles in English designed to probe these core reasoning capabilities. Evaluation of state-of-the-art models on RiddleBench shows fundamental weaknesses. Even top proprietary models like Gemini 2.5 Pro, o3, and Claude 4 Sonnet achieve accuracy just above 60% (60.30%, 63.37%, and 63.16%). Analysis further reveals deep failures, including hallucination cascades (accepting flawed reasoning from other models) and poor self-correction due to a strong self-confirmation bias. Their reasoning is also fragile, with performance degrading significantly when constraints are reordered or irrelevant information is introduced. RiddleBench functions as a diagnostic tool for these issues and as a resource for guiding the development of more robust and reliable language models.</p> + https://arxiv.org/abs/2510.24932 + Tue, 28 Oct 2025 19:58:24 +0000 - World Simulation with Video Foundation Models for Physical AI - https://arxiv.org/abs/2511.00062 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00062.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NVIDIA, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao, Prithvijit Chattopadhyay, Mike Chen, Yongxin Chen, Yu Chen, Shuai Cheng, Yin Cui, Jenna Diamond, Yifan Ding, Jiaojiao Fan, Linxi Fan, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Ruiyuan Gao, Yunhao Ge, Jinwei Gu, Aryaman Gupta, Siddharth Gururani, Imad El Hanafi, Ali Hassani, Zekun Hao, Jacob Huffman, Joel Jang, Pooya Jannaty, Jan Kautz, Grace Lam, Xuan Li, Zhaoshuo Li, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Yen-Chen Lin, Huan Ling, Ming-Yu Liu, Xian Liu, Yifan Lu, Alice Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Seungjun Nah, Yashraj Narang, Abhijeet Panaskar, Lindsey Pavao, Trung Pham, Morteza Ramezanali, Fitsum Reda, Scott Reed, Xuanchi Ren, Haonan Shao, Yue Shen, Stella Shi, Shuran Song, Bartosz Stefaniak, Shangkun Sun, Shitao Tang, Sameena Tasmeen, Lyne Tchapmi, Wei-Cheng Tseng, Jibin Varghese, Andrew Z. Wang, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Jiashu Xu, Dinghao Yang, Xiaodong Yang, Haotian Ye, Seonghyeon Ye, Xiaohui Zeng, Jing Zhang, Qinsheng Zhang, Kaiwen Zheng, Andrew Zhu, Yuke Zhu</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5times smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.</p> - https://arxiv.org/abs/2511.00062 - Tue, 28 Oct 2025 22:44:13 +0000 + Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization + https://arxiv.org/abs/2510.25616 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.25616.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikita Kachaev, Mikhail Kolosov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov</p><p><b>Upvotes:</b> 68</p><p><b>Summary:</b> The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for action models with broader generalization. Yet when these VLMs are adapted to the action modality, it remains unclear to what extent their original VL representations and knowledge are preserved. In this work, we conduct a systematic study of representation retention during VLA fine-tuning, showing that naive action fine-tuning leads to degradation of visual representations. To characterize and measure these effects, we probe VLA's hidden representations and analyze attention maps, further, we design a set of targeted tasks and methods that contrast VLA models with their counterpart VLMs, isolating changes in VL capabilities induced by action fine-tuning. We further evaluate a range of strategies for aligning visual representations and introduce a simple yet effective method that mitigates degradation and yields improved generalization to out-of-distribution (OOD) scenarios. Taken together, our analysis clarifies the trade-off between action fine-tuning and the degradation of VL representations and highlights practical approaches to recover inherited VL capabilities. Code is publicly available: https://blind-vla-paper.github.io</p> + https://arxiv.org/abs/2510.25616 + Wed, 29 Oct 2025 15:20:10 +0000 - Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph - https://arxiv.org/abs/2511.00086 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00086.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fali Wang, Jihai Chen, Shuhua Yang, Runxue Bao, Tianxiang Zhao, Zhiwei Zhang, Xianfeng Tang, Hui Liu, Qi He, Suhang Wang</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> Test-Time Scaling (TTS) improves large language models (LLMs) by allocating additional computation during inference, typically through parallel, sequential, or hybrid scaling. However, prior studies often assume fixed collaboration architectures (e.g., topologies) and single-model usage, overlooking that optimal architectures and model combinations can vary across tasks. Therefore, we study the novel problem of searching for compute-optimal model combinations and architectures in TTS under a fixed budget. We formalize it as a multi-LLM collaboration graph, where nodes encode roles and LLM model assignments, and edges capture information flow. This problem is challenging because (i) the combinatorial search space is prohibitively large, and (ii) task-specific requirements demand tailored designs. To address these, we reformulate the problem as probabilistic graph optimization and, through pilot experiments, derive three empirical insights into TTS collaboration graphs. Guided by these insights, we propose Agent-REINFORCE, an LLM-agent-augmented framework that mirrors the REINFORCE pipeline by mapping sampling-gradient-update to sampling-feedback-update, where feedback serves as a textual gradient to update the probabilistic graph and efficiently search for optimal multi-LLM collaboration graphs. Experiments show that Agent-REINFORCE outperforms both traditional and LLM-based baselines in sample efficiency and search performance, and effectively identifies optimal graphs under joint objectives of accuracy and inference latency.</p> - https://arxiv.org/abs/2511.00086 - Wed, 29 Oct 2025 22:14:25 +0000 + Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer + https://arxiv.org/abs/2510.25976 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.25976.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Roman Beliy, Amit Zalcher, Jonathan Kogman, Navve Wasserman, Michal Irani</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reconstructing images seen by people from their fMRI brain recordings provides a non-invasive window into the human brain. Despite recent progress enabled by diffusion models, current methods often lack faithfulness to the actual seen images. We present "Brain-IT", a brain-inspired approach that addresses this challenge through a Brain Interaction Transformer (BIT), allowing effective interactions between clusters of functionally-similar brain-voxels. These functional-clusters are shared by all subjects, serving as building blocks for integrating information both within and across brains. All model components are shared by all clusters & subjects, allowing efficient training with a limited amount of data. To guide the image reconstruction, BIT predicts two complementary localized patch-level image features: (i)high-level semantic features which steer the diffusion model toward the correct semantic content of the image; and (ii)low-level structural features which help to initialize the diffusion process with the correct coarse layout of the image. BIT's design enables direct flow of information from brain-voxel clusters to localized image features. Through these principles, our method achieves image reconstructions from fMRI that faithfully reconstruct the seen images, and surpass current SotA approaches both visually and by standard objective metrics. Moreover, with only 1-hour of fMRI data from a new subject, we achieve results comparable to current methods trained on full 40-hour recordings.</p> + https://arxiv.org/abs/2510.25976 + Wed, 29 Oct 2025 21:21:54 +0000 - PHUMA: Physically-Grounded Humanoid Locomotion Dataset - https://arxiv.org/abs/2510.26236 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.26236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kyungmin Lee, Sibeen Kim, Minho Park, Hyunseung Kim, Dongyoon Hwang, Hojoon Lee, Jaegul Choo</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Motion imitation is a promising approach for humanoid locomotion, enabling agents to acquire humanlike behaviors. Existing methods typically rely on high-quality motion capture datasets such as AMASS, but these are scarce and expensive, limiting scalability and diversity. Recent studies attempt to scale data collection by converting large-scale internet videos, exemplified by Humanoid-X. However, they often introduce physical artifacts such as floating, penetration, and foot skating, which hinder stable imitation. In response, we introduce PHUMA, a Physically-grounded HUMAnoid locomotion dataset that leverages human video at scale, while addressing physical artifacts through careful data curation and physics-constrained retargeting. PHUMA enforces joint limits, ensures ground contact, and eliminates foot skating, producing motions that are both large-scale and physically reliable. We evaluated PHUMA in two sets of conditions: (i) imitation of unseen motion from self-recorded test videos and (ii) path following with pelvis-only guidance. In both cases, PHUMA-trained policies outperform Humanoid-X and AMASS, achieving significant gains in imitating diverse motions. The code is available at https://davian-robotics.github.io/PHUMA.</p> - https://arxiv.org/abs/2510.26236 - Thu, 30 Oct 2025 08:13:12 +0000 + iFlyBot-VLA Technical Report + https://arxiv.org/abs/2511.01914 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01914.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuan Zhang, Chenyu Xue, Wenjie Xu, Chao Ji, Jiajia wu, Jia Pan</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce iFlyBot-VLA, a large-scale Vision-Language-Action (VLA) model trained under a novel framework. The main contributions are listed as follows: (1) a latent action model thoroughly trained on large-scale human and robotic manipulation videos; (2) a dual-level action representation framework that jointly supervises both the Vision-Language Model (VLM) and the action expert during training; (3) a mixed training strategy that combines robot trajectory data with general QA and spatial QA datasets, effectively enhancing the 3D perceptual and reasoning capabilities of the VLM backbone. Specifically, the VLM is trained to predict two complementary forms of actions: latent actions, derived from our latent action model pretrained on cross-embodiment manipulation data, which capture implicit high-level intentions; and structured discrete action tokens, obtained through frequency-domain transformations of continuous control signals, which encode explicit low-level dynamics. This dual supervision aligns the representation spaces of language, vision, and action, enabling the VLM to directly contribute to action generation. Experimental results on the LIBERO Franka benchmark demonstrate the superiority of our frame-work, while real-world evaluations further show that iFlyBot-VLA achieves competitive success rates across diverse and challenging manipulation tasks. Furthermore, we plan to open-source a portion of our self-constructed dataset to support future research in the community</p> + https://arxiv.org/abs/2511.01914 + Sat, 01 Nov 2025 06:24:56 +0000 - Data-Efficient RLVR via Off-Policy Influence Guidance - https://arxiv.org/abs/2510.26491 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.26491.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data selection methods are largely heuristic-based, lacking theoretical guarantees and generalizability. This work proposes a theoretically-grounded approach using influence functions to estimate the contribution of each data point to the learning objective. To overcome the prohibitive computational cost of policy rollouts required for online influence estimation, we introduce an off-policy influence estimation method that efficiently approximates data influence using pre-collected offline trajectories. Furthermore, to manage the high-dimensional gradients of LLMs, we employ sparse random projection to reduce dimensionality and improve storage and computation efficiency. Leveraging these techniques, we develop Curriculum RL with Off-Policy Influence guidance (CROPI), a multi-stage RL framework that iteratively selects the most influential data for the current policy. Experiments on models up to 7B parameters demonstrate that CROPI significantly accelerates training. On a 1.5B model, it achieves a 2.66x step-level acceleration while using only 10\% of the data per stage compared to full-dataset training. Our results highlight the substantial potential of influence-based data selection for efficient RLVR.</p> - https://arxiv.org/abs/2510.26491 - Thu, 30 Oct 2025 13:40:52 +0000 + CodeClash: Benchmarking Goal-Oriented Software Engineering + https://arxiv.org/abs/2511.00839 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00839.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> John Yang, Kilian Lieret, Joyce Yang, Carlos E. Jimenez, Ofir Press, Ludwig Schmidt, Diyi Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targeted tests. However, human programmers do not spend all day incessantly addressing isolated tasks. Instead, real-world software development is grounded in the pursuit of high-level goals, like improving user retention or reducing costs. Evaluating whether LMs can also iteratively develop code to better accomplish open-ended objectives without any explicit guidance remains an open challenge. To address this, we introduce CodeClash, a benchmark where LMs compete in multi-round tournaments to build the best codebase for achieving a competitive objective. Each round proceeds in two phases: agents edit their code, then their codebases compete head-to-head in a code arena that determines winners based on objectives like score maximization, resource acquisition, or survival. Whether it's writing notes, scrutinizing documentation, analyzing competition logs, or creating test suites, models must decide for themselves how to improve their codebases both absolutely and against their opponents. We run 1680 tournaments (25,200 rounds total) to evaluate 8 LMs across 6 arenas. Our results reveal that while models exhibit diverse development styles, they share fundamental limitations in strategic reasoning. Models also struggle with long-term codebase maintenance, as repositories become progressively messy and redundant. These limitations are stark: top models lose every round against expert human programmers. We open-source CodeClash to advance the study of autonomous, goal-oriented code development.</p> + https://arxiv.org/abs/2511.00839 + Sun, 02 Nov 2025 07:42:51 +0000 - Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench - https://arxiv.org/abs/2510.26865 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.26865.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fenfen Lin, Yesheng Liu, Haiyu Xu, Chen Yue, Zheqi He, Mingxuan Zhao, Miguel Hu Chen, Jiakang Liu, JG Yao, Xi Yang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work, we introduce MeasureBench, a benchmark on visual measurement reading covering both real-world and synthesized images of various types of measurements, along with an extensible pipeline for data synthesis. Our pipeline procedurally generates a specified type of gauge with controllable visual appearance, enabling scalable variation in key details such as pointers, scales, fonts, lighting, and clutter. Evaluation on popular proprietary and open-weight VLMs shows that even the strongest frontier VLMs struggle measurement reading in general. A consistent failure mode is indicator localization: models can read digits or labels but misidentify the key positions of pointers or alignments, leading to big numeric errors despite plausible textual reasoning. We have also conducted preliminary experiments with reinforcement learning over synthetic data, and find encouraging results on in-domain synthetic subset but less promising for real-world images. Our analysis highlights a fundamental limitation of current VLMs in fine-grained spatial grounding. We hope this resource can help future advances on visually grounded numeracy and precise spatial perception of VLMs, bridging the gap between recognizing numbers and measuring the world.</p> - https://arxiv.org/abs/2510.26865 - Thu, 30 Oct 2025 17:20:51 +0000 + Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR + https://arxiv.org/abs/2511.01937 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01937.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abdelaziz Bounhar, Hadi Abdine, Evan Dufraisse, Ahmad Chamma, Amr Mohamed, Dani Bouch, Michalis Vazirgiannis, Guokan Shang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training efficiency, leaving the model to train primarily on harder problems that require longer reasoning chains. This skews the output length distribution upward, resulting in a model that conflates ``thinking longer'' with ``thinking better''. In this work, we show that retaining and modestly up-weighting moderately easy problems acts as an implicit length regularizer. Exposing the model to solvable short-chain tasks constrains its output distribution and prevents runaway verbosity. The result is \emph{emergent brevity for free}: the model learns to solve harder problems without inflating the output length, despite the absence of any explicit length penalization. RLVR experiments using this approach on Qwen3-4B-Thinking-2507 (with a 16k token limit) achieve baseline pass@1 AIME25 accuracy while generating solutions that are, on average, nearly twice as short. The code is available at https://github.com/MBZUAI-Paris/Frugal-AI{GitHub}, with datasets and models on https://huggingface.co/collections/MBZUAI-Paris/k2-think-mini-68dcfa8b114686a4bd3dc2bc{Hugging Face}.</p> + https://arxiv.org/abs/2511.01937 + Sun, 02 Nov 2025 17:29:16 +0000 - NaviTrace: Evaluating Embodied Navigation of Vision-Language Models - https://arxiv.org/abs/2510.26909 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.26909.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tim Windecker, Manthan Patel, Moritz Reuss, Richard Schwarzkopf, Cesar Cadena, Rudolf Lioutikov, Marco Hutter, Jonas Frey</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Vision-language models demonstrate unprecedented performance and generalization across a wide range of tasks and scenarios. Integrating these foundation models into robotic navigation systems opens pathways toward building general-purpose robots. Yet, evaluating these models' navigation capabilities remains constrained by costly real-world trials, overly simplified simulations, and limited benchmarks. We introduce NaviTrace, a high-quality Visual Question Answering benchmark where a model receives an instruction and embodiment type (human, legged robot, wheeled robot, bicycle) and must output a 2D navigation trace in image space. Across 1000 scenarios and more than 3000 expert traces, we systematically evaluate eight state-of-the-art VLMs using a newly introduced semantic-aware trace score. This metric combines Dynamic Time Warping distance, goal endpoint error, and embodiment-conditioned penalties derived from per-pixel semantics and correlates with human preferences. Our evaluation reveals consistent gap to human performance caused by poor spatial grounding and goal localization. NaviTrace establishes a scalable and reproducible benchmark for real-world robotic navigation. The benchmark and leaderboard can be found at https://leggedrobotics.github.io/navitrace_webpage/.</p> - https://arxiv.org/abs/2510.26909 - Thu, 30 Oct 2025 18:16:32 +0000 + Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation + https://arxiv.org/abs/2511.01450 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01450.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jie Du, Xinyu Gong, Qingshan Tan, Wen Li, Yangming Cheng, Weitao Wang, Chenlu Zhan, Suhui Wu, Hao Zhang, Jun Zhang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largely follow image-domain paradigms and are mainly developed on small-scale models (approximately 2B parameters), limiting their ability to address the unique challenges of video tasks, such as costly data construction, unstable training, and heavy memory consumption. To overcome these limitations, we introduce a GT-Pair that automatically builds high-quality preference pairs by using real videos as positives and model-generated videos as negatives, eliminating the need for any external annotation. We further present Reg-DPO, which incorporates the SFT loss as a regularization term into the DPO objective to enhance training stability and generation fidelity. Additionally, by combining the FSDP framework with multiple memory optimization techniques, our approach achieves nearly three times higher training capacity than using FSDP alone. Extensive experiments on both I2V and T2V tasks across multiple datasets demonstrate that our method consistently outperforms existing approaches, delivering superior video generation quality.</p> + https://arxiv.org/abs/2511.01450 + Mon, 03 Nov 2025 11:04:22 +0000 - ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use - https://arxiv.org/abs/2510.27363 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.27363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengjie Deng, Guanting Dong, Zhicheng Dou</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of multimodal information, enabling multimodal large language models (MLLMs) to flexibly and efficiently utilize external tools during reasoning remains an underexplored challenge. In this work, we introduce ToolScope, an agentic framework designed to unify global planning with local multimodal perception, adopting a specialized Perceive tool to mitigates visual context degradation in long-horizon VQA task. ToolScope comprises three primary components: the Global Navigator, the Agentic Executor, and the Response Synthesizer. The Global Navigator functions as a "telescope", offering high-level strategic guidance. The Agentic Executor operates iteratively to augment MLLM with local perception through the integration of external tools-Search, Code, and Perceive. Finally, the Response Synthesizer consolidates and organizes the reasoning process into a coherent, user-friendly output. We evaluate ToolScope on four VQA benchmarks across diverse domains, including VQA 2.0, ScienceQA, MAT-Search and MathVista. It demonstrates strong generalization capabilities, achieving an average performance improvement of up to +6.69% across all datasets.</p> - https://arxiv.org/abs/2510.27363 - Fri, 31 Oct 2025 10:51:27 +0000 + Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning + https://arxiv.org/abs/2511.01502 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01502.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengtan Zhang, Zizhan Guo, Hongbo Zhao, Yi Feng, Zuyi Xiong, Yue Wang, Shaoyi Du, Hanli Wang, Rui Fan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Unsupervised learning of depth and ego-motion, two fundamental 3D perception tasks, has made significant strides in recent years. However, most methods treat ego-motion as an auxiliary task, either mixing all motion types or excluding depth-independent rotational motions in supervision. Such designs limit the incorporation of strong geometric constraints, reducing reliability and robustness under diverse conditions. This study introduces a discriminative treatment of motion components, leveraging the geometric regularities of their respective rigid flows to benefit both depth and ego-motion estimation. Given consecutive video frames, network outputs first align the optical axes and imaging planes of the source and target cameras. Optical flows between frames are transformed through these alignments, and deviations are quantified to impose geometric constraints individually on each ego-motion component, enabling more targeted refinement. These alignments further reformulate the joint learning process into coaxial and coplanar forms, where depth and each translation component can be mutually derived through closed-form geometric relationships, introducing complementary constraints that improve depth robustness. DiMoDE, a general depth and ego-motion joint learning framework incorporating these designs, achieves state-of-the-art performance on multiple public datasets and a newly collected diverse real-world dataset, particularly under challenging conditions. Our source code will be publicly available at mias.group/DiMoDE upon publication.</p> + https://arxiv.org/abs/2511.01502 + Mon, 03 Nov 2025 12:14:52 +0000 - EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities - https://arxiv.org/abs/2510.27545 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.27545.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Travis Davies, Yiqi Huang, Alexi Gladstone, Yunxin Liu, Xiang Chen, Heng Ji, Huxian Liu, Luhui Hu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Implicit policies parameterized by generative models, such as Diffusion Policy, have become the standard for policy learning and Vision-Language-Action (VLA) models in robotics. However, these approaches often suffer from high computational cost, exposure bias, and unstable inference dynamics, which lead to divergence under distribution shifts. Energy-Based Models (EBMs) address these issues by learning energy landscapes end-to-end and modeling equilibrium dynamics, offering improved robustness and reduced exposure bias. Yet, policies parameterized by EBMs have historically struggled to scale effectively. Recent work on Energy-Based Transformers (EBTs) demonstrates the scalability of EBMs to high-dimensional spaces, but their potential for solving core challenges in physically embodied models remains underexplored. We introduce a new energy-based architecture, EBT-Policy, that solves core issues in robotic and real-world settings. Across simulated and real-world tasks, EBT-Policy consistently outperforms diffusion-based policies, while requiring less training and inference computation. Remarkably, on some tasks it converges within just two inference steps, a 50x reduction compared to Diffusion Policy's 100. Moreover, EBT-Policy exhibits emergent capabilities not seen in prior models, such as zero-shot recovery from failed action sequences using only behavior cloning and without explicit retry training. By leveraging its scalar energy for uncertainty-aware inference and dynamic compute allocation, EBT-Policy offers a promising path toward robust, generalizable robot behavior under distribution shifts.</p> - https://arxiv.org/abs/2510.27545 - Fri, 31 Oct 2025 15:21:05 +0000 + TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data + https://arxiv.org/abs/2511.02219 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02219.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Changjiang Jiang, Fengchang Yu, Haihua Chen, Wei Lu, Jin Zeng</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose \method, a framework consisting of: (1) a query decomposer that breaks down complex questions, (2) a table sanitizer that cleans and filters noisy tables, and (3) a program-of-thoughts (PoT)-based reasoner that generates executable code to derive the final answer from the sanitized table. To ensure unbiased evaluation and mitigate data leakage, we introduce a new dataset, CalTab151, specifically designed for complex numerical reasoning over tables. Experimental results demonstrate that \method consistently outperforms existing methods, achieving state-of-the-art (SOTA) performance with 8.79%, 6.08%, and 19.87% accuracy improvement on TAT-QA, TableBench, and \method, respectively. Moreover, our framework integrates seamlessly with mainstream LLMs, providing a robust solution for complex tabular numerical reasoning. These findings highlight the effectiveness of our framework in enhancing LLM performance for complex tabular numerical reasoning. Data and code are available upon request.</p> + https://arxiv.org/abs/2511.02219 + Tue, 04 Nov 2025 03:13:02 +0000 - Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum - https://arxiv.org/abs/2510.27571 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2510.27571.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoning Guo, Mingxin Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Xiaowen Chu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> The prevailing video retrieval paradigm is structurally misaligned, as narrow benchmarks incentivize correspondingly limited data and single-task training. Therefore, universal capability is suppressed due to the absence of a diagnostic evaluation that defines and demands multi-dimensional generalization. To break this cycle, we introduce a framework built on the co-design of evaluation, data, and modeling. First, we establish the Universal Video Retrieval Benchmark (UVRB), a suite of 16 datasets designed not only to measure performance but also to diagnose critical capability gaps across tasks and domains. Second, guided by UVRB's diagnostics, we introduce a scalable synthesis workflow that generates 1.55 million high-quality pairs to populate the semantic space required for universality. Finally, we devise the Modality Pyramid, a curriculum that trains our General Video Embedder (GVE) by explicitly leveraging the latent interconnections within our diverse data. Extensive experiments show GVE achieves state-of-the-art zero-shot generalization on UVRB. In particular, our analysis reveals that popular benchmarks are poor predictors of general ability and that partially relevant retrieval is a dominant but overlooked scenario. Overall, our co-designed framework provides a practical path to escape the limited scope and advance toward truly universal video retrieval.</p> - https://arxiv.org/abs/2510.27571 - Fri, 31 Oct 2025 15:54:48 +0000 + When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs + https://arxiv.org/abs/2511.02243 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02243.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoran Zhang, Tengyue Wang, Xilin Gong, Yang Shi, Haotian Wang, Di Wang, Lijie Hu</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Multimodal large language models (MLLMs) must resolve conflicts when different modalities provide contradictory information, a process we term modality following. Prior work measured this behavior only with coarse dataset-level statistics, overlooking the influence of model's confidence in unimodal reasoning. In this paper, we introduce a new framework that decomposes modality following into two fundamental factors: relative reasoning uncertainty (the case-specific confidence gap between unimodal predictions) and inherent modality preference( a model's stable bias when uncertainties are balanced). To validate this framework, we construct a controllable dataset that systematically varies the reasoning difficulty of visual and textual inputs. Using entropy as a fine-grained uncertainty metric, we uncover a universal law: the probability of following a modality decreases monotonically as its relative uncertainty increases. At the relative difficulty level where the model tends to follow both modalities with comparable probability what we call the balance point, a practical indicator of the model's inherent preference. Unlike traditional macro-level ratios, this measure offers a more principled and less confounded way to characterize modality bias, disentangling it from unimodal capabilities and dataset artifacts. Further, by probing layer-wise predictions, we reveal the internal mechanism of oscillation: in ambiguous regions near the balance point, models vacillate between modalities across layers, explaining externally observed indecision. Together, these findings establish relative uncertainty and inherent preference as the two governing principles of modality following, offering both a quantitative framework and mechanistic insight into how MLLMs resolve conflicting information.</p> + https://arxiv.org/abs/2511.02243 + Tue, 04 Nov 2025 04:11:31 +0000 - LongCat-Flash-Omni Technical Report - https://arxiv.org/abs/2511.00279 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00279.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meituan LongCat Team, Bairui Wang, Bayan, Bin Xiao, Bo Zhang, Bolin Rong, Borun Chen, Chang Wan, Chao Zhang, Chen Huang, Chen Chen, Chen Chen, Chengxu Yang, Chengzuo Yang, Cong Han, Dandan Peng, Delian Ruan, Detai Xin, Disong Wang, Dongchao Yang, Fanfan Liu, Fengjiao Chen, Fengyu Yang, Gan Dong, Gang Huang, Gang Xu, Guanglu Wan, Guoqiang Tan, Guoqiao Yu, Haibo Qiu, Hao Lu, Hongbo Liu, Hongyu Xiang, Jiaheng Wu, Jian Yang, Jiaxing Liu, Jing Huang, Jingang Wang, Jinrui Ding, Juchao Jiang, Jun Kuang, Jun Wang, Junhui Mei, Ke Ding, Kefeng Zhang, Lei Chen, Liang Shi, Limeng Qiao, Liming Zheng, Lin Ma, Liuyang Guo, Liya Ma, Luying Sun, Man Gao, Mengshen Zhu, Miao Cao, Minliang Lin, Nuo Xu, Peng Shi, Qi Zhang, Qian Fang, Qian Wang, Qian Yang, Quanxiu Wang, Rongxiang Weng, Rongxin Guo, Ruoxuan Liang, Senbin Yang, Shanbo Xu, Shanglin Lei, Shengze Ye, Shimin Chen, Shuaiqi Chen, Shujie Hu, Shuo Li, Siqi Yang, Siyu Xu, Siyu Ren, Song Li, Songxiang Liu, Tianhao Bai, Tianye Dai, Wei Hong, Wei Wang, Weixiao Zhao, Wengang Cao, Wenlong Zhu, Wenlong He, Xi Su, Xi Nan, Xiaohan Zhao, Xiaohao Wang, Xiaoyu Zhao, Xiaoyu Wang, Xiaoyu Li, Xin Pan, Xin Chen, Xiusong Sun, Xu Xiang, Xudong Xing, Xuezhi Cao, Xunliang Cai, Yang Yang, Yanli Tan, Yao Yao, Yerui Sun, Yi Chen, Yifan Lu, Yin Gong, Yining Zhang, Yitian Chen, Yiyang Gan, Yuchen Tang, Yuchen Xie, Yueqian Wang, Yuewen Zheng, Yufei Zhang, Yufeng Zhong, Yulei Qian, Yuqi Peng, Yuwei Jiang, Zeyang Hu, Zheng Zhang, Zhengkun Tian, Zhiqing Hong, Zhixiong Zeng, Zhuqi Mi, Ziran Li, Ziwen Wang, Ziyi Zhao, Ziyuan Zhuang, Zizhe Zhao</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.</p> - https://arxiv.org/abs/2511.00279 - Fri, 31 Oct 2025 21:58:15 +0000 + LTD-Bench: Evaluating Large Language Models by Letting Them Draw + https://arxiv.org/abs/2511.02347 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02347.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liuhao Lin, Ke Li, Zihan Xu, Yuchen Shi, Yulei Qin, Yan Zhang, Xing Sun, Rongrong Ji</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research--relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive understanding of model capabilities. This deficiency creates a dangerous disconnect between reported performance and practical abilities, particularly for applications requiring physical world understanding. We introduce LTD-Bench, a breakthrough benchmark that transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code. This approach makes spatial reasoning limitations immediately apparent even to non-experts, bridging the fundamental gap between statistical performance and intuitive assessment. LTD-Bench implements a comprehensive methodology with complementary generation tasks (testing spatial imagination) and recognition tasks (assessing spatial perception) across three progressively challenging difficulty levels, methodically evaluating both directions of the critical language-spatial mapping. Our extensive experiments with state-of-the-art models expose an alarming capability gap: even LLMs achieving impressive results on traditional benchmarks demonstrate profound deficiencies in establishing bidirectional mappings between language and spatial concept--a fundamental limitation that undermines their potential as genuine world models. Furthermore, LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.</p> + https://arxiv.org/abs/2511.02347 + Tue, 04 Nov 2025 08:11:23 +0000 - UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings - https://arxiv.org/abs/2511.00405 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, Jinsong Su</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation paradigm. In this work, we pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm. We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy: a cold-start supervised fine-tuning equips the model with reasoning capabilities and enables it to generate both discriminative and generative embeddings; a subsequent reinforcement learning enhances reasoning and further optimizes generative embedding quality. This pioneering work reveals four key insights: 1) generative embeddings unlock substantial performance gains over conventional discriminative embeddings by leveraging the powerful generative reasoning capabilities of MLLMs; 2) discriminative and generative embeddings are complementary, whose combined oracle performance far exceeding that of either alone; 3) RL can effectively enhance generative embeddings, establishing a scalable optimization paradigm.; 4) repeated sampling at inference boosts downstream task coverage (pass@k), highlighting the inference-time scalability potential of generative embeddings. Evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents, UME-R1 significantly outperforms conventional discriminative embedding models and offers a foundation for more interpretable, reasoning-driven generative multimodal embeddings. Our code, models, and datasets will be publicly available at https://github.com/XMUDeepLIT/UME-R1.</p> - https://arxiv.org/abs/2511.00405 - Sat, 01 Nov 2025 05:04:23 +0000 + LiveSecBench: A Dynamic and Culturally-Relevant AI Safety Benchmark for LLMs in Chinese Context + https://arxiv.org/abs/2511.02366 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02366.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yudong Li, Zhongliang Yang, Kejiang Chen, Wenxuan Wang, Tianxin Zhang, Sifang Wan, Kecheng Wang, Haitian Li, Xu Wang, Lefan Cheng, Youdan Yang, Baocheng Chen, Ziyu Liu, Yufei Sun, Liyan Wu, Wenya Wen, Xingchi Gu, Peiru Yang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> In this work, we propose LiveSecBench, a dynamic and continuously updated safety benchmark specifically for Chinese-language LLM application scenarios. LiveSecBench evaluates models across six critical dimensions (Legality, Ethics, Factuality, Privacy, Adversarial Robustness, and Reasoning Safety) rooted in the Chinese legal and social frameworks. This benchmark maintains relevance through a dynamic update schedule that incorporates new threat vectors, such as the planned inclusion of Text-to-Image Generation Safety and Agentic Safety in the next update. For now, LiveSecBench (v251030) has evaluated 18 LLMs, providing a landscape of AI safety in the context of Chinese language. The leaderboard is publicly accessible at https://livesecbench.intokentech.cn/.</p> + https://arxiv.org/abs/2511.02366 + Tue, 04 Nov 2025 08:44:09 +0000 - OpenSIR: Open-Ended Self-Improving Reasoner - https://arxiv.org/abs/2511.00602 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wai-Chung Kwan, Joshua Ong Jun Leang, Pavlos Vougiouklis, Jeff Z. Pan, Marco Valentino, Pasquale Minervini</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass human-level performance. While self-play offers a promising alternative, existing approaches depend on external verifiers or cannot learn open-endedly. We present Open-Ended Self-Improving Reasoner (OpenSIR), a self-play framework where an LLM learns to generate and solve novel problems by alternating teacher and student roles without external supervision. To generate novel problems, OpenSIR optimises for both difficulty and diversity, rewarding problems that challenge appropriately while exploring distinct concepts, enabling open-ended mathematical discovery. Starting from a single trivial seed problem, OpenSIR substantially improves instruction models: Llama-3.2-3B-Instruct advances from 73.9 to 78.3 on GSM8K, and from 28.8 to 34.4 on College Math, while Gemma-2-2B-Instruct rises from 38.5 to 58.7 on GSM8K. Our analyses reveal that OpenSIR achieves open-ended learning through co-evolving teacher-student roles that adaptively calibrate difficulty and drive diverse exploration, progressing autonomously from basic to advanced mathematics.</p> - https://arxiv.org/abs/2511.00602 - Sat, 01 Nov 2025 16:08:28 +0000 + AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda + https://arxiv.org/abs/2511.02374 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02374.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohd Nauman, Sravan Gvm, Vijay Devane, Shyam Pawar, Viraj Thakur, Kundeshwar Pundalik, Piyush Sawarkar, Rohit Saluja, Maunendra Desarkar, Ganesh Ramakrishnan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cultural, linguistic, and subject-matter expertise. In particular, traditional medical systems such as Ayurveda embody centuries of nuanced textual and clinical knowledge that mainstream LLMs fail to accurately interpret or apply. We introduce AyurParam-2.9B, a domain-specialized, bilingual language model fine-tuned from Param-1-2.9B using an extensive, expertly curated Ayurveda dataset spanning classical texts and clinical guidance. AyurParam's dataset incorporates context-aware, reasoning, and objective-style Q&A in both English and Hindi, with rigorous annotation protocols for factual precision and instructional clarity. Benchmarked on BhashaBench-Ayur, AyurParam not only surpasses all open-source instruction-tuned models in its size class (1.5--3B parameters), but also demonstrates competitive or superior performance compared to much larger models. The results from AyurParam highlight the necessity for authentic domain adaptation and high-quality supervision in delivering reliable, culturally congruent AI for specialized medical knowledge.</p> + https://arxiv.org/abs/2511.02374 + Tue, 04 Nov 2025 08:53:21 +0000 - GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding - https://arxiv.org/abs/2511.00810 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.00810.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shijie Zhou, Viet Dac Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Graphical user interface (GUI) grounding is a key function of computer-use agents, which maps natural-language instructions to actionable screen regions. Existing approaches based on Multimodal Large Language Models (MLLMs) typically formulate it as a text-based coordinate generation task, yet directly generating precise coordinates from visual inputs remains challenging and computationally intensive. An intuitive way to implement GUI grounding is to first select visual patches relevant to the instructions and then determine the precise click location within those patches. Based on the observations that general MLLMs have some native grounding capability, nested within their attentions, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 85k screenshots, demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 58.6% on ScreenSpot-Pro and 62.2% on OSWorld-G. Project page: https://github.com/sjz5202/GUI-AIMA</p> - https://arxiv.org/abs/2511.00810 - Sun, 02 Nov 2025 05:34:21 +0000 + ChartM^3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension + https://arxiv.org/abs/2511.02415 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02415.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duo Xu, Hao Cheng, Xin Lin, Zhen Xie, Hao Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Complex chart understanding tasks demand advanced visual recognition and reasoning capabilities from multimodal large language models (MLLMs). However, current research provides limited coverage of complex chart scenarios and computation-intensive reasoning tasks prevalent in real-world applications. This study proposes an automated multi-stage code-driven pipeline for systematically generating visual reasoning datasets to address these limitations. The pipeline integrates retrieval-augmented generation (RAG) to retrieve professional chart templates and employs chain-of-thought (CoT) strategies to generate reasoning codes that simulate real data distributions, thereby driving chart rendering and question-related statistical computations. Through model-based evaluation, the pipeline enhances chart diversity and data quality. Using this framework, we construct ChartM^3, a multi-dimensional and multi-step dataset containing 38K charts and 142K Q&A pairs for training, along with 2,871 high-quality evaluation samples for enabling practical performance assessment. Supervised fine-tuning (SFT) and reinforcement learning (RL) experiments demonstrate that our dataset significantly improves reasoning capabilities and cross-domain generalization performance, enabling smaller models to achieve performance comparable to larger-scale models in complex chart comprehension.</p> + https://arxiv.org/abs/2511.02415 + Tue, 04 Nov 2025 09:45:34 +0000 - ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation - https://arxiv.org/abs/2511.01163 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01163.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongyuan Liang, Wei Chow, Feng Li, Ziqiao Ma, Xiyao Wang, Jiageng Mao, Jiuhai Chen, Jiatao Gu, Yue Wang, Furong Huang</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat these abilities in isolation, such that tasks with multimodal inputs and outputs are scored primarily through unimodal reasoning, i.e., textual benchmarks emphasize language-based reasoning, while visual benchmarks emphasize reasoning outcomes manifested in the pixels. We introduce ROVER to address this pressing need to test reciprocal cross-modal reasoning, the use of one modality to guide, verify, or refine outputs in the other, an ability central to the vision of unified multimodal intelligence. ROVER is a human-annotated benchmark that explicitly targets reciprocal cross-modal reasoning, which contains 1312 tasks grounded in 1876 images, spanning two complementary settings. Verbally-augmented reasoning for visual generation evaluates whether models can use verbal prompts and reasoning chains to guide faithful image synthesis. Visually-augmented reasoning for verbal generation evaluates whether models can generate intermediate visualizations that strengthen their own reasoning processes for question answering. Experiments on 17 unified models reveal two key findings: (i) Cross-modal reasoning determines visual generation quality, with interleaved models significantly outperforming non-interleaved ones; notably, combining strong unimodal models fails to achieve comparable reasoning. (ii) Models show dissociation between physical and symbolic reasoning: they succeed at interpreting perceptual concepts literally but fail to construct visual abstractions for symbolic tasks, where faulty reasoning harms performance. These results highlight reciprocal cross-modal reasoning as a critical frontier for enabling true omnimodal generation.</p> - https://arxiv.org/abs/2511.01163 - Mon, 03 Nov 2025 02:27:46 +0000 + BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring + https://arxiv.org/abs/2511.02490 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02490.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rajan Das Gupta, Md Kishor Morol, Nafiz Fahad, Md Tanzib Hosain, Sumaya Binte Zilani Choya, Md Jakir Hossen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> As the global burden of Alzheimer's disease (AD) continues to grow, early and accurate detection has become increasingly critical, especially in regions with limited access to advanced diagnostic tools. We propose BRAINS (Biomedical Retrieval-Augmented Intelligence for Neurodegeneration Screening) to address this challenge. This novel system harnesses the powerful reasoning capabilities of Large Language Models (LLMs) for Alzheimer's detection and monitoring. BRAINS features a dual-module architecture: a cognitive diagnostic module and a case-retrieval module. The Diagnostic Module utilizes LLMs fine-tuned on cognitive and neuroimaging datasets -- including MMSE, CDR scores, and brain volume metrics -- to perform structured assessments of Alzheimer's risk. Meanwhile, the Case Retrieval Module encodes patient profiles into latent representations and retrieves similar cases from a curated knowledge base. These auxiliary cases are fused with the input profile via a Case Fusion Layer to enhance contextual understanding. The combined representation is then processed with clinical prompts for inference. Evaluations on real-world datasets demonstrate BRAINS effectiveness in classifying disease severity and identifying early signs of cognitive decline. This system not only shows strong potential as an assistive tool for scalable, explainable, and early-stage Alzheimer's disease detection, but also offers hope for future applications in the field.</p> + https://arxiv.org/abs/2511.02490 + Tue, 04 Nov 2025 11:27:03 +0000 - MotionStream: Real-Time Video Generation with Interactive Motion Controls - https://arxiv.org/abs/2511.01266 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01266.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Schechtman, Xun Huang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. Our approach begins by augmenting a text-to-video model with motion control, which generates high-quality videos that adhere to the global text prompt and local motion guidance, but does not perform inference on the fly. As such, we distill this bidirectional teacher into a causal student through Self Forcing with Distribution Matching Distillation, enabling real-time streaming inference. Several key challenges arise when generating videos of long, potentially infinite time-horizons: (1) bridging the domain gap from training on finite length and extrapolating to infinite horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without incurring growth in computational cost due to increasing context windows. A key to our approach is introducing carefully designed sliding-window causal attention, combined with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we properly simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Our models achieve state-of-the-art results in motion following and video quality while being two orders of magnitude faster, uniquely enabling infinite-length streaming. With MotionStream, users can paint trajectories, control cameras, or transfer motion, and see results unfold in real-time, delivering a truly interactive experience.</p> - https://arxiv.org/abs/2511.01266 - Mon, 03 Nov 2025 06:37:53 +0000 + Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models + https://arxiv.org/abs/2511.02650 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02650.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianfan Peng, Yuntao Du, Pengzhou Ji, Shijie Dong, Kailin Jiang, Mingchuan Ma, Yijun Tian, Jinhe Bi, Qian Li, Wei Du, Feng Xiao, Lizhen Cui</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in reducing redundancy, their evaluation remains fragmented and inconsistent. In this work, we present UniPruneBench, a unified and extensible benchmark for visual token pruning in multimodal LLMs. UniPruneBench provides standardized protocols across six ability dimensions and ten datasets, covering ten representative compression algorithms and three families of LMMs (LLaVA-v1.5, Intern-VL3, and Qwen2.5-VL). Beyond task accuracy, it incorporates system-level metrics such as runtime and prefilling latency to provide a holistic view. Our experiments uncover several key findings: (1) random pruning is a surprisingly strong baseline, (2) no single method consistently outperforms others across scenarios, (3) pruning sensitivity varies significantly across tasks, with OCR being most vulnerable, and (4) pruning ratio is the dominant factor governing performance degradation. We believe UniPruneBench will serve as a reliable foundation for future research on efficient multimodal modeling.</p> + https://arxiv.org/abs/2511.02650 + Tue, 04 Nov 2025 15:17:06 +0000 - UniREditBench: A Unified Reasoning-based Image Editing Benchmark - https://arxiv.org/abs/2511.01295 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01295.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Feng Han, Yibin Wang, Chenglin Li, Zheming Liang, Dianyi Wang, Yang Jiao, Zhipeng Wei, Chao Gong, Cheng Jin, Jingjing Chen, Jiaqi Wang</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects.</p> - https://arxiv.org/abs/2511.01295 - Mon, 03 Nov 2025 07:24:57 +0000 + The Collaboration Gap + https://arxiv.org/abs/2511.02687 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02687.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tim R. Davidson, Adam Fourney, Saleema Amershi, Robert West, Eric Horvitz, Ece Kamar</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The trajectory of AI development suggests that we will increasingly rely on agent-based systems composed of independently developed agents with different information, privileges, and tools. The success of these systems will critically depend on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, few empirical studies have evaluated such agent-agent collaboration at scale. We propose a collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, preserving ecological plausibility. Using this framework, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a "collaboration gap": models that perform well solo often degrade substantially when required to collaborate. Collaboration can break down dramatically; for instance, small distilled models that solve mazes well alone may fail almost completely in certain pairings. We find that starting with the stronger agent often improves outcomes, motivating a "relay inference" approach where the stronger agent leads before handing off to the weaker one, closing much of the gap. Our findings argue for (1) collaboration-aware evaluation, (2) training strategies developed to enhance collaborative capabilities, and (3) interaction design that reliably elicits agents' latent skills, guidance that applies to AI-AI and human-AI collaboration.</p> + https://arxiv.org/abs/2511.02687 + Tue, 04 Nov 2025 16:10:57 +0000 - left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles - https://arxiv.org/abs/2511.01340 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01340.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Trishanu Das, Abhilash Nandy, Khush Bajaj, Deepiha S</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Understanding Rebus Puzzles (Rebus Puzzles use pictures, symbols, and letters to represent words or phrases creatively) requires a variety of skills such as image recognition, cognitive skills, commonsense reasoning, multi-step reasoning, image-based wordplay, etc., making this a challenging task for even current Vision-Language Models. In this paper, we present left|,circlearrowright,text{BUS},right|, a large and diverse benchmark of 1,333 English Rebus Puzzles containing different artistic styles and levels of difficulty, spread across 18 categories such as food, idioms, sports, finance, entertainment, etc. We also propose RebusDescProgICE, a model-agnostic framework which uses a combination of an unstructured description and code-based, structured reasoning, along with better, reasoning-based in-context example selection, improving the performance of Vision-Language Models on left|,circlearrowright,text{BUS},right| by 2.1-4.1% and 20-30% using closed-source and open-source models respectively compared to Chain-of-Thought Reasoning.</p> - https://arxiv.org/abs/2511.01340 - Mon, 03 Nov 2025 08:42:59 +0000 + VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models + https://arxiv.org/abs/2511.02712 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhicheng Zhang, Weicheng Wang, Yongjie Zhu, Wenyu Qin, Pengfei Wan, Di Zhang, Jufeng Yang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Understanding and predicting emotion from videos has gathered significant attention in recent studies, driven by advancements in video large language models (VideoLLMs). While advanced methods have made progress in video emotion analysis, the intrinsic nature of emotions poses significant challenges. Emotions are characterized by dynamic and cues-dependent properties, making it difficult to understand complex and evolving emotional states with reasonable rationale. To tackle these challenges, we propose a novel affective cues-guided reasoning framework that unifies fundamental attribute perception, expression analysis, and high-level emotional understanding in a stage-wise manner. At the core of our approach is a family of video emotion foundation models (VidEmo), specifically designed for emotion reasoning and instruction-following. These models undergo a two-stage tuning process: first, curriculum emotion learning for injecting emotion knowledge, followed by affective-tree reinforcement learning for emotion reasoning. Moreover, we establish a foundational data infrastructure and introduce a emotion-centric fine-grained dataset (Emo-CFG) consisting of 2.1M diverse instruction-based samples. Emo-CFG includes explainable emotional question-answering, fine-grained captions, and associated rationales, providing essential resources for advancing emotion understanding tasks. Experimental results demonstrate that our approach achieves competitive performance, setting a new milestone across 15 face perception tasks.</p> + https://arxiv.org/abs/2511.02712 + Tue, 04 Nov 2025 16:31:09 +0000 - Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers - https://arxiv.org/abs/2511.01617 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01617.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohamed Eltahir, Ali Habibullah, Lama Ayash, Tanveer Hussain, Naeemullah Khan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they rely solely on rank or score signals, disregarding candidates' representations. This work introduces Vote-in-Context (ViC), a generalized, training-free framework that re-thinks list-wise reranking and fusion as a zero-shot reasoning task for a Vision-Language Model (VLM). The core insight is to serialize both content evidence and retriever metadata directly within the VLM's prompt, allowing the model to adaptively weigh retriever consensus against visual-linguistic content. We demonstrate the generality of this framework by applying it to the challenging domain of cross-modal video retrieval. To this end, we introduce the S-Grid, a compact serialization map that represents each video as an image grid, optionally paired with subtitles to enable list-wise reasoning over video candidates. ViC is evaluated both as a single-list reranker, where it dramatically improves the precision of individual retrievers, and as an ensemble fuser, where it consistently outperforms strong baselines like CombSUM. Across video retrieval benchmarks including ActivityNet and VATEX, the framework establishes new state-of-the-art zero-shot retrieval performance, demonstrating its effectiveness in handling complex visual and temporal signals alongside text. In zero-shot settings, ViC achieves Recall@1 scores of 87.1% (t2v) / 89.0% (v2t) on MSR-VTT and 99.6% (v2t) on VATEX, representing massive gains of up to +40 Recall@1 over previous state-of-the-art baselines. We present ViC as a simple, reproducible, and highly effective recipe for turning modern VLMs into powerful zero-shot rerankers and fusers. Code and resources are publicly available at: https://github.com/mohammad2012191/ViC</p> - https://arxiv.org/abs/2511.01617 - Mon, 03 Nov 2025 14:25:12 +0000 + VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation + https://arxiv.org/abs/2511.02778 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02778.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kevin Qinghong Lin, Yuhao Zheng, Hangyu Ran, Dantong Zhu, Dongxing Mao, Linjie Li, Philip Torr, Alex Jinpeng Wang</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored. Inspired by how humans reason over sketches, we advocate SVG code as a compact, interpretable, and executable visual representation. We introduce VCode, a benchmark that reframes multimodal understanding as code generation: given an image, a model must produce SVG that preserves symbolic meaning for downstream reasoning. VCode covers three domains - general commonsense (MM-Vet), professional disciplines (MMMU), and visual-centric perception (CV-Bench). To assess symbolic fidelity, we propose CodeVQA, a novel evaluation protocol in which a policy model answers questions over rendered SVGs; correct answers indicate faithful symbolic preservation. Empirically, frontier VLMs struggle to generate faithful SVGs, revealing a persistent gap between language-centric and visual-centric coding. To close this gap, we introduce VCoder, an agentic framework that augments VLMs along two axes: (i) Thinking with Revision, which iteratively analyzes discrepancies and refines SVG code; and (ii) Acting with Visual Tools, where detectors and parsers supply structured cues such as objects, shapes, and text beyond the model's intrinsic capacity. Across benchmarks, frontier VLMs with strong reasoning capabilities score well overall yet remain limited in professional knowledge and 3D reasoning. VCoder delivers a 12.3-point overall gain over the top-performing Claude-4-Opus. Human studies show that both humans and VLMs perform worse on rendered SVGs, their consistency reveals the promise of symbolic visual representation. The benchmark and code are available at https://github.com/CSU-JPG/VCode.</p> + https://arxiv.org/abs/2511.02778 + Tue, 04 Nov 2025 18:00:18 +0000 - Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models - https://arxiv.org/abs/2511.01618 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoyu Zhan, Wenxuan Huang, Hao Sun, Xinyu Fu, Changfeng Ma, Shaosheng Cao, Bohan Jia, Shaohui Lin, Zhenfei Yin, Lei Bai, Wanli Ouyang, Yuanqi Li, Jie Guo, Yanwen Guo</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.</p> - https://arxiv.org/abs/2511.01618 - Mon, 03 Nov 2025 14:27:00 +0000 + When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought + https://arxiv.org/abs/2511.02779 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02779.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyang Zhou, Haoqin Tu, Zijun Wang, Zeyu Wang, Niklas Muennighoff, Fan Nie, Yejin Choi, James Zou, Chaorui Deng, Shen Yan, Haoqi Fan, Cihang Xie, Huaxiu Yao, Qinghao Ye</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require models to generate and utilize intermediate images - such as sketches, structural diagrams, or path drawings - to guide their reasoning process. This setup closely mirrors how humans solve complex problems through "drawing to think". To solve this, MIRA focuses on tasks that are intrinsically challenging and involve complex structures, spatial relationships, or reasoning steps that are difficult to express through language alone. To ensure that our evaluation data is of high-quality, we include 546 multimodal problems, annotated with intermediate visual images and final answers. We also propose a unified evaluation protocol for MIRA that spans three levels of evaluation input: direct input with image and question only, text-only CoT input with image and thinking prompts, and Visual-CoT input with both annotated image clues and textual thinking prompts. To probe the upper bound of model capacity on our benchmark, we also report pass@k and majority voting accuracies under different k settings. Experimental results show that existing multimodal large language models, including strongest private models as well as strong open-weight models, perform poorly when relying solely on textual prompts. However, when intermediate visual cues are provided, model performance improves consistently, yielding an average relative gain of 33.7% across all models and tasks. We also probe the upper bound by expanding the search space and designing textual prompts aligned with Visual-CoT, but both yield only limited improvements compared to our Visual-CoT setting. These results underscore the critical role of imagined visual information in enabling successful reasoning on MIRA.</p> + https://arxiv.org/abs/2511.02779 + Tue, 04 Nov 2025 18:00:51 +0000 - UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback - https://arxiv.org/abs/2511.01678 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ropeway Liu, Hangjie Yuan, Bo Dong, Jiazheng Xing, Jinwang Wang, Rui Zhao, Yan Xing, Weihua Chen, Fan Wang</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results, such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom.</p> - https://arxiv.org/abs/2511.01678 - Mon, 03 Nov 2025 15:41:41 +0000 - - - Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement - https://arxiv.org/abs/2511.01706 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01706.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions, drawing on both external Context Knowledge (CK) and Parametric Knowledge (PK) stored in model weights. Understanding their interaction is key to assessing the grounding of NLEs, yet it remains underexplored. Prior work has largely examined only single-step generation, typically the final answer, and has modelled PK and CK interaction only as a binary choice in a rank-1 subspace. This overlooks richer forms of interaction, such as complementary or supportive knowledge. We propose a novel rank-2 projection subspace that disentangles PK and CK contributions more accurately and use it for the first multi-step analysis of knowledge interactions across longer NLE sequences. Experiments on four QA datasets and three open-weight instruction-tuned LLMs show that diverse knowledge interactions are poorly represented in a rank-1 subspace but are effectively captured in our rank-2 formulation. Our multi-step analysis reveals that hallucinated NLEs align strongly with the PK direction, context-faithful ones balance PK and CK, and Chain-of-Thought prompting for NLEs shifts generated NLEs toward CK by reducing PK reliance. This work provides the first framework for systematic studies of multi-step knowledge interactions in LLMs through a richer rank-2 subspace disentanglement. Code and data: https://github.com/copenlu/pk-ck-knowledge-disentanglement.</p> - https://arxiv.org/abs/2511.01706 - Mon, 03 Nov 2025 16:15:06 +0000 - - - Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process - https://arxiv.org/abs/2511.01718 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01718.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Chen, Wenxuan Song, Pengxiang Ding, Ziyang Zhou, Han Zhao, Feilong Tang, Donglin Wang, Haoang Li</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4times faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.</p> - https://arxiv.org/abs/2511.01718 - Mon, 03 Nov 2025 16:26:54 +0000 - - - How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment - https://arxiv.org/abs/2511.01775 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01775.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhen Chen, Qing Xu, Jinlin Wu, Biao Yang, Yuhao Zhai, Geng Guo, Jing Zhang, Yinlu Ding, Nassir Navab, Jiebo Luo</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Foundation models in video generation are demonstrating remarkable capabilities as potential world models for simulating the physical world. However, their application in high-stakes domains like surgery, which demand deep, specialized causal knowledge rather than general physical rules, remains a critical unexplored gap. To systematically address this challenge, we present SurgVeo, the first expert-curated benchmark for video generation model evaluation in surgery, and the Surgical Plausibility Pyramid (SPP), a novel, four-tiered framework tailored to assess model outputs from basic appearance to complex surgical strategy. On the basis of the SurgVeo benchmark, we task the advanced Veo-3 model with a zero-shot prediction task on surgical clips from laparoscopic and neurosurgical procedures. A panel of four board-certified surgeons evaluates the generated videos according to the SPP. Our results reveal a distinct "plausibility gap": while Veo-3 achieves exceptional Visual Perceptual Plausibility, it fails critically at higher levels of the SPP, including Instrument Operation Plausibility, Environment Feedback Plausibility, and Surgical Intent Plausibility. This work provides the first quantitative evidence of the chasm between visually convincing mimicry and causal understanding in surgical AI. Our findings from SurgVeo and the SPP establish a crucial foundation and roadmap for developing future models capable of navigating the complexities of specialized, real-world healthcare domains.</p> - https://arxiv.org/abs/2511.01775 - Mon, 03 Nov 2025 17:28:54 +0000 - - - TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning - https://arxiv.org/abs/2511.01833 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01833.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ming Li, Jike Zhong, Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Yuxiang Lai, Wei Chen, Konstantinos Psounis, Kaipeng Zhang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as thinking-with-images in chain-of-thought. Yet existing benchmarks fail to fully capture this advanced capability. Even Visual Search, the most common benchmark for current thinking-with-images methods, tests only basic operations such as localization and cropping, offering little insight into more complex, dynamic, and tool-dependent reasoning. We introduce TIR-Bench, a comprehensive benchmark for evaluating agentic thinking-with-images across 13 diverse tasks, each requiring novel tool use for image processing and manipulation in chain-of-thought. We evaluate 22 multimodal large language models (MLLMs), from leading open-sourced and proprietary models to those with explicit tool-use augmentation. Results show that TIR-Bench is universally challenging, and strong performance requires genuine thinking-with-images capabilities. Finally, we present a pilot study comparing direct versus agentic fine-tuning.</p> - https://arxiv.org/abs/2511.01833 - Mon, 03 Nov 2025 18:40:17 +0000 - - - Towards Robust Mathematical Reasoning - https://arxiv.org/abs/2511.01846 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01846.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Thang Luong, Dawsen Hwang, Hoang H. Nguyen, Golnaz Ghiasi, Yuri Chervonyi, Insuk Seo, Junsu Kim, Garrett Bingham, Jonathan Lee, Swaroop Mishra, Alex Zhai, Clara Huiyi Hu, Henryk Michalewski, Jimin Kim, Jeonghyun Ahn, Junhwi Bae, Xingyou Song, Trieu H. Trinh, Quoc V. Le, Junehyuk Jung</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Finding the right north-star metrics is highly critical for advancing the mathematical reasoning capabilities of foundation models, especially given that existing evaluations are either too easy or only focus on getting correct short answers. To address these issues, we present IMO-Bench, a suite of advanced reasoning benchmarks, vetted by a panel of top specialists and that specifically targets the level of the International Mathematical Olympiad (IMO), the most prestigious venue for young mathematicians. IMO-AnswerBench first tests models on 400 diverse Olympiad problems with verifiable short answers. IMO-Proof Bench is the next-level evaluation for proof-writing capabilities, which includes both basic and advanced IMO level problems as well as detailed grading guidelines to facilitate automatic grading. These benchmarks played a crucial role in our historic achievement of the gold-level performance at IMO 2025 with Gemini Deep Think (Luong and Lockhart, 2025). Our model achieved 80.0% on IMO-AnswerBench and 65.7% on the advanced IMO-Proof Bench, surpassing the best non-Gemini models by large margins of 6.9% and 42.4% respectively. We also showed that autograders built with Gemini reasoning correlate well with human evaluations and construct IMO-GradingBench, with 1000 human gradings on proofs, to enable further progress in automatic evaluation of long-form answers. We hope that IMO-Bench will help the community towards advancing robust mathematical reasoning and release it at https://imobench.github.io/.</p> - https://arxiv.org/abs/2511.01846 - Mon, 03 Nov 2025 18:53:02 +0000 - - - Trove: A Flexible Toolkit for Dense Retrieval - https://arxiv.org/abs/2511.01857 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.01857.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Reza Esfandiarpoor, Max Zuo, Stephen H. Bach</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We introduce Trove, an easy-to-use open-source retrieval toolkit that simplifies research experiments without sacrificing flexibility or speed. For the first time, we introduce efficient data management features that load and process (filter, select, transform, and combine) retrieval datasets on the fly, with just a few lines of code. This gives users the flexibility to easily experiment with different dataset configurations without the need to compute and store multiple copies of large datasets. Trove is highly customizable: in addition to many built-in options, it allows users to freely modify existing components or replace them entirely with user-defined objects. It also provides a low-code and unified pipeline for evaluation and hard negative mining, which supports multi-node execution without any code changes. Trove's data management features reduce memory consumption by a factor of 2.6. Moreover, Trove's easy-to-use inference pipeline incurs no overhead, and inference times decrease linearly with the number of available nodes. Most importantly, we demonstrate how Trove simplifies retrieval experiments and allows for arbitrary customizations, thus facilitating exploratory research.</p> - https://arxiv.org/abs/2511.01857 - Mon, 03 Nov 2025 18:59:57 +0000 + TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System + https://arxiv.org/abs/2511.02832 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.02832.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanjie Ze, Siheng Zhao, Weizhuo Wang, Angjoo Kanazawa, Rocky Duan, Pieter Abbeel, Guanya Shi, Jiajun Wu, C. Karen Liu</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large-scale data has driven breakthroughs in robotics, from language models to vision-language-action models in bimanual manipulation. However, humanoid robotics lacks equally effective data collection frameworks. Existing humanoid teleoperation systems either use decoupled control or depend on expensive motion capture setups. We introduce TWIST2, a portable, mocap-free humanoid teleoperation and data collection system that preserves full whole-body control while advancing scalability. Our system leverages PICO4U VR for obtaining real-time whole-body human motions, with a custom 2-DoF robot neck (cost around $250) for egocentric vision, enabling holistic human-to-humanoid control. We demonstrate long-horizon dexterous and mobile humanoid skills and we can collect 100 demonstrations in 15 minutes with an almost 100% success rate. Building on this pipeline, we propose a hierarchical visuomotor policy framework that autonomously controls the full humanoid body based on egocentric vision. Our visuomotor policy successfully demonstrates whole-body dexterous manipulation and dynamic kicking tasks. The entire system is fully reproducible and open-sourced at https://yanjieze.com/TWIST2 . Our collected dataset is also open-sourced at https://twist-data.github.io .</p> + https://arxiv.org/abs/2511.02832 + Tue, 04 Nov 2025 18:58:35 +0000