视觉大模型 / VLM - arXivDaily 专题

2511.00776 2025-11-04 cs.SE 50%

A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI

Cuiyun Gao, Guodong Fan, Chun Yong Chong, Shizhan Chen, Chao Liu, David Lo, Zibin Zheng, Qing Liao

专题命中幻觉与鲁棒性：grounding(abstract)

2510.20223 2025-10-24 cs.CR cs.MM 50%

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations

Divyanshu Kumar, Shreyas Jena, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

2510.19886 2025-10-24 cs.CL 50%

An Expert-grounded benchmark of General Purpose LLMs in LCA

Artur Donaldson, Bharathan Balaji, Cajetan Oriekezie, Manish Kumar, Laure Patouillard

机构 * PRé Sustainability B.V.（PRé可持续性公司）； Amazon（亚马逊）

专题命中幻觉与鲁棒性：grounding(abstract)

2510.16198 2025-10-21 cs.CL 50%

EgMM-Corpus: A Multimodal Vision-Language Dataset for Egyptian Culture

Mohamed Gamil, Abdelrahman Elsayed, Abdelrahman Lila, Ahmed Gad, Hesham Abdelgawad, Mohamed Aref, Ahmed Fares

机构 * Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11629, Egypt（电气工程系，谢布拉工程学院，本海大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)

2510.13190 2025-10-16 cs.CL 50%

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs

Juan Ren, Mark Dras, Usman Naseem

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)

Comments Preprint

2506.16012 2025-10-14 cs.RO 50%

DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning

Boyu Li, Siyuan He, Hang Xu, Haoqi Yuan, Yu Zang, Liwei Hu, Junpeng Yue, Zhenxiong Jiang, Pengbo Hu, Börje F. Karlsson, Yehui Tang, Zongqing Lu

专题命中幻觉与鲁棒性：vision language model(abstract)

Comments The experiments in the paper need to be further supplemented, and more methods should be considered for expansion

2510.01929 2025-10-03 cs.CL 50%

Inverse Language Modeling towards Robust and Grounded LLMs

Davide Gabrielli, Simone Sestito, Iacopo Masi

机构 * Sapienza University of Rome（罗马萨皮恩扎大学）； OmnAI Lab（OmnAI实验室）

专题命中幻觉与鲁棒性：grounding(abstract)

2509.22486 2025-09-29 cs.IR cs.CR 50%

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks

Gaurav Bagwe, Saket S. Chaturvedi, Xiaolong Ma, Xiaoyong Yuan, Kuang-Ching Wang, Lan Zhang

专题命中幻觉与鲁棒性：grounding(abstract)

Comments Accepted by EMNLP 2025

2509.14446 2025-09-19 q-bio.NC 50%

Mouse vs. AI: A Neuroethological Benchmark for Visual Robustness and Neural Alignment

Marius Schneider, Joe Canzano, Jing Peng, Yuchen Hou, Spencer LaVere Smith, Michael Beyeler

专题命中幻觉与鲁棒性：grounding(abstract)

2509.13127 2025-09-17 cs.CL 50%

Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning

Sijia Cui, Shuai Xu, Aiyao He, Yanna Wang, Bo Xu

机构 * 1 Institute of Automation, Chinese Academy of Sciences, Beijing, China ； 2 School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China ； 3 Nanjing Artificial Intelligence Research of IA, Nanjing, China ； 4 University of Chinese Academy of Sciences,Nanjing, Nanjing, China ； 5 Nanjing University of Information Science \& Technology, Nanjing, China

专题命中幻觉与鲁棒性：grounding(abstract)

Comments Accepted to IJCNN 2025

2509.05838 2025-09-09 cs.CY 50%

Towards an Automated Framework to Audit Youth Safety on TikTok

Linda Xue, Francesco Corso, Nicolo' Fontana, Geng Liu, Stefano Ceri, Francesco Pierri

专题命中幻觉与鲁棒性：vision-language model(abstract)

Comments 7 pages, 3 figures, submitted to EMNLP 2025 and ECAT Research Workshop 2025

2509.04214 2025-09-05 cs.CR 50%

An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline

Tyler Shumaker, Jessica Carpenter, David Saranchak, Nathaniel D. Bastian

专题命中幻觉与鲁棒性：vision language model(abstract)

2509.03787 2025-09-05 cs.IR cs.CL 50%

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai

机构 * University of Waterloo（滑铁卢大学）； Toronto Metropolitan University（多伦多 Metropolitan 大学）

专题命中幻觉与鲁棒性：grounding(abstract)

2502.13053 2025-08-07 cs.CL 50%

Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks

Yurun Chen, Xavier Hu, Keting Yin, Juncheng Li, Shengyu Zhang

机构 * School of Software Technology Zhejiang University Hangzhou Zhejiang China（软件技术学院浙江大学杭州浙江中国）； Zhejiang University（浙江大学）

专题命中幻觉与鲁棒性：MLLM(abstract)

Comments Accepted at ACM MM 2025 Main Conference

2505.04980 2025-07-16 cs.RO cs.SY eess.SY 50%

LVLM-MPC Collaboration for Autonomous Driving: A Safety-Aware and Task-Scalable Control Architecture

Kazuki Atsuta, Kohei Honda, Hiroyuki Okuda, Tatsuya Suzuki

机构 * Department of Mechanical Systems Engineering（机械系统工程系）； Nagoya University（名古屋大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)

Comments 8 pages, 8 figures

2507.08203 2025-07-14 cs.CL 50%

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs

Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sungmin Kang, Alperen Öziş, Hayrettin Eren Yildiz, Mitash Ashish Shah, Zhiqi Huang, Anoop Kumar, Alfy Samuel, Daben Liu, Sai Praneeth Karimireddy, Salman Avestimehr

机构 * University of Southern California（南加州大学）； Bogazici University（博鲁斯大学）； Capital One（Capital One公司）

专题命中幻觉与鲁棒性：grounding(abstract)

2507.00740 2025-07-02 cs.CR cs.CL cs.DC 50%

Safe Low Bandwidth SPV: A Formal Treatment of Simplified Payment Verification Protocols and Security Bounds

Craig S Wright

机构 * University of Exeter Business School（埃克塞特大学商学院）

专题命中幻觉与鲁棒性：grounding(abstract)

Comments 56 pages 5 images

2506.20944 2025-06-27 cs.MM cs.CR 50%

E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs

Van-Hoang Phan, Long-Khanh Pham, Dang Vu, Anh-Duy Tran, Minh-Son Dao

专题命中幻觉与鲁棒性：vision-language model(abstract)

Comments Accepted to AsiaCCS 2025 @ SCID

2406.15677 2025-06-27 cs.RO 50%

Learning Efficient and Robust Language-conditioned Manipulation using Textual-Visual Relevancy and Equivariant Language Mapping

Mingxi Jia, Haojie Huang, Zhewen Zhang, Chenghao Wang, Linfeng Zhao, Dian Wang, Jason Xinyu Liu, Robin Walters, Robert Platt, Stefanie Tellex

机构 * Brown University（布朗大学）； Northeastern University（东北大学）

专题命中幻觉与鲁棒性：vision-language model(abstract)

2403.13198 2025-06-18 cs.RO 50%

LBAP: Improved Uncertainty Alignment of LLM Planners using Bayesian Inference

James F. Mullen, Dinesh Manocha

机构 * University of Maryland, College Park（马里兰大学学院公园分校）

专题命中幻觉与鲁棒性：grounding(abstract)

2506.00054 2025-06-03 cs.IR cs.CL 50%

Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

Chaitanya Sharma

机构 * Independent Researcher（独立研究者）

专题命中幻觉与鲁棒性：grounding(abstract)

2411.02391 2025-05-27 cs.CL 50%

Attacking Vision-Language Computer Agents via Pop-ups

Yanzhe Zhang, Tao Yu, Diyi Yang

机构 * Georgia Tech（佐治亚理工学院）； The University of Hong Kong（香港大学）； Stanford University（斯坦福大学）

专题命中幻觉与鲁棒性：VLM(abstract)

Comments ACL 2025

2505.16703 2025-05-23 cs.CL 50%

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

Zeping Yu, Sophia Ananiadou

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

2503.02589 2025-05-21 cs.CL cs.IR 50%

MCiteBench: A Multimodal Benchmark for Generating Text with Citations

Caiyu Hu, Yikai Zhang, Tinghui Zhu, Yiwei Ye, Yanghua Xiao

机构 * Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学 key 实验室，计算机科学学院，复旦大学）

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

Comments https://caiyuhu.github.io/MCiteBench/

2505.04960 2025-05-09 cs.IR cs.MM 50%

Learning Item Representations Directly from Multimodal Features for Effective Recommendation

Xin Zhou, Xiaoxiong Zhang, Dusit Niyato, Zhiqi Shen

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

Comments Code: https://github.com/enoche/LIRDRec

2411.05474 2025-04-29 cs.RO 50%

Enhancing Robustness in Language-Driven Robotics: A Modular Approach to Failure Reduction

Émiland Garrabé, Pierre Teixeira, Mahdi Khoramshahi, Stéphane Doncieux

机构 * ISIR, Sorbonne Université, Paris（ISIR，索邦大学，巴黎）

专题命中幻觉与鲁棒性：grounding(abstract)

Comments Submitted to ICRA 2025

2504.04103 2025-04-11 cs.CE 50%

LATTE: Lightweight Attention-based Traffic Accident Anticipation Engine

Jiaxun Zhang, Yanchen Guan, Chengyue Wang, Haicheng Liao, Guohui Zhang, Zhenning Li

专题命中幻觉与鲁棒性：vision-language model(abstract)

Comments Accept by Information Fusion (Elsevier)

2503.10690 2025-03-17 cs.CL cs.CR 50%

Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models

Shahnewaz Karim Sakib, Anindya Bijoy Das, Shibbir Ahmed

专题命中幻觉与鲁棒性：LLaVA(abstract)

2503.05529 2025-03-10 stat.AP cs.SI 50%

PoSSUM: A Protocol for Surveying Social-media Users with Multimodal LLMs

Roberto Cerina

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

2502.09940 2025-02-17 cs.CL cs.SD eess.AS 50%

A Preliminary Exploration with GPT-4o Voice Mode

Yu-Xiang Lin, Chih-Kai Yang, Wei-Chih Chen, Chen-An Li, Chien-yu Huang, Xuanjun Chen, Hung-yi Lee

专题命中幻觉与鲁棒性：multimodal large language model(abstract)

Comments Work in progress

1. 幻觉与鲁棒性 2277 篇

A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations

An Expert-grounded benchmark of General Purpose LLMs in LCA

EgMM-Corpus: A Multimodal Vision-Language Dataset for Egyptian Culture

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs

DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning

Inverse Language Modeling towards Robust and Grounded LLMs

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks

Mouse vs. AI: A Neuroethological Benchmark for Visual Robustness and Neural Alignment

Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning

Towards an Automated Framework to Audit Youth Safety on TikTok

An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks

LVLM-MPC Collaboration for Autonomous Driving: A Safety-Aware and Task-Scalable Control Architecture

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs

Safe Low Bandwidth SPV: A Formal Treatment of Simplified Payment Verification Protocols and Security Bounds

E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs

Learning Efficient and Robust Language-conditioned Manipulation using Textual-Visual Relevancy and Equivariant Language Mapping

LBAP: Improved Uncertainty Alignment of LLM Planners using Bayesian Inference

Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

Attacking Vision-Language Computer Agents via Pop-ups

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

MCiteBench: A Multimodal Benchmark for Generating Text with Citations

Learning Item Representations Directly from Multimodal Features for Effective Recommendation

Enhancing Robustness in Language-Driven Robotics: A Modular Approach to Failure Reduction

LATTE: Lightweight Attention-based Traffic Accident Anticipation Engine

Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models

PoSSUM: A Protocol for Surveying Social-media Users with Multimodal LLMs

A Preliminary Exploration with GPT-4o Voice Mode