大模型对齐与安全

SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting

Paschalis Giakoumoglou, Dimitrios Karageorgiou, Symeon Papadopoulos, Panagiotis C. Petrantonakis

机构 * Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki（阿尔伯塔大学电气与计算机工程系） ； Information Technologies Institute, CERTH（信息科技研究所） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments ICCV2025

Uncertainty Awareness in Wireless Communications and Sensing

Shixiong Wang, Wei Dai, Jianyong Sun, Zongben Xu, Geoffrey Ye Li

专题命中 幻觉与事实性 ：trustworthy(abstract)

Journal ref IEEE Communications Magazine, July 2025

Decentralized Uncertainty-Aware Multi-Agent Collision Avoidance with Model Predictive Path Integral

Stepan Dergachev, Konstantin Yakovlev

机构 * FRC CSC RAS（俄罗斯科学院应用数学与控制论研究所） ； HSE University（俄罗斯高等经济大学） ； AIRI（人工智能研究所） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

Comments This is a pre-print of the paper accepted to IROS2025. The manuscript includes 8 pages, 4 figures, and 1 table. A supplementary video is available at https://youtu.be/_D4zDYJ4KCk Updated version: added link to source code in the abstract; updated experimental results description in Section VI.A; updated author affiliation and funding information; minor typo corrections

BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems

Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger

机构 * University of Gothenburg（哥德堡大学） ； Chalmers University of Technology（查尔姆斯理工大学） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

Comments Accepted in The IEEE International Conference on Intelligent Transportation Systems (ITSC)2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

Qiyan Zhao, Xiaofeng Zhang, Yiheng Li, Yun Xing, Xiaosong Yuan, Feilong Tang, Sinan Fan, Xuhang Chen, Xuyao Zhang, Dahan Wang

机构 * FKLPRIU, Xiamen University of Technology, China（福克斯理工国际大学，厦门理工学院，中国） ； Shanghai Jiao Tong University, China（上海交通大学，中国） ； Nanyang Technological University, Singapore（南洋理工大学，新加坡） ； Jilin University, China（吉林大学，中国） ； Monash University, Australia（墨尔本大学，澳大利亚） ； Zhejiang University, China（浙江大学，中国） ； Huizhou University, China（惠州大学，中国） ； Chinese Academy of Sciences, China（中国科学院，中国） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments Accepted in ACM MM 2025

LLM-based ambiguity detection in natural language instructions for collaborative surgical robots

Ana Davila, Jacinto Colan, Yasuhisa Hasegawa

机构 * Institutes of Innovation for Future Society, Nagoya University（未来社会创新研究所，名古屋大学） ； Department of Micro-Nano Mechanical Science and Engineering, Nagoya University（微纳米机械科学与工程系，名古屋大学） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

Comments Accepted at 2025 IEEE International Conference on Robot and Human Interactive Communication (ROMAN)

Journal ref 2025 IEEE International Conference on Robot and Human Interactive Communication (ROMAN)

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

Xiao Liang, Di Wang, Zhicheng Jiao, Ronghan Li, Pengfei Yang, Quan Wang, Tat-Seng Chua

机构 * The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, Xidian University, China（陕西省智能人机交互与可穿戴技术重点实验室，西安电子科技大学） ； Warren Alpert Medical School, Brown University, USA（布朗大学沃伦·阿尔珀特医学院） ； National University of Singapore, Singapore（新加坡国立大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap

Kaicheng Huang, Fanyu Wang, Yutan Huang, Chetan Arora

专题命中 幻觉与事实性 ：trustworthy(abstract)

Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model

Nokimul Hasan Arif, Shadman Rabby, Md Hefzul Hossain Papon, Sabbir Ahmed

专题命中 幻觉与事实性 ：trustworthy(abstract)

Comments Submitted for review in NCAA Springer, 21 pages, 4 figures, 4 Tables

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs

Yixuan Wu, Yang Zhang, Jian Wu, Philip Torr, Jindong Gu

机构 * University of Oxford（牛津大学） ； Zhejiang University（浙江大学） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation

Shuaiye Lu, Linjiang Zhou, Xiaochuan Shi

机构 * Wuhan University（武汉大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs

Zijian Zhang, Xuecheng Wu, Danlei Huang, Siyu Yan, Chong Peng, Xuezhi Cao

机构 * Xi'an Jiaotong University（西安交通大学） ； East China Normal University（华东师范大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Sense and Sensibility: What makes a social robot convincing to high-school students?

Pablo Gonzalez-Oliveras, Olov Engwall, Ali Reza Majlesi

机构 * Dept. of Intelligent Systems, KTH Royal Institute of Technology, Stockholm, Sweden（智能系统系，皇家理工学院） ； Dept. of Education, Stockholm University, Stockholm, Sweden（教育系，斯德哥尔摩大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments 14 pages; 8 figures; 3 tables; RSS 2025 (Robotics: Science & Systems)

Neural Network Certification Informed Power System Transient Stability Preventive Control with Renewable Energy

Tong Su, Junbo Zhao

专题命中 幻觉与事实性 ：safety(abstract)

Journal ref IEEE Transactions on Power Systems, 2025

Evaluating explainable AI for deep learning-based network intrusion detection system alert classification

Rajesh Kalakoti, Risto Vaarandi, Hayretdin Bahsi, Sven Nõmm

专题命中 幻觉与事实性 ：alignment(abstract)

Comments Accepted version of a paper published in the Proceedings of the 11th International Conference on Information Systems Security and Privacy (ICISSP 2025). Final version available via SCITEPRESS

HJRNO: Hamilton-Jacobi Reachability with Neural Operators

Yankai Li, Mo Chen

机构 * School of Computing Science（计算科学学院） ； Simon Fraser University（西蒙弗雷泽大学） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems

Amra Ramic, Stefan Kugele

专题命中 幻觉与事实性 ：safety(abstract)

Comments 8 pages, 10 figures, 4 tables

LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization

Zirui Shang, Xinxiao Wu, Shuo Yang

机构 * Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology（北京智能信息科技重点实验室，计算机科学与技术学院） ； Beijing Institute of Technology（北京理工大学） ； Guangdong Laboratory of Machine Perception and Intelligent Computing（广东机器感知与智能计算实验室） ； Shenzhen MSU-BIT University（深圳MSU-BIT大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification

Long Hui, Wai Lok Yeung

机构 * Sky Long Artificial Intelligence Company（Sky Long人工智能公司） ； Berkeley（伯克利） 纠错

专题命中 幻觉与事实性 ：trustworthy(abstract)

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

Weihao Xuan, Qingcheng Zeng, Heli Qi, Junjue Wang, Naoto Yokoya

专题命中 幻觉与事实性 ：alignment(abstract)

DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments

Kota Kondo, Mason Peterson, Nicholas Rober, Juan Rached Viso, Lucas Jia, Jialin Chen, Harvey Merton, Jonathan P. How

专题命中 幻觉与事实性 ：safety(abstract)

Comments 20 pages, 30 figures, Under review at IEEE Transactions on Robotics

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Xin Zou, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Kening Zheng, Sirui Huang, Junkai Chen, Peijie Jiang, Jia Liu, Chang Tang, Xuming Hu

专题命中 幻觉与事实性 ：alignment(abstract)

Comments Accepted by ICML 2025

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Weijia Wu, Zhuang Li, Yefei He, Mike Zheng Shou, Chunhua Shen, Lele Cheng, Yan Li, Tingting Gao, Di Zhang

机构 * Kuaishou Technology（快手科技） ； Zhejiang University（浙江大学） ； Show Lab, National University of Singapore（新加坡国立大学Show实验室） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments The project website is at: https://weijiawu.github.io/ParaDiffusionPage/. Code: https://github.com/weijiawu/ParaDiffusion

Journal ref IJCV 2025

Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration

Dominik Werner Wolf, Alexander Braun, Markus Ulrich

机构 * Machine Vision Metrology Group of the Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院机器视觉计量组） ； Volkswagen Group（大众集团） ； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院） ； University of Applied Sciences Duesseldorf (HSD)（杜塞尔多夫应用技术大学） 纠错

专题命中 幻觉与事实性 ：trustworthy(abstract)

Comments Under review at IEEE Transactions on Intelligent Transportation Systems (T-ITS)

Automating Nanoindentation: Optimizing Workflows for Precision and Accuracy

Vivek Chawla, Dayakar Penumadu, Sergei Kalinin

专题命中 幻觉与事实性 ：alignment(abstract)

Comments 26 pages (Including supplemental information), 13 figures, 0 Tables

StoryGPT-V: Large Language Models as Consistent Story Visualizers

Xiaoqian Shen, Mohamed Elhoseiny

机构 * KAUST（卡塞姆大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments Accepted to CVPR 2025; Project page: https://xiaoqian-shen.github.io/StoryGPT-V

Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning

Ehsan Ahmadi, Chao Wang

机构 * Bert S. Turner Department of Construction Management, Louisiana State University, Baton Rouge, LA 70803（伯特·S·特纳建设管理系，路易斯安那州立大学，巴吞鲁日，LA 70803） 纠错

专题命中 幻觉与事实性 ：safety(abstract)

Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence

Heming Fu, Guojun Xiong, Jian Li, Shan Lin

专题命中 幻觉与事实性 ：alignment(abstract)

Comments ACM SIGMETRICS 2025 Workshop

FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting

Liyao Jiang, Negar Hassanpour, Mohammad Salameh, Mohan Sai Singamsetti, Fengyu Sun, Wei Lu, Di Niu

专题命中 幻觉与事实性 ：alignment(abstract)

Comments TMLR 2025

Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding

Jinlong Li, Cristiano Saltori, Fabio Poiesi, Nicu Sebe

专题命中 幻觉与事实性 ：alignment(abstract)

Comments Accepted by CVPR 2025