大模型推理能力 - arXivDaily 专题

2503.16188 2025-10-28 cs.CV 50%

Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning

Ming Li, Jike Zhong, Shitian Zhao, Yuxiang Lai, Haoquan Zhang, Wang Bill Zhu, Kaipeng Zhang

机构 * Shanghai AI Laboratory（上海人工智能实验室）； University of Southern California（南加州大学）； Emory University（埃默里大学）； Chinese University of Hong Kong（香港中文大学）

专题命中推理评测：CoT(abstract)

Comments Neurips 2025 Spotlight

2510.20113 2025-10-24 eess.SY cs.SD cs.SY 50%

SpeechAgent: An End-to-End Mobile Infrastructure for Speech Impairment Assistance

Haowei Lou, Chengkai Huang, Hye-young Paik, Yongquan Hu, Aaron Quigley, Wen Hu, Lina Yao

机构 * University of New South Wales（新南威尔士大学）； Macquarie University（麦考瑞大学）； National University of Singapore（国立新加坡大学）； CSIRO's Data61（澳大利亚联邦科学与工业研究组织Data61部门）

专题命中推理评测：reasoning(abstract)

2505.16793 2025-10-24 cs.CV 50%

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Xiang Li, Yong Tao, Siyuan Zhang, Siwei Liu, Zhitong Xiong, Chunbo Luo, Lu Liu, Mykola Pechenizkiy, Xiao Xiang Zhu, Tianjin Huang

机构 * University of Bristol, UK（英国布里斯托大学）； University of Exeter, UK（英国埃克塞特大学）； South China Normal University, China（华南师范大学）； The University of Aberdeen, UK（英国阿伯丁大学）； Technical University of Munich, Germany（慕尼黑技术大学）； Eindhoven University of Technology, NL（埃因霍温理工大学）

专题命中推理评测：planning(abstract)

Comments Accepted to NeruIPS 2025 D&B Track

2510.19626 2025-10-23 cs.CV 50%

MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom

Yifan Li, Fenghe Tang, Yingtai Li, Shaohua Kevin Zhou

机构 * 1 School of Biomedical Engineering, Division of Life Sciences ； Medicine, University of Science ； Technology of China, Hefei, Anhui, 230026, P.R. China 2 Center for Medical Imaging, Robotics ； Analytic Computing \& LEarning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou 215123, P.R. China 3 Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou Jiangsu, 215123 4 State Key Laboratory of Precision

专题命中推理评测：reasoning(abstract)

Comments The code, checkpoints, and dataset are available at: https://github.com/Leevan001/MedReason-R1

2510.19336 2025-10-23 cs.CV 50%

DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents

Kai Shi, Jun Yang, Ni Yang, Binqiang Pan, Qingsong Xie, Chao Zhang, Zhenyu Yang, Tianhuang Su, Haonan Lu

机构 * OPPO AI Center（OPPO人工智能中心）

专题命中推理评测：reasoning(abstract)

2506.12323 2025-10-23 cs.CV 50%

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

Janet Wang, Yunbei Zhang, Zhengming Ding, Jihun Hamm

机构 * Tulane University（路易斯安那州立大学）

专题命中推理评测：reasoning(abstract)

Comments NeurIPS 2025

2506.10043 2025-10-23 cs.SE 50%

TrioXpert: An Automated Incident Management Framework for Microservice System

Yongqian Sun, Yu Luo, Xidao Wen, Yuan Yuan, Xiaohui Nie, Shenglin Zhang, Tong Liu, Xi Luo

专题命中推理评测：reasoning(abstract)

2412.01069 2025-10-23 q-fin.GN econ.GN q-fin.EC 50%

The Promise and Peril of Generative AI: Evidence from GPT as Sell-Side Analysts

Edward Li, Min Shen, Zhiyuan Tu, Dexin Zhou

专题命中推理评测：reasoning(abstract)

2510.18873 2025-10-22 cs.CV 50%

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

Ziang Zhang, Zehan Wang, Guanghao Zhang, Weilong Dai, Yan Xia, Ziang Yan, Minjie Hong, Zhou Zhao

机构 * Zhejiang University（浙江大学）； Alibaba Group（阿里巴巴集团）； Shanghai AI Lab（上海人工智能实验室）

专题命中推理评测：reasoning(abstract)

2510.18596 2025-10-22 cs.SE cs.CV 50%

CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent

Haojia Lin, Xiaoyu Tan, Yulei Qin, Zihan Xu, Yuchen Shi, Zongyi Li, Gang Li, Shaofei Cai, Siqi Cai, Chaoyou Fu, Ke Li, Xing Sun

机构 * Youtu-Agent Team（YouTu-Agent团队）

专题命中推理评测：reasoning(abstract)

Comments 24 pages, 6 figures

2510.18262 2025-10-22 cs.CV 50%

UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding

Da Zhang, Chenggang Rong, Bingyu Li, Feiyu Wang, Zhiyuan Zhao, Junyu Gao, Xuelong Li

机构 * Institute of Artificial Intelligence (TeleAI), China Telecom, China（人工智能研究院（TeleAI）、中国电信）

专题命中推理评测：reasoning(abstract)

Comments We have released V1, which only reports the test results. Our work is still ongoing, and the next version will be coming soon

2505.21089 2025-10-22 cs.CV 50%

DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response

Junjue Wang, Weihao Xuan, Heli Qi, Zhihao Liu, Kunyi Liu, Yuhan Wu, Hongruixuan Chen, Jian Song, Junshi Xia, Zhuo Zheng, Naoto Yokoya

机构 * The University of Tokyo（东京大学）； RIKEN AIP（理化学研究所AIP）； Waseda University（早稻田大学）； Stony Brook University（石溪大学）； Stanford University（斯坦福大学）

专题命中推理评测：reasoning(abstract)

Comments A multi-hazard, multi-sensor, and multi-task vision-language dataset for global-scale disaster assessment and response

2507.05289 2025-10-21 cs.SE 50%

Measuring how changes in code readability attributes affect code quality evaluation by Large Language Models

Igor Regis da Silva Simoes, Elaine Venson

专题命中推理评测：reasoning(abstract)

Journal ref 2025: Proceedings of the XXXIX Brazilian Symposium on Software Engineering

2505.14671 2025-10-21 cs.CV 50%

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

Ruichuan An, Sihan Yang, Renrui Zhang, Zijun Shen, Ming Lu, Gaole Dai, Hao Liang, Ziyu Guo, Shilin Yan, Yulin Luo, Bocheng Zou, Chaoqun Yang, Wentao Zhang

机构 * Peking University（北京大学）； Xi’an JiaoTong University（西安交通大学）； CUHK（香港中文大学）； Intel Labs, China（中国英特尔实验室）； Nanjing University（南京大学）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； Tsinghua University（清华大学）

专题命中推理评测：reasoning(abstract)

Journal ref NeurIPS 2025

2510.16641 2025-10-21 cs.CV 50%

MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang, Yechan Hwang, Byungsoo Ko, Han-Gyu Kim, Dongyu Yao, Xuankun Rong, Eojin Joo, Seung-Ho Han, Bowon Ko, Ho-Jin Choi

机构 * KAIST（韩国科学技术院）； WHU（华中科技大学）； NAVER ； CMU（卡内基梅隆大学）

专题命中推理评测：reasoning(abstract)

Comments Project website: https://passing2961.github.io/multiverse-project-page/

2510.16579 2025-10-21 cs.SE 50%

Human-Aligned Code Readability Assessment with Large Language Models

Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang, Pawel Borsukiewicz, Xin Zhou, Anil Koyuncu, Jacques Klein, David Lo, Tegawendé F. Bissyandé

专题命中推理评测：CoT(abstract)

2510.16137 2025-10-21 physics.ed-ph 50%

Exploring the potential of ChatGPT for feedback and evaluation in experimental physics

Marcos Abreu, Álvaro Suárez, Cecilia Stari, Arturo C. Marti

专题命中推理评测：reasoning(abstract)

Comments 5 pages

2508.02736 2025-10-21 cs.OS cs.SE 50%

AgentSight: System-Level Observability for AI Agents Using eBPF

Yusheng Zheng, Yanpeng Hu, Tong Yu, Andi Quinn

专题命中推理评测：reasoning(abstract)

Journal ref PACMI'2025

2510.14560 2025-10-17 cs.CV 50%

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Yulin Zhang, Cheng Shi, Yang Wang, Sibei Yang

机构 * ShanghaiTech University（上海科技大学）； School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）； School of Computing and Data Science, The University of Hong Kong（香港大学计算科学与数据科学学院）

专题命中推理评测：reasoning(abstract)

Comments Accepted at NeurIPS 2025 (preview; camera-ready in preparation)

2510.14257 2025-10-17 cs.IR 50%

Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation

Lingyu Mu, Hao Deng, Haibo Xing, Kaican Lin, Zhitong Zhu, Yu Zhang, Xiaoyi Zeng, Zhengxiao Liu, Zheng Lin, Jinxin Hu

专题命中推理评测：reasoning(abstract)

2509.22642 2025-10-17 cs.RO cs.CV cs.MM 50%

WoW: Towards a World omniscient World model Through Embodied Interaction

Xiaowei Chi, Peidong Jia, Chun-Kai Fan, Xiaozhu Ju, Weishi Mi, Kevin Zhang, Zhiyuan Qin, Wanxin Tian, Kuangzhi Ge, Hao Li, Zezhong Qian, Anthony Chen, Qiang Zhou, Yueru Jia, Jiaming Liu, Yong Dai, Qingpo Wuwu, Chengyu Bai, Yu-Kai Wang, Ying Li, Lizhang Chen, Yong Bao, Zhiyuan Jiang, Jiacheng Zhu, Kai Tang, Ruichuan An, Yulin Luo, Qiuxuan Feng, Siyuan Zhou, Chi-min Chan, Chengkai Hou, Wei Xue, Sirui Han, Yike Guo, Shanghang Zhang, Jian Tang

机构 * Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心）； State Key Laboratory of Multimedia Information Processing（国家多媒体信息处理重点实验室）； School of Computer Science, Peking University（北京大学计算机学院）； Hong Kong University of Science and Technology（香港科技大学）

专题命中推理评测：reasoning(abstract)

2509.26165 2025-10-16 cs.CV 50%

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

Yuansen Liu, Haiming Tang, Jinlong Peng, Jiangning Zhang, Xiaozhong Ji, Qingdong He, Wenbin Wu, Donghao Luo, Zhenye Gan, Junwei Zhu, Yunhang Shen, Chaoyou Fu, Chengjie Wang, Xiaobin Hu, Shuicheng Yan

机构 * Yuan-Hou（元侯）

专题命中推理评测：reasoning(abstract)

2510.12422 2025-10-15 cs.CV 50%

VideoLucy: Deep Memory Backtracking for Long Video Understanding

Jialong Zuo, Yongtai Deng, Lingdong Kong, Jingkang Yang, Rui Jin, Yiwei Zhang, Nong Sang, Liang Pan, Ziwei Liu, Changxin Gao

机构 * National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（多谱段信息智能处理国家级重点实验室，人工智能与自动化学院，华中科技大学）； NUS（国立大学新加坡）； S-Lab, NTU（NTU的S实验室）； Shanghai AI Lab（上海人工智能实验室）

专题命中推理评测：reasoning(abstract)

Comments NeurIPS-2025 Accepted Paper

2510.12400 2025-10-15 cs.CV 50%

Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agenda

André Torneiro, Diogo Monteiro, Paulo Novais, Pedro Rangel Henriques, Nuno F. Rodrigues

机构 * ALGORITMI Research Centre/LASI（ALGORITMI研究机构/LASI）； University of Minho（明霍大学）； Logimade（Logimade公司）； INESC TEC（INESC TEC研究机构）； Ai, School of Technology（2Ai技术学院）； IPCA

专题命中推理评测：reasoning(abstract)

Comments 44 pages

2505.15818 2025-10-14 cs.CV 50%

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition

Yijie Zheng, Weijie Wu, Qingyun Li, Xuehui Wang, Xu Zhou, Aiai Ren, Jun Shen, Long Zhao, Guoqing Li, Xue Yang

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）； Harbin Institute of Technology（哈尔滨工业大学）； Shanghai Jiao Tong University（上海交通大学）； University of Wollongong（沃林戈大学）； SAIS, Shanghai Jiao Tong University（上海交通大学国际关系学院）

专题命中推理评测：reasoning(abstract)

Comments Accepted to NeurIPS 2025

2510.10880 2025-10-14 cs.CV 50%

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales

Zhaofang Qian, Hardy Chen, Zeyu Wang, Li Zhang, Zijun Wang, Xiaoke Huang, Hui Liu, Xianfeng Tang, Zeyu Zheng, Haoqin Tu, Cihang Xie, Yuyin Zhou

机构 * University of Central Florida（中央佛罗里达大学）； University of California, Santa Cruz（加州大学圣克鲁兹分校）； Columbia University（哥伦比亚大学）； Amazon Research（亚马逊研究）； University of California, Berkeley（加州大学伯克利分校）

专题命中推理评测：reasoning(abstract)

2507.05970 2025-10-14 cs.CV 50%

Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval

Haiwen Li, Delong Liu, Zhaohui Hou, Zhicheng Zhao, Fei Su

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

专题命中推理评测：reasoning(abstract)

Comments This paper was originally submitted to ACM MM 2025 on April 12, 2025

2505.18846 2025-10-14 cs.CR 50%

LLM-Driven APT Detection for 6G Wireless Networks: A Systematic Review and Taxonomy

Muhammed Golec, Yaser Khamayseh, Suhib Bani Melhem, Abdulmalik Alwarafy

专题命中推理评测：reasoning(abstract)

Comments 22 pages, 11 figures, 8 tables. Submitted to Computer Science Review (Elsevier), May 2025

Journal ref IEEE Access 2025

2504.09282 2025-10-14 cs.CV 50%

VideoAds for Fast-Paced Video Understanding

Zheyuan Zhang, Monica Dou, Linkai Peng, Hongyi Pan, Ulas Bagci, Boqing Gong

机构 * Northwestern University（西北大学）； Boston University（波士顿大学）

专题命中推理评测：reasoning(abstract)

Comments ICCV2025

2510.08921 2025-10-13 cs.CY 50%

GBA-UBF : A Large-Scale and Fine-Grained Building Function Classification Dataset in the Greater Bay Area

Chunsong Chen, Yichen Hou, Huan Chen, Junlin Li, Rong Fu, Qiushen Lai, Yiping Chen, Ting Han

专题命中推理评测：planning(abstract)

Comments 12 pages, 10 figures, The 4th ACM SIGSPATIAL International Workshop on Spatial Big Data and AI for Industrial Applications (GeoIndustry '25), November 3--6, 2025, Minneapolis, MN, USA

1. 推理评测 10577 篇

Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning

SpeechAgent: An End-to-End Mobile Infrastructure for Speech Impairment Assistance

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom

DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

TrioXpert: An Automated Incident Management Framework for Microservice System

The Promise and Peril of Generative AI: Evidence from GPT as Sell-Side Analysts

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent

UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding

DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response

Measuring how changes in code readability attributes affect code quality evaluation by Large Language Models

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

Human-Aligned Code Readability Assessment with Large Language Models

Exploring the potential of ChatGPT for feedback and evaluation in experimental physics

AgentSight: System-Level Observability for AI Agents Using eBPF

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation

WoW: Towards a World omniscient World model Through Embodied Interaction

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

VideoLucy: Deep Memory Backtracking for Long Video Understanding

Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agenda

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales

Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval

LLM-Driven APT Detection for 6G Wireless Networks: A Systematic Review and Taxonomy

VideoAds for Fast-Paced Video Understanding

GBA-UBF : A Large-Scale and Fine-Grained Building Function Classification Dataset in the Greater Bay Area