大模型对齐与安全

Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning

Chengwei Qin, Wenhan Xia, Fangkai Jiao, Chen Chen, Yuchen Hu, Bosheng Ding, Ruirui Chen, Shafiq Joty

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Princeton University（普林斯顿大学） ； Nanyang Technological University（南洋理工大学） ； Salesforce Research（Salesforce 研究） ； Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore（高性能计算研究所，新加坡科技研究局） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Chen Huang, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Josh Susskind

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments ICML 2025

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment

Yongxin Huang, Kexin Wang, Goran Glavaš, Iryna Gurevych

机构 * Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science Technical University of Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany（技术大学达姆施塔特计算机科学系通用知识处理实验室（UKP实验室）和应用网络安全国家研究中心ATHENE德国） ； Center for AI and Data Science, University of Würzburg（人工智能与数据科学中心，乌尔姆大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments Accepted for ACL 2025 main conference

Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving

Shahin Atakishiyev, Mohammad Salameh, Randy Goebel

专题命中 其他安全 ：safety(title,abstract)；分类 cs.AI

Comments Accepted for publication in IEEE Transactions on Intelligent Transportation Systems

TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment

Zheng Li, Mao Zheng, Mingyang Song, Wenjie Yang

机构 * Tencent Hunyuan（腾讯文言） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Agent-Environment Alignment via Automated Interface Generation

Kaiming Liu, Xuanyu Lei, Ziyue Wang, Peng Li, Yang Liu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Future of Code with Generative AI: Transparency and Safety in the Era of AI Generated Software

David Hanson

专题命中 其他安全 ：safety(title,abstract)；分类 cs.AI

Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment

Liangwei Nathan Zheng, Chang George Dong, Wei Emma Zhang, Lin Yue, Miao Xu, Olaf Maennel, Weitong Chen

机构 * The University of Adelaide（阿德莱德大学） ； The University of Queensland（昆士兰大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

An Affective-Taxis Hypothesis for Alignment and Interpretability

Eli Sennesh, Maxwell Ramstead

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Ziqiao Wang, Wangbo Zhao, Yuhao Zhou, Zekai Li, Zhiyuan Liang, Mingjia Shi, Xuanlei Zhao, Pengfei Zhou, Kaipeng Zhang, Zhangyang Wang, Kai Wang, Yang You

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Comments 24 pages

The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect

Cosimo Iaia, Bhavin Choksi, Emily Wiebers, Gemma Roig, Christian J. Fiebach

机构 * Goethe University Frankfurt（弗赖堡歌德大学） ； Center for Brains, Minds and Machines, MIT Hessian.AI（大脑、心智与机器中心，MIT 荷尔斯泰因人工智能） ； Brain Imaging Center（脑成像中心） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments 13 pages, 4 Figures, 1 Table

ALN-P3: Unified Language Alignment for Perception, Prediction, and Planning in Autonomous Driving

Yunsheng Ma, Burhaneddin Yaman, Xin Ye, Mahmut Yurt, Jingru Luo, Abhirup Mallik, Ziran Wang, Liu Ren

机构 * Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI)（博世北美研究部及博世人工智能中心） ； Purdue University（普渡大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments 10 pages

Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image

Sifan Li, Ming Tao, Hao Zhao, Ling Shao, Hao Tang

机构 * Liaoning University（辽宁大学） ； Nanjing University of Posts and Telecommunications（南京邮电大学） ； Tsinghua University（清华大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Peking University（北京大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Improve Language Model and Brain Alignment via Associative Memory

Congchi Yin, Yongpeng Zhang, Xuyun Wen, Piji Li

机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学） ； The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education（脑机智能技术重点实验室，教育部） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments Accepted by Findings of ACL 2025

Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment

Siming Sun, Kai Zhang, Xuejun Jiang, Wenchao Meng, Qinmin Yang

机构 * Zhejiang University（浙江大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Model alignment using inter-modal bridges

Ali Gholamzadeh, Noor Sajid

机构 * MPI for Biological Cybernetics & University of Tübingen（生物感知研究所及图宾根大学） ； Kempner Institute, Harvard University（凯普纳研究所及哈佛大学） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment

Weicong Qin, Yi Xu, Weijie Yu, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； University of International Business and Economics（国际商务经济大学） ； AI Lab at Lenovo Research, Lenovo Group Limited（联想集团研究院人工智能实验室） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments accepted to ACL 2025 main conference

Consensus-Aware AV Behavior: Trade-offs Between Safety, Interaction, and Performance in Mixed Urban Traffic

Mohammad Elayan, Wissam Kontar

专题命中 其他安全 ：safety(title,abstract)；分类 cs.AI

Comments 7 pages, 8 figures

AI2-Active Safety: AI-enabled Interaction-aware Active Safety Analysis with Vehicle Dynamics

Keshu Wu, Zihao Li, Sixu Li, Xinyue Ye, Dominique Lord, Yang Zhou

机构 * AI2 纠错

专题命中 其他安全 ：safety(title,abstract)；分类 cs.AI

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Siyu Zhou, Tianyi Zhou, Yijun Yang, Guodong Long, Deheng Ye, Jing Jiang, Chengqi Zhang

机构 * Australian AI Institute, Faculty of Engineering and IT, University of Technology Sydney（澳大利亚人工智能研究所，工程与信息学院，悉尼大学） ； Department of Computer Science, University of Maryland, College Park（计算机科学系，马里兰大学，College Park） ； Tencent, China（腾讯，中国） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Comments Code is available at https://github.com/elated-sawyer/WALL-E

ResiDual Transformer Alignment with Spectral Decomposition

Lorenzo Basile, Valentino Maiorca, Luca Bortolussi, Emanuele Rodolà, Francesco Locatello

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments Published in Transactions on Machine Learning Research (TMLR)

BiPVL-Seg: Bidirectional Progressive Vision-Language Fusion with Global-Local Alignment for Medical Image Segmentation

Rafi Ibn Sultan, Hui Zhu, Chengyin Li, Dongxiao Zhu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Improved Alignment of Modalities in Large Vision Language Models

Kartik Jangra, Aman Kumar Singh, Yashwani Mann, Geetanjali Rathee

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment

Chao Wang, Giulio Franzese, Alessandro Finamore, Pietro Michiardi

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.LG

Comments to appear at ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation

Henglyu Liu, Andong Chen, Kehai Chen, Xuefeng Bai, Meizhi Zhong, Yuan Qiu, Min Zhang

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments 12 pages, 7 figures

Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection

Wentao Wu, Chenglong Li, Xiao Wang, Bin Luo, Qi Liu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Alignment for Efficient Tool Calling of Large Language Models

Hongshen Xu, Zihan Wang, Zichen Zhu, Lei Pan, Xingyu Chen, Lu Chen, Kai Yu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue

Sangyeop Kim, Sohhyung Park, Jaewon Jung, Jinseok Kim, Sungzoon Cho

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments Accepted by NAACL 2025

StarVid: Enhancing Semantic Alignment in Video Diffusion Models via Spatial and SynTactic Guided Attention Refocusing

Yuanhang Li, Qi Mao, Lan Chen, Zhen Fang, Lei Tian, Xinyan Xiao, Libiao Jin, Hua Wu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models

Hongchuan Zeng, Senyu Han, Lu Chen, Kai Yu

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.CL

Comments 16 pages, 11 figures, 4 tables