大模型推理能力

Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability

Haiqi Yang, Jinzhe Li, Gengxu Li, Yi Chang, Yuan Wu

专题命中 推理评测 ：reasoning(abstract)

Comments 9pages, 2figures

From Waveforms to Pixels: A Survey on Audio-Visual Segmentation

Jia Li, Yapeng Tian

机构 * Department of Computer Science, The University of Texas at Dallas（计算机科学系，德克萨斯大学达拉斯分校） 纠错

专题命中 推理评测 ：reasoning(abstract)

Towards Zero-Shot Terrain Traversability Estimation: Challenges and Opportunities

Ida Germann, Mark O. Mints, Peer Neubert

机构 * Intelligent Autonomous Systems Group, Institute of Computational Visualisitics, University of Koblenz（智能自主系统组，计算可视化研究所，科隆大学） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted and presented at the 1st German Robotics Conference (GRC); March 13-15, 2025, Nuremberg, Germany https://ras.papercept.net/conferences/conferences/GRC25/program/GRC25_ContentListWeb_3.html#sada_48

VLH: Vision-Language-Haptics Foundation Model

Luis Francisco Moreno Fuentes, Muhammad Haris Khan, Miguel Altamirano Cabrera, Valerii Serpiva, Dmitri Iarchuk, Yara Mahmoud, Issatay Tokmurziyev, Dzmitry Tsetserukou

机构 * Intelligent Space Robotics Laboratory（智能空间机器人实验室） ； Skolkovo Institute of Science and Technology（斯克尔科沃科学与技术研究所） 纠错

专题命中 推理评测 ：reasoning(abstract)

MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models

Jiale Li, Mingrui Wu, Zixiang Jin, Hao Chen, Jiayi Ji, Xiaoshuai Sun, Liujuan Cao, Rongrong Ji

机构 * Xiamen University（厦门大学） ； Zhongguancun Academy（中关村学院） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments ACM MM25 has accepted this paper

Minimum Data, Maximum Impact: 20 annotated samples for explainable lung nodule classification

Luisa Gallée, Catharina Silvia Lisson, Christoph Gerhard Lisson, Daniela Drees, Felix Weig, Daniel Vogele, Meinrad Beer, Michael Götz

机构 * Experimental Radiology, Ulm University Medical Center, Ulm, Germany（实验放射学，乌尔姆大学医学中心，乌尔姆，德国） ； Department of Diagnostic and Interventional Radiology, Ulm University Medical Center, Ulm, Germany（诊断与介入放射学系，乌尔姆大学医学中心，乌尔姆，德国） ； XAIRAD - Cooperation for Artificial Intelligence in Experimental Radiology, Ulm, Germany（XAIRAD - 实验放射学中的人工智能合作） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted at iMIMIC - Interpretability of Machine Intelligence in Medical Image Computing workshop MICCAI 2025 Medical Image Computing and Computer Assisted Intervention

CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography

Murong Xu, Tamaz Amiranashvili, Fernando Navarro, Maksym Fritsak, Ibrahim Ethem Hamamci, Suprosanna Shit, Bastian Wittmann, Sezgin Er, Sebastian M. Christ, Ezequiel de la Rosa, Julian Deseoe, Robert Graf, Hendrik Möller, Anjany Sekuboyina, Jan C. Peeken, Sven Becker, Giulia Baldini, Johannes Haubold, Felix Nensa, René Hosch, Nikhil Mirajkar, Saad Khalid, Stefan Zachow, Marc-André Weber, Georg Langs, Jakob Wasserthal, Mehmet Kemal Ozdemir, Andrey Fedorov, Ron Kikinis, Stephanie Tanadini-Lang, Jan S. Kirschke, Stephanie E. Combs, Bjoern Menze

机构 * Department of Quantitative Biomedicine, University of Zurich（定量生物医学系，苏黎世大学） ； ETH AI Center, ETH Zurich（ETH人工智能中心，苏黎世联邦理工学院） ； Department of Radiation Oncology, University Hospital and University of Zurich（放射肿瘤科，苏黎世大学医院和苏黎世大学） ； Faculty of Medicine, University of Zurich（医学系，苏黎世大学） ； Department of Neurology and Clinical Neuroscience Center, University Hospital Zurich and University of Zurich（神经科和临床神经科学中心，苏黎世大学医院和苏黎世大学） ； International School of Medicine, Istanbul Medipol University（国际医学院，伊斯坦布尔Medipol大学） ； School of Computation, Information and Technology, Technical University of Munich（计算、信息与技术学院，慕尼黑技术大学） ； Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Technical University of Munich（诊断与介入神经放射科，医学与健康学院，慕尼黑技术大学） ； Department of Radiation Oncology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich（放射肿瘤科，慕尼黑技术大学医院Rechts der Isar，慕尼黑技术大学医学与健康学院） ； Institute of Radiation Medicine (IRM), Helmholtz Zentrum München (HMGU)（放射医学研究所（IRM），亥姆霍兹慕尼黑研究中心（HMGU）） ； German Consortium for Translational Cancer Research (DKTK), Partner Site Munich, Munich, Germany（德国转化癌症研究联盟（DKTK），慕尼黑分部，德国） ； University Hospital Essen, Institute of Interventional and Diagnostic Radiology and Neuroradiology（埃森大学医院，介入与诊断放射学及神经放射学研究所） ； University Hospital Essen, Institute for Artificial Intelligence in Medicine（埃森大学医院，医学人工智能研究所） ； Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, University Medical Center Rostock（诊断与介入放射学、儿童放射学及神经放射学研究所，罗斯托克大学医学中心） ； Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna（生物医学成像与图像引导治疗系，维也纳医科大学） ； Department of Radiology, University Hospital Basel（放射科，巴塞尔大学医院） ； Department of Radiology, Cambridge University Hospitals NHS Foundation Trust（放射科，剑桥大学医院 NHS 基础信托） ； Labelata GmbH（Labelata 公司） ； Visual and Data-Centric Computing, Zuse Institute Berlin (ZIB)（视觉与数据导向计算，柏林 Zuse 研究所（ZIB）） ； Brigham and Women’s Hospital（布里格姆和女性医院） 纠错

专题命中 推理评测 ：planning(abstract)

ChatVis: Large Language Model Agent for Generating Scientific Visualizations

Tom Peterka, Tanwi Mallick, Orcun Yildiz, David Lenz, Cory Quammen, Berk Geveci

专题命中 推理评测 ：chain-of-thought(abstract)

See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs

Ziyun Dai, Xiaoqiang Li, Shaohua Zhang, Yuanchen Wu, Jide Li

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted by ACM MM25

Journal ref 33rd ACM International Conference on Multimedia 2025

Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention

Syed Haider Ali, Asrar Ahmad, Muhammad Ali, Asifullah Khan, Nadeem Shaukat

机构 * Department of Medical Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS)（医学系，巴基斯坦工程与应用科学研究所） ； Pakistan Institute of Engineering and Applied Sciences (PIEAS)（巴基斯坦工程与应用科学研究所） ； Department of Physics & Applied Mathematics, Pakistan Institute of Engineering and Applied Sciences (PIEAS)（物理与应用数学系，巴基斯坦工程与应用科学研究所） ； Center for Mathematical Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS)（数学科学中心，巴基斯坦工程与应用科学研究所） ； Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences（模式识别实验室，计算机与信息科学系，巴基斯坦工程与应用科学研究所） ； Pakistan Institute of Engineering & Applied Sciences（巴基斯坦工程与应用科学研究所） ； Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering & Applied Sciences（人工智能中心（PAIC），巴基斯坦工程与应用科学研究所） 纠错

专题命中 推理评测 ：planning(abstract)

Comments 16 pages, 5 figures

Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation

Adam Kostka, Jarosław A. Chudziak

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted at CogSci 2025

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO

Wei Guan, Jun Lan, Jian Cao, Hao Tan, Huijia Zhu, Weiqiang Wang

专题命中 推理评测 ：reasoning(abstract)

Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Farzana Abdulzada

专题命中 推理评测 ：planning(abstract)

Object-centric Video Question Answering with Visual Grounding and Referring

Haochen Wang, Qirui Chen, Cilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, Weidi Xie, Stratis Gavves

机构 * University of Amsterdam（阿姆斯特丹大学） ； SAI, Shanghai Jiao Tong University（上海交通大学SAI研究所） ； Xiaohongshu Inc（小红书公司） 纠错

专题命中 推理评测 ：reasoning(abstract)

How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts

Ngoc Luyen Le, Marie-Hélène Abel

专题命中 推理评测 ：reasoning(abstract)

PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior

Junda Wu, Jessica Echterhoff, Kyungtae Han, Amr Abdelraouf, Rohit Gupta, Julian McAuley

机构 * Computer Science and Engineering University of California San Diego（计算机科学与工程大学加州大学圣地亚哥分校） ； InfoTech Labs Toyota Motor North America（信息科技实验室丰田北美） 纠错

专题命中 推理评测 ：reasoning(abstract)

DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis

Minxi Ouyang, Lianghui Zhu, Yaqing Bao, Qiang Huang, Jingli Ouyang, Tian Guan, Xitong Ling, Jiawen Li, Song Duan, Wenbin Dai, Li Zheng, Xuemei Zhang, Yonghong He

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Department of Pathology, Liuzhou People’s Hospital Affiliated to Guangxi Medical University（广西医科大学柳州市人民医院病理科） ； Department of Immunology, College of Basic Medical Sciences, China Medical University（中国医科大学基础医学学院免疫科） ； Greater Bay Area Center for Medical Device Evaluation and Inspection.NMPA（粤港澳大湾区医疗器械评价和检验中心.NMPA） ； Shenzhen Shengqiang Technology Co., Ltd.（深圳盛强科技有限公司） ； Department of Pathology, Chongqing University Affiliated Three Gorges Hospital（重庆大学附属第三人民医院病理科） 纠错

专题命中 推理评测 ：reasoning(abstract)

T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation

Yubin Chen, Xuyang Guo, Zhenmei Shi, Zhao Song, Jiahao Zhang

机构 * San Jose State University（圣何塞州立大学） ； Guilin University of Electronic Technology（桂林电子科技大学） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 推理评测 ：reasoning(abstract)

LLMShot: Reducing snapshot testing maintenance via LLMs

Ergün Batuhan Kaynak, Mayasah Lami, Sahand Moslemi, Anil Koyuncu

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted to ICSME 2025

Reusing Attention for One-stage Lane Topology Understanding

Yang Li, Zongzheng Zhang, Xuchong Qiu, Xinrun Li, Ziming Liu, Leichen Wang, Ruikai Li, Zhenxin Zhu, Huan-ang Gao, Xiaojian Lin, Zhiyong Cui, Hang Zhao, Hao Zhao

机构 * Institute for AI Industry Research, Tsinghua University（人工智能产业研究院，清华大学） ； Bosch Corporate Research, China（博世企业研究，中国） ； Institute for Interdisciplinary Information Sciences, Tsinghua University（交叉信息科学研究院，清华大学） ； Department of Computer Science, ETH Zürich（计算机科学系，苏黎世联邦理工学院） ； State Key Lab of Intelligent Transportation System, Beihang University（智能交通系统国家重点实验室，北航） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted to IROS 2025, Project Page: https://github.com/Yang-Li-2000/one-stage.git

VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding

Younggun Kim, Ahmed S. Abdelrahman, Mohamed Abdel-Aty

机构 * University of Central Florida（中央佛罗里达大学） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments 22 pages, 11 figures, 5 tables

Can Your Model Separate Yolks with a Water Bottle? Benchmarking Physical Commonsense Understanding in Video Generation Models

Enes Sanli, Baris Sarper Tezcan, Aykut Erdem, Erkut Erdem

专题命中 推理评测 ：reasoning(abstract)

ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts

Lyuye Zhang, Kaixuan Li, Kairan Sun, Daoyuan Wu, Ye Liu, Haoye Tian, Yang Liu

专题命中 推理评测 ：chain-of-thought(abstract)

Comments This is a technical report from Nanyang Technological University

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models

Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Haiyan Zhao, Mengnan Du

机构 * Northwestern University（西北大学） ； NewsBreak ； New Jersey Institute of Technology（新泽西理工学院） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments 20 Pages, 18 Figures

NPUEval: Optimizing NPU Kernels with LLMs and Open Source Compilers

Sarunas Kalade, Graham Schelle

专题命中 推理评测 ：reasoning(abstract)

Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation

Genki Kusano, Kosuke Akimoto, Kunihiro Takeoka

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted to ACM RecSys2025 reproducibility

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems

Yu Cui, Hongyang Du

专题命中 推理评测 ：reasoning(abstract)

Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval

Sangam Lee, Ryang Heo, SeongKu Kang, Dongha Lee

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted to COLM 2025

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation

Sahid Hossain Mustakim, S M Jishanul Islam, Ummay Maria Muna, Montasir Chowdhury, Mohammed Jawwadul Islam, Sadia Ahmmed, Tashfia Sikder, Syed Tasdid Azam Dhrubo, Swakkhar Shatabda

机构 * United International University（国际大学） ； BRAC University（BRAC大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Bangladesh University of Professionals（孟加拉专业大学） ； University of Alberta（阿尔伯塔大学） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments Accepted as long paper, SVU Workshop at ICCV 2025

DRISHTIKON: Visual Grounding at Multiple Granularities in Documents

Badri Vishal Kasuba, Parag Chaudhuri, Ganesh Ramakrishnan

专题命中 推理评测 ：reasoning(abstract)

Comments Work in Progress