大模型对齐与安全

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)

Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

Weinan He, Zilei Wang, Yixin Zhang

专题命中 安全评测 ：alignment(abstract)

Comments Camera-ready version for AAAI 2025

Large-scale Self-supervised Video Foundation Model for Intelligent Surgery

Shu Yang, Fengtao Zhou, Leon Mayer, Fuxiang Huang, Yiliang Chen, Yihui Wang, Sunan He, Yuxiang Nie, Xi Wang, Ömer Sümer, Yueming Jin, Huihui Sun, Shuchang Xu, Alex Qinyang Liu, Zheng Li, Jing Qin, Jeremy YuenChun Teoh, Lena Maier-Hein, Hao Chen

专题命中 安全评测 ：safety(abstract)

Towards Computation- and Communication-efficient Computational Pathology

Chu Han, Bingchao Zhao, Jiatai Lin, Shanshan Lyu, Longfei Wang, Tianpeng Deng, Cheng Lu, Changhong Liang, Hannah Y. Wen, Xiaojing Guo, Zhenwei Shi, Zaiyi Liu

机构 * Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application（广东省人工智能在医学影像分析与应用重点实验室） ； Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences)（广东省人民医院（广东省医学科学院）） ； Southern Medical University（南方医科大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation

Jiaxi Sheng, Leyi Yu, Haoyue Li, Yifan Gao, Xin Gao

专题命中 安全评测 ：trustworthy(abstract)

Comments under review

STORM: Benchmarking Visual Rating of MLLMs with a Comprehensive Ordinal Regression Dataset

Jinhong Wang, Shuo Tong, Jian liu, Dongqi Tang, Jintai Chen, Haochao Ying, Hongxia Xu, Danny Chen, Jian Wu

机构 * Zhejiang University（浙江大学） ； Ant Group（蚂蚁集团） ； HKUST (Guangzhou)（香港科技大学（广州）） ； University of Notre Dame（Notre Dame 大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Comments underreview of NIPS2025 D&B track

Towards Scalable Video Anomaly Retrieval: A Synthetic Video-Text Benchmark

Shuyu Yang, Yilun Wang, Yaxiong Wang, Li Zhu, Zhedong Zheng

机构 * Xi’an Jiaotong University（西安交通大学） ； Hefei University of Technology（合肥工业大学） ； University of Macau（澳门大学） 纠错

专题命中 安全评测 ：safety(abstract)

PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning

Ke Niu, Yuwen Chen, Haiyang Yu, Zhuofan Chen, Xianghui Que, Bin Li, Xiangyang Xue

机构 * Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理关键实验室） ； School of Computer Science, Fudan University（复旦大学计算机科学学院） 纠错

专题命中 安全评测 ：alignment(abstract)

LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

Hongyu Li, Jinyu Chen, Ziyu Wei, Shaofei Huang, Tianrui Hui, Jialin Gao, Xiaoming Wei, Si Liu

机构 * School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院） ； School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院） ； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； Meituan（美团） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted by CVPR2025

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

Yinqi Li, Jiahe Zhao, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, Kaishun Wu

机构 * The Hong Kong University of Science & Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science & Technology（香港科技大学） ； Zhejiang University（浙江大学） ； Lappeenranta-Lahti University of Technology（拉佩兰塔-拉赫蒂技术大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted by CVPR 2025

Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression

Yiwei Xie, Ping Liu, Zheng Zhang

机构 * Huazhong University of Science and Technology, China（华中科技大学） ； University of Nevada, Reno（内华达大学拉斯维加斯分校） 纠错

专题命中 安全评测 ：safety(abstract)

A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models

Shiho Noda, Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

专题命中 安全评测 ：safety(abstract)

Comments Accepted at ICIP2025 Dataset and Benchmark Track

Benchmarking YOLOv8 for Optimal Crack Detection in Civil Infrastructure

Woubishet Zewdu Taffese, Ritesh Sharma, Mohammad Hossein Afsharmovahed, Gunasekaran Manogaran, Genda Chen

专题命中 安全评测 ：safety(abstract)

Comments We would like to extend/modify this work and make changes for resubmission to a different place. Hence we would like to withdraw the paper

IKIWISI: An Interactive Visual Pattern Generator for Evaluating the Reliability of Vision-Language Models Without Ground Truth

Md Touhidul Islam, Imran Kabir, Md Alimoor Reza, Syed Masum Billah

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Drake University（德拉威大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted at DIS'25 (Funchal, Portugal)

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

Hang Hua, Ziyun Zeng, Yizhi Song, Yunlong Tang, Liu He, Daniel Aliaga, Wei Xiong, Jiebo Luo

机构 * University of Rochester（罗切斯特大学） ； Purdue University（普渡大学） ； NVIDIA（英伟达） 纠错

专题命中 安全评测 ：alignment(abstract)

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

Yifan Li, Yuhang Chen, Anh Dao, Lichi Li, Zhongyi Cai, Zhen Tan, Tianlong Chen, Yu Kong

专题命中 安全评测 ：safety(abstract)

Comments v1.0

TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs

Juntong Wang, Jiarui Wang, Huiyu Duan, Guangtao Zhai, Xiongkuo Min

机构 * Institute of Image Communication and Network Engineering（图像通信与网络工程研究所） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments 25 pages, 14 figures, 8 tables

On the Dual-Use Dilemma in Physical Reasoning and Force

William Xie, Enora Rice, Nikolaus Correll

机构 * University of Colorado Boulder（科罗拉多大学博尔德分校） 纠错

专题命中 安全评测 ：alignment(abstract)

Describe Anything in Medical Images

Xi Xiao, Yunbei Zhang, Thanh-Huy Nguyen, Ba-Thinh Lam, Janet Wang, Lin Zhao, Jihun Hamm, Tianyang Wang, Xingjian Li, Xiao Wang, Hao Xu, Tianming Liu, Min Xu

专题命中 安全评测 ：alignment(abstract)

Illuminating the Path: Attention-Assisted Beamforming and Predictive Insights in 5G NR Systems

Dino Pjanić, Guoda Tian, Andres Reial, Xuesong Cai, Bo Bernhardsson, Fredrik Tufvesson

专题命中 安全评测 ：alignment(abstract)

Comments In this paper, we employ an attention-driven ML/AI model to address both short- and long-term beam prediction tasks in a commercial 5G NR uplink scenario. Our key contributions include demonstrating accurate beam predictions that extend beyond the coherence time, thereby overcoming the limitations of traditional techniques bounded by coherence-time constraints

Re-evaluation of Logical Specification in Behavioural Verification

Radoslaw Klimek, Jakub Semczyszyn

专题命中 安全评测 ：safety(abstract)

Comments The paper has been peer-reviewed and accepted for publication to the 29th International Conference on Evaluation and Assessment in Software Engineering (EASE 2025)

When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction

Yiping Ma, Shiyu Hu, Xuchen Li, Yipei Wang, Yuqing Chen, Shiqing Liu, Kang Hao Cheong

专题命中 安全评测 ：alignment(abstract)

Pathobiological Dictionary Defining Pathomics and Texture Features: Addressing Understandable AI Issues in Personalized Liver Cancer; Dictionary Version LCP1.0

Mohammad R. Salmanpour, Seyed Mohammad Piri, Somayeh Sadat Mehrnia, Ahmad Shariftabrizi, Masume Allahmoradi, Venkata SK. Manem, Arman Rahmim, Ilker Hacihaliloglu

专题命中 安全评测 ：trustworthy(abstract)

Comments 29 pages, 4 figures and 1 table

FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning

Shiyu Hu, Xuchen Li, Xuzhao Li, Jing Zhang, Yipei Wang, Xin Zhao, Kang Hao Cheong

专题命中 安全评测 ：alignment(abstract)

LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation

Jiarui Wang, Huiyu Duan, Ziheng Jia, Yu Zhao, Woo Yi Yang, Zicheng Zhang, Zijian Chen, Juntong Wang, Yuke Xing, Guangtao Zhai, Xiongkuo Min

机构 * Institute of Image Communication and Network Engineering（图像通信与网络工程研究所） ； MoE Key Lab of Artificial Intelligence（人工智能MoE重点实验室） ； AI Institute（人工智能研究院） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 安全评测 ：alignment(abstract)

EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

Hu Yue, Siyuan Huang, Yue Liao, Shengcong Chen, Pengfei Zhou, Liliang Chen, Maoqing Yao, Guanghui Ren

专题命中 安全评测 ：alignment(abstract)

Comments Website: https://github.com/AgibotTech/EWMBench