大模型对齐与安全

CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation

Nicolas Bougie, Narimasa Watanabe

机构 * Woven by Toyota（丰田织造） 纠错

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

From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining

Fuying Wang, Jiacheng Xu, Lequan Yu

机构 * School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China（计算与数据科学学院，香港大学，香港特别行政区，中国） 纠错

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

Comments ICML 2025

TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization

Chuanrui Hu, Wei Hu, Penghang Yu, Hua Zhang, Bing-Kun Bao

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

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs

Fengze Li, Yue Wang, Yangle Liu, Ming Huang, Dou Hong, Jieming Ma

机构 * Xi'an Jiaotong-Liverpool University（西安交通大学利物浦大学） ； University of Liverpool（利物浦大学） 纠错

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

Graph Linearization Methods for Reasoning on Graphs with Large Language Models

Christos Xypolopoulos, Guokan Shang, Xiao Fei, Giannis Nikolentzos, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Giorgos Stamou, Michalis Vazirgiannis

机构 * Ecole Polytechnique（巴黎高等理工学院） ； MBZUAI（马克斯·普朗克人工智能研究所） ； NTUA（希腊国家技术研究中心） ； University of Peloponnese（希腊皮洛斯大学） 纠错

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

ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model

Zhenke Duan, Jiqun Pan, Jiani Tu, Xiaoyi Wang, Yanqing Wang

机构 * School of Statistics and Mathematics, Zhongnan University of Economics and Law（统计与数学学院，中国政法大学） 纠错

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

Automatic Posology Structuration : What role for LLMs?

Natalia Bobkova, Laura Zanella-Calzada, Anyes Tafoughalt, Raphaël Teboul, François Plesse, Félix Gaschi

机构 * SAS Posos ； Sorbonne Université（索邦大学） 纠错

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

End-to-End Spoken Grammatical Error Correction

Mengjie Qian, Rao Ma, Stefano Bannò, Mark J. F. Gales, Kate M. Knill

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

Comments This work has been submitted to the IEEE for possible publication

Towards Robust Stability Prediction in Smart Grids: GAN-based Approach under Data Constraints and Adversarial Challenges

Emad Efatinasab, Alessandro Brighente, Denis Donadel, Mauro Conti, Mirco Rampazzo

机构 * University of Padova, Department of Information Engineering（帕多瓦大学信息工程系） ； University of Padova, Department of Mathematics（帕多瓦大学数学系） 纠错

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

Journal ref Internet of Things, Volume 33, 2025, ISSN 2542-6605

Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, Yang Feng

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院智能信息处理重点实验室） ； Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学） 纠错

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

Comments Code: https://github.com/ictnlp/Stream-Omni , Model: https://huggingface.co/ICTNLP/stream-omni-8b

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Yuanhe Zhang, Fanghui Liu, Yudong Chen

机构 * Department of Statistics, University of Warwick, UK.（威斯敏斯特大学统计学系） ； Department of Computer Science, University of Warwick, UK.（威斯敏斯特大学计算机科学系） ； Centre for Discrete Mathematics and its Applications (DIMAP), University of Warwick, UK.（威斯敏斯特大学离散数学及其应用中心（DIMAP）） 纠错

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

Comments Accepted by ICML 2025 (Oral)

Recent Trends in Artificial Intelligence Technology: A Scoping Review

Teemu Niskanen, Tuomo Sipola, Olli Väänänen

机构 * Institute of Information Technology（信息技术学院） 纠错

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

Cash or Comfort? How LLMs Value Your Inconvenience

Mateusz Cedro, Timour Ichmoukhamedov, Sofie Goethals, Yifan He, James Hinns, David Martens

机构 * University of Antwerp（安特卫普大学） 纠错

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

Comments 12 pages, 4 figures, 3 tables

CF-VLM:CounterFactual Vision-Language Fine-tuning

Jusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang, Keze Wang

机构 * Sun Yat-sen University（中山大学） ； Snap Inc.（Snap公司） 纠错

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

Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning

Giuseppe Attanasio, Sonal Sannigrahi, Ben Peters, André F. T. Martins

机构 * Instituto de Telecomunicações（电信研究所） ； Instituto Superior Técnico（技术高等学院） ； Unbabel 纠错

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

Comments 7 pages, 1 figure, IWSLT 2025

LLMs in Coding and their Impact on the Commercial Software Engineering Landscape

Vladislav Belozerov, Peter J Barclay, Askhan Sami

机构 * School of Engineering, Computing, \& the Built Environment Edinburgh Napier University, Scotland WWW home page: https://www.napier.ac.uk 纠错

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

Convergent Linear Representations of Emergent Misalignment

Anna Soligo, Edward Turner, Senthooran Rajamanoharan, Neel Nanda

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

UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation

Wangzhi Zhan, Jianpeng Chen, Dongqi Fu, Dawei Zhou

机构 * Department of Computer Science, Virginia Polytechnic Institute and State University, Virginia, US（计算机科学系，弗吉尼亚理工大学和州立大学，弗吉尼亚，美国） ； Meta AI 纠错

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

RAST: Reasoning Activation in LLMs via Small-model Transfer

Siru Ouyang, Xinyu Zhu, Zilin Xiao, Minhao Jiang, Yu Meng, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Virginia（弗吉尼亚大学） ； Rice University（里德大学） ； GE HealthCare（通用电气医疗） 纠错

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

Co-Creative Learning via Metropolis-Hastings Interaction between Humans and AI

Ryota Okumura, Tadahiro Taniguchi, Akira Taniguchi, Yoshinobu Hagiwara

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

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey

Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Yueqian Lin, Qing Yu, Go Irie, Shafiq Joty, Yixuan Li, Hai Li, Ziwei Liu, Toshihiko Yamasaki, Kiyoharu Aizawa

机构 * The University of Tokyo（东京大学） ； S-Lab, Nanyang Technological University（南洋理工大学S实验室） ； Duke University（杜克大学） ； Salesforce AI Research（Salesforce人工智能研究） ； Nanyang Technological University（南洋理工大学） ； University of Wisconsin–Madison（威斯康星大学麦迪逊分校） ； Tokyo University of Science（东京科学大学） 纠错

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

Comments Accepted at TMLR2025. Survey paper. We welcome questions, issues, and paper requests via https://github.com/AtsuMiyai/Awesome-OOD-VLM

Object-Centric Neuro-Argumentative Learning

Abdul Rahman Jacob, Avinash Kori, Emanuele De Angelis, Ben Glocker, Maurizio Proietti, Francesca Toni

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

Comments Proceedings of Machine Learning Research, 2025 19th Conference on Neurosymbolic Learning and Reasoning

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study

Sompote Youwai, David Phim, Vianne Gayl Murcia, Rianne Clair Onas

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

Intelligent Automation for FDI Facilitation: Optimizing Tariff Exemption Processes with OCR And Large Language Models

Muhammad Sukri Bin Ramli

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

CRITS: Convolutional Rectifier for Interpretable Time Series Classification

Alejandro Kuratomi, Zed Lee, Guilherme Dinis Chaliane Junior, Tony Lindgren, Diego García Pérez

机构 * Department of Computer and Systems Sciences, Stockholm University（斯德哥尔摩大学计算机与系统科学系） ； Department of Computer Science and Engineering, University of Oviedo（奥维多大学计算机科学与工程系） 纠错

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

Comments This paper was presented at the 2024 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), as part of the XKDD workshop on interpretability. However it was not published in the LNCSI proceedings of the conference

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration

Hanzhi Zhang, Heng Fan, Kewei Sha, Yan Huang, Yunhe Feng

机构 * LLaVi Lab, Department of Computer Science & Engineering（LLaVi实验室，计算机科学与工程系） ； Department of Data Science（数据科学系） 纠错

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

Build the web for agents, not agents for the web

Xing Han Lù, Gaurav Kamath, Marius Mosbach, Siva Reddy

机构 * McGill University（麦吉尔大学） ； Mila – Quebec AI Institute（蒙特利尔人工智能研究所） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.LG

Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework

Sadia Kamal, Tim Oates, Joy Wan

机构 * Department of Computer Science, University of Maryland, Baltimore County（计算机科学系，马里兰大学巴尔的摩县分校） ； Department of Dermatology, Johns Hopkins University School of Medicine（皮肤科系，约翰霍普金斯大学医学院） 纠错

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

Comments Accepted at IEEE/CVF Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

AAD-LLM: Neural Attention-Driven Auditory Scene Understanding

Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari, Stephan Bickel, Ashesh Mehta, Guy M McKhann, Daniel Friedman, Adeen Flinker, Nima Mesgarani

机构 * Department of Electrical Engineering（电气工程系） ； Department of Neurological Surgery（神经外科系） ； Mortimer B. Zuckerman Mind Brain Behavior Institute（莫提默·B·祖克曼心智-脑-行为研究所） ； Hofstra Northwell School of Medicine（霍夫曼斯特拉北well医学院） ； The Feinstein Institutes for Medical Research（费森特医学研究所） ； Neurology Department（神经病学系） 纠错

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

Comments Accepted by ACL 2025 Main Conference

Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL

Mishca de Costa, Muhammad Anwar, Dave Mercier, Mark Randall, Issam Hammad

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.LG

Comments 44th Annual CNS Conference and the 49th Annual CNS/CNA Student Conference, Westin Harbour Castle Hotel, Toronto, ON, Canada, June 8-11, 2025