大模型推理能力 - arXivDaily 专题

2509.22688 2025-10-08 cs.CV 50%

Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization

Xu Jia

专题命中复杂问题求解：reasoning(abstract)

2509.23899 2025-10-06 cs.CV 50%

Q-FSRU: Quantum-Augmented Frequency-Spectral For Medical Visual Question Answering

Rakesh Thakur, Yusra Tariq, Rakesh Chandra Joshi

机构 * Amity University（阿米蒂大学）

专题命中复杂问题求解：reasoning(abstract)

Comments 12 pages (9 main + 2 references/appendix), 2 figures, conference paper submitted to ICLR 2026

2508.20088 2025-10-06 cs.CV cs.MM cs.SD 50%

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Yuxin Guo, Teng Wang, Yuying Ge, Shijie Ma, Yixiao Ge, Wei Zou, Ying Shan

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； ARC Lab, Tencent PCG（腾讯PCG ARC实验室）； MAIS, Institute of Automation, CAS, Beijing（自动化研究所北京研究所MAIS）

专题命中复杂问题求解：reasoning(abstract)

2510.01580 2025-10-03 eess.SY cs.SY 50%

Stability and Robustness of Time-Varying Opinion Dynamics: A Graph-Theoretic Approach

M. Hossein Abedinzadeh, Emrah Akyol

专题命中复杂问题求解：reasoning(abstract)

2510.00701 2025-10-02 cs.CV 50%

Graph Integrated Multimodal Concept Bottleneck Model

Jiakai Lin, Jinchang Zhang, Guoyu Lu

机构 * Intelligent Vision and Sensing (IVS) Lab at SUNY Binghamton（智能视觉与感知实验室（IVS）位于纽约州立大学布法罗分校）

专题命中复杂问题求解：reasoning(abstract)

2509.26641 2025-10-01 cs.CV 50%

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

Yuxin Song, Wenkai Dong, Shizun Wang, Qi Zhang, Song Xue, Tao Yuan, Hu Yang, Haocheng Feng, Hang Zhou, Xinyan Xiao, Jingdong Wang

机构 * Baidu VIS（百度视觉）； National University of Singapore（新加坡国立大学）

专题命中复杂问题求解：reasoning(abstract)

Comments 23 pages, 10 figures

2509.24200 2025-10-01 cs.CV 50%

UniVid: The Open-Source Unified Video Model

Jiabin Luo, Junhui Lin, Zeyu Zhang, Biao Wu, Meng Fang, Ling Chen, Hao Tang

机构 * Peking University（北京大学）； AI Geeks ； Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）

专题命中复杂问题求解：reasoning(abstract)

2508.20462 2025-10-01 cs.CY 50%

Automated Quality Assessment for LLM-Based Complex Qualitative Coding: A Confidence-Diversity Framework

Zhilong Zhao, Yindi Liu

专题命中复杂问题求解：reasoning(abstract)

Comments 21 pages, 2 figures, 5 tables. v2: revised abstract and JCSS-aligned prose; unified table formatting and naming; clean compile

2509.24943 2025-09-30 cs.CV 50%

Perceive, Reflect and Understand Long Video: Progressive Multi-Granular Clue Exploration with Interactive Agents

Jiahua Li, Kun Wei, Zhe Xu, Zibo Su, Xu Yang, Cheng Deng

机构 * School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）； Department of Computer Science and Engineering, Hong Kong University of Science and Technology（香港理工大学计算机科学与工程系）； College of Computer and Information, Hohai University（河海大学计算机与信息学院）

专题命中复杂问题求解：reasoning(abstract)

2503.16257 2025-09-30 cs.CV 50%

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Keda Tao, Haoxuan You, Yang Sui, Can Qin, Huan Wang

机构 * Zhejiang University（浙江大学）； Westlake University（西湖大学）； Columbia University（哥伦比亚大学）； Rice University（Rice大学）； Salesforce AI Research（Salesforce人工智能研究）

专题命中复杂问题求解：reasoning(abstract)

Comments 12 pages

2503.23758 2025-09-29 cond-mat.stat-mech math-ph math.MP 50%

Exact solution of the frustrated Potts model with next-nearest-neighbor interactions in one dimension via AI bootstrapping

Weiguo Yin

专题命中复杂问题求解：reasoning(abstract)

Comments The version accepted for publication. 6 pages, 4 figures, plus a 4-page Supplemental Material. The codes and data that support the findings of this article are openly available at https://community.wolfram.com/groups/-/m/t/3466026

Journal ref Phys. Rev. B 112, 094424 (2025)

2509.18475 2025-09-24 eess.SY cs.SY math.CT math.DS 50%

Compositional System Dynamics: The Higher Mathematics Underlying System Dynamics Diagrams & Practice

Xiaoyan Li, Evan Patterson, Patricia L. Mabry, Nathaniel D. Osgood

专题命中复杂问题求解：reasoning(abstract)

2509.15775 2025-09-22 cs.SD eess.AS 50%

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model

Yiqing Yang, Man-Wai Mak

机构 * Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（电子与电气工程系，香港理工大学）

专题命中复杂问题求解：reasoning(abstract)

Comments 5 pages, 2 figures

2509.14033 2025-09-22 cs.CV 50%

SAIL-VL2 Technical Report

Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng

机构 * Douyin SAIL Team（字节跳动 SAIL 团队）； LV-NUS Lab（NUS 实验室）

专题命中复杂问题求解：reasoning(abstract)

Comments Technical Report

2509.14889 2025-09-19 cs.RO 50%

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li, Huaping Liu

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）

专题命中复杂问题求解：reasoning(abstract)

Comments 8 pages, 5 figures, 3 tables

2509.11523 2025-09-16 cs.SE 50%

VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection

Ziliang Wang, Ge Li, Jia Li, Hao Zhu, Zhi Jin

专题命中复杂问题求解：reasoning(abstract)

2509.11447 2025-09-16 cs.CE cs.NA math.NA 50%

Large language model-empowered next-generation computer-aided engineering

Jiachen Guo, Chanwook Park, Dong Qian, Thomas J. R. Hughes, Wing Kam Liu

专题命中复杂问题求解：reasoning(abstract)

2412.05479 2025-09-16 cs.CV 50%

LATTE: Learning to Think with Vision Specialists

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

机构 * University of Washington（华盛顿大学）； Salesforce Research（Salesforce研究）

专题命中复杂问题求解：reasoning(abstract)

Journal ref EMNLP 2025

2509.09584 2025-09-12 cs.CV cs.RO 50%

Visual Grounding from Event Cameras

Lingdong Kong, Dongyue Lu, Ao Liang, Rong Li, Yuhao Dong, Tianshuai Hu, Lai Xing Ng, Wei Tsang Ooi, Benoit R. Cottereau

机构 * NUS（新加坡国立大学）； HKUST(GZ)（香港科技大学（广州））； NTU（南洋理工大学）； HKUST（香港科技大学）； I 2 R, A*STAR（新加坡科技研究局）； IPAL, CNRS（法国国家科学研究中心IPAL）； CerCo, CNRS（法国国家科学研究中心CerCo）

专题命中复杂问题求解：reasoning(abstract)

Comments Abstract Paper (Non-Archival) @ ICCV 2025 NeVi Workshop

2409.03521 2025-09-11 cs.CV 50%

Have Large Vision-Language Models Mastered Art History?

Ombretta Strafforello, Derya Soydaner, Michiel Willems, Anne-Sofie Maerten, Stefanie De Winter

机构 * KU Leuven（库勒韦恩大学）； Leiden University（莱顿大学）

专题命中复杂问题求解：reasoning(abstract)

2506.13905 2025-09-10 cs.AR 50%

Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

Zhongzhi Yu, Mingjie Liu, Michael Zimmer, Yingyan Celine Lin, Yong Liu, Haoxing Ren

专题命中复杂问题求解：reasoning(abstract)

2509.05695 2025-09-09 cs.CV 50%

Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization

Jingwei Peng, Zhixuan Qiu, Boyu Jin, Surasakdi Siripong

机构 * Tianjin Agricultural University（天津农业大学）； Walailak University（Walailak大学）

专题命中复杂问题求解：reasoning(abstract)

2509.04834 2025-09-08 cs.CV 50%

TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution

Yifei Jia, Shiyu Cheng, Yu Dong, Guan Li, Dong Tian, Ruixiao Peng, Xuyi Lu, Yu Wang, Wei Yao, Guihua Shan

专题命中复杂问题求解：reasoning(abstract)

2506.02353 2025-09-03 cs.RO 50%

SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition

Zhanxin Wu, Bo Ai, Tom Silver, Tapomayukh Bhattacharjee

机构 * Cornell University（康奈尔大学）； UC San Diego（南加州大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Conference on Robot Learning, Oral

2505.03735 2025-09-03 cs.CV 50%

Multi-Agent System for Comprehensive Soccer Understanding

Jiayuan Rao, Zifeng Li, Haoning Wu, Ya Zhang, Yanfeng Wang, Weidi Xie

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted by ACM MM 2025; Project Page: https://jyrao.github.io/SoccerAgent/

2508.19870 2025-08-28 cs.NI 50%

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

Yinqiu Liu, Ruichen Zhang, Haoxiang Luo, Yijing Lin, Geng Sun, Dusit Niyato, Hongyang Du, Zehui Xiong, Yonggang Wen, Abbas Jamalipour, Dong In Kim, Ping Zhang

专题命中复杂问题求解：reasoning(abstract)

Comments 35 pages

2508.19800 2025-08-28 q-bio.TO q-bio.BM 50%

A Multi-Layered Framework for Modeling Human Biology: From Basic AI Agents to a Full-Body AI Agent

Aoqi Wang, Jiajia Liu, Jianguo Wen, Yangyang Luo, Zhiwei Fan, Liren Yang, Xi Hu, Ruihan Luo, Yankai Yu, Sophia Li, Weiling Zhao, Xiaobo Zhou

专题命中复杂问题求解：reasoning(abstract)

2508.16652 2025-08-28 cs.CV 50%

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Ashwath Vaithinathan Aravindan, Abha Jha, Mihir Kulkarni

机构 * University of Southern California（南加州大学）

专题命中复杂问题求解：reasoning(abstract)

Comments To be published in Explainable Computer Vision: Quo Vadis? workshop at ICCV'25

2506.11803 2025-08-27 cs.MA 50%

PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems

Yingfan Deng, Anhao Zhou, Yuan Yuan, Xiao Zhang, Yifei Zou, Dongxiao Yu

专题命中复杂问题求解：reasoning(abstract)

Comments 5 pages,Latex;references added

2508.15903 2025-08-25 cs.CV 50%

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos

Kaining Li, Shuwei He, Zihan Xu

机构 * Xidian University（西电大学）

专题命中复杂问题求解：reasoning(abstract)

1. 复杂问题求解 5035 篇

Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization

Q-FSRU: Quantum-Augmented Frequency-Spectral For Medical Visual Question Answering

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Stability and Robustness of Time-Varying Opinion Dynamics: A Graph-Theoretic Approach

Graph Integrated Multimodal Concept Bottleneck Model

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

UniVid: The Open-Source Unified Video Model

Automated Quality Assessment for LLM-Based Complex Qualitative Coding: A Confidence-Diversity Framework

Perceive, Reflect and Understand Long Video: Progressive Multi-Granular Clue Exploration with Interactive Agents

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Exact solution of the frustrated Potts model with next-nearest-neighbor interactions in one dimension via AI bootstrapping

Compositional System Dynamics: The Higher Mathematics Underlying System Dynamics Diagrams & Practice

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model

SAIL-VL2 Technical Report

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection

Large language model-empowered next-generation computer-aided engineering

LATTE: Learning to Think with Vision Specialists

Visual Grounding from Event Cameras

Have Large Vision-Language Models Mastered Art History?

Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization

TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution

SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition

Multi-Agent System for Comprehensive Soccer Understanding

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

A Multi-Layered Framework for Modeling Human Biology: From Basic AI Agents to a Full-Body AI Agent

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

PE-MA: Parameter-Efficient Co-Evolution of Multi-Agent Systems

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos