大模型对齐与安全

Specialized Foundation Models for Intelligent Operating Rooms

Ege Özsoy, Chantal Pellegrini, David Bani-Harouni, Kun Yuan, Matthias Keicher, Nassir Navab

专题命中 安全评测 ：safety(abstract)

AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM

Ruchao Fan, Bo Ren, Yuxuan Hu, Rui Zhao, Shujie Liu, Jinyu Li

专题命中 安全评测 ：alignment(abstract)

Comments To be published in the Journal of Selected Topics in Signal Processing (JSTSP)

A Vehicle-in-the-Loop Simulator with AI-Powered Digital Twins for Testing Automated Driving Controllers

Zengjie Zhang, Giannis Badakis, Michalis Galanis, Adem Bavarşi, Edwin van Hassel, Mohsen Alirezaei, Sofie Haesaert

机构 * Department of Electrical Engineering, Eindhoven University of Technology（电子工程系，埃因霍温理工大学） ； Siemens Digital Industries Software（西门子数字工业软件） ； Department of Mechanical Engineering, Eindhoven University of Technology（机械工程系，埃因霍温理工大学） 纠错

专题命中 安全评测 ：safety(abstract)

Human-Centered Explainability in Interactive Information Systems: A Survey

Yuhao Zhang, Jiaxin An, Ben Wang, Yan Zhang, Jiqun Liu

专题命中 安全评测 ：trustworthy(abstract)

SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement

Weijie Yin, Dingkang Yang, Hongyuan Dong, Zijian Kang, Jiacong Wang, Xiao Liang, Chao Feng, Jiao Ran

机构 * ByteDance Inc.（字节跳动公司） ； College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments We release SAILViT, a series of versatile vision foundation models

AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation

Xiao Liu, Jiawei Zhang

机构 * IFM Lab, University of California, Davis（信息与媒体实验室，加州大学戴维斯分校） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Working in Progress

A Comprehensive Review of Human Error in Risk-Informed Decision Making: Integrating Human Reliability Assessment, Artificial Intelligence, and Human Performance Models

Xingyu Xiao, Hongxu Zhu, Jingang Liang, Jiejuan Tong, Haitao Wang

专题命中 安全评测 ：safety(abstract)

Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration

Haoxiang Luo, Yinqiu Liu, Ruichen Zhang, Jiacheng Wang, Gang Sun, Dusit Niyato, Hongfang Yu, Zehui Xiong, Xianbin Wang, Xuemin Shen

专题命中 安全评测 ：trustworthy(abstract)

Out-of-distribution detection in 3D applications: a review

Zizhao Li, Xueyang Kang, Joseph West, Kourosh Khoshelham

机构 * The University of Melbourne（墨尔本大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Out-of-Distribution Detection with Adaptive Top-K Logits Integration

Hikaru Shijo, Yutaka Yoshihama, Kenichi Yadani, Norifumi Murata

机构 * Panasonic Automotive Systems Co Ltd（松下汽车系统株式会社） 纠错

专题命中 安全评测 ：safety(abstract)

Calligrapher: Freestyle Text Image Customization

Yue Ma, Qingyan Bai, Hao Ouyang, Ka Leong Cheng, Qiuyu Wang, Hongyu Liu, Zichen Liu, Haofan Wang, Jingye Chen, Yujun Shen, Qifeng Chen

机构 * Hong Kong University of Science and Technology（香港理工大学） ； InstantX 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Project page: https://calligrapher2025.github.io/Calligrapher Code: https://github.com/Calligrapher2025/Calligrapher

Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation

Chang Liu, Yixin Wang, Moontae Lee

专题命中 安全评测 ：alignment(abstract)

Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations

Zhihao Yuan, Shuyi Jiang, Chun-Mei Feng, Yaolun Zhang, Shuguang Cui, Zhen Li, Na Zhao

机构 * FNii-Shenzhen, CUHKSZ（FNii深圳，香港科技大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Fusion of multi-source precipitation records via coordinate-based generative model

Sencan Sun, Congyi Nai, Baoxiang Pan, Wentao Li, Lu Li, Xin Li, Efi Foufoula-Georgiou, Yanluan Lin

专题命中 安全评测 ：trustworthy(abstract)

Comments 49 pages, 21 figures

Development of a persuasive User Experience Research (UXR) Point of View for Explainable Artificial Intelligence (XAI)

Mohammad Naiseh, Huseyin Dogan, Stephen Giff, Nan Jiang

专题命中 安全评测 ：trustworthy(abstract)

Collaborative Perception Datasets for Autonomous Driving: A Review

Naibang Wang, Deyong Shang, Yan Gong, Xiaoxi Hu, Ziying Song, Lei Yang, Yuhan Huang, Xiaoyu Wang, Jianli Lu

机构 * School of Mechanical and Electrical Engineering, China University of Mining and Technology (Beijing)（中国矿业大学（北京）机械与电子工程学院） ； State Key Laboratory of Robotics and System, Harbin Institute of Technology（哈尔滨工业大学机器人系统国家重点实验室） ； State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与移动系统国家重点实验室） ； School of Mechanical and Aerospace Engineering, Nanyang Technological University（南洋理工大学机械与航空航天工程学院） ； School of Mechatronics Engineering, Harbin Institute of Technology（哈尔滨工业大学机械电子工程学院） ； Department of Electronic & Electrical Engineering, University of Bath（巴斯大学电子与电气工程系） 纠错

专题命中 安全评测 ：safety(abstract)

Comments 18pages, 7figures, journal

RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning

Alexander Vogel, Omar Moured, Yufan Chen, Jiaming Zhang, Rainer Stiefelhagen

机构 * CV:HCI lab, Karlsruhe Institute of Technology, Germany.（CV:HCI实验室，卡尔斯鲁厄理工学院，德国） ； CVG, ETH, Switzerland.（CVG，瑞士联邦理工学院） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted by ICDAR 2025. All models and code will be publicly available at https://github.com/moured/RefChartQA

SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models

Xinyi Zhao, Congjing Zhang, Pei Guo, Wei Li, Lin Chen, Chaoyue Zhao, Shuai Huang

机构 * University of Washington（华盛顿大学） ； Wyze Labs, Inc.（Wyze实验室） 纠错

专题命中 安全评测 ：safety(abstract)

Comments CVPR 2025 Workshop: VAND 3.0 - Visual Anomaly and Novelty Detection

RationalVLA: A Rational Vision-Language-Action Model with Dual System

Wenxuan Song, Jiayi Chen, Wenxue Li, Xu He, Han Zhao, Can Cui, Pengxiang Ding Shiyan Su, Feilong Tang, Xuelian Cheng, Donglin Wang, Zongyuan Ge, Xinhu Zheng, Zhe Liu, Hesheng Wang, Haoang Li

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Westlake University（西湖大学） ； Monash University（墨尔本大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 安全评测 ：safety(abstract)

Comments 14 pages

GenWorld: Towards Detecting AI-generated Real-world Simulation Videos

Weiliang Chen, Wenzhao Zheng, Yu Zheng, Lei Chen, Jie Zhou, Jiwen Lu, Yueqi Duan

机构 * Department of Automation, Tsinghua University, China（自动化系，清华大学） ； Department of Electronic Engineering, Tsinghua University, China（电子工程系，清华大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Efficient Edge Deployment of Quantized YOLOv4-Tiny for Aerial Emergency Object Detection on Raspberry Pi 5

Sindhu Boddu, Arindam Mukherjee

机构 * Department of Electrical 纠错

专题命中 安全评测 ：safety(abstract)

SACA: A Scenario-Aware Collision Avoidance Framework for Autonomous Vehicles Integrating LLMs-Driven Reasoning

Shiyue Zhao, Junzhi Zhang, Neda Masoud, Heye Huang, Xiaohui Hou, Chengkun He

专题命中 安全评测 ：safety(abstract)

Comments 11 pages,10 figures. This work has been submitted to the IEEE TVT for possible publication

Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoring

Mingjie Xu, Andrew Estornell, Hongzheng Yang, Yuzhi Zhao, Zhaowei Zhu, Qi Xuan, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； ByteDance Seed（字节跳动种子） ； The Chinese University of Hong Kong（香港中文大学） ； City University of Hong Kong（香港城市大学） ； BIAI-ZJUT ； Zhejiang University of Technology（浙江工业大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives

Xingxing Weng, Chao Pang, Gui-Song Xia

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted by IEEE Geoscience and Remote Sensing Magazine

Journal ref IEEE Geoscience and Remote Sensing Magazine, Early Access, 2025

DrowzEE-G-Mamba: Leveraging EEG and State Space Models for Driver Drowsiness Detection

Gourav Siddhad, Sayantan Dey, Partha Pratim Roy

专题命中 安全评测 ：safety(abstract)

Comments 8 Pages, 2 Figures, 1 Table

Journal ref International Conference on Pattern Recognition (ICPR) 2024

CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems

Aniket Rege, Zinnia Nie, Mahesh Ramesh, Unmesh Raskar, Zhuoran Yu, Aditya Kusupati, Yong Jae Lee, Ramya Korlakai Vinayak

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； University of Washington（华盛顿大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments 41 pages, 22 figures, 17 tables

Dreamland: Controllable World Creation with Simulator and Generative Models

Sicheng Mo, Ziyang Leng, Leon Liu, Weizhen Wang, Honglin He, Bolei Zhou

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Project Page: https://metadriverse.github.io/dreamland/

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

Haoyuan Li, Yanpeng Zhou, Yufei Gao, Tao Tang, Jianhua Han, Yujie Yuan, Dave Zhenyu Chen, Jiawang Bian, Hang Xu, Xiaodan Liang

机构 * Shenzhen campus of Sun Yat-sen University（中山大学深圳校区） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； MBZUAI ； Peng Cheng Laboratory（鹏城实验室） ； Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室） 纠错

专题命中 安全评测 ：alignment(abstract)

Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

Qing Jiang, Xingyu Chen, Zhaoyang Zeng, Junzhi Yu, Lei Zhang

机构 * International Digital Economy Academy (IDEA)（国际数字经济学院） ； South China University of Technology（华南理工大学） ； Peking University（北京大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Comments homepage: https://rexthinker.github.io/

PRJ: Perception-Retrieval-Judgement for Generated Images

Qiang Fu, Zonglei Jing, Zonghao Ying, Xiaoqian Li

专题命中 安全评测 ：safety(abstract)