arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

共收录 8057 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8057 篇

2506.02739 2025-06-04 cs.AI 57%

Why do AI agents communicate in human language?

Pengcheng Zhou, Yinglun Feng, Halimulati Julaiti, Zhongliang Yang

机构 * Beijing University Of Posts and Telecommunications(北京邮电大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02616 2025-06-04 cs.LG 57%

Compositional Learning for Modular Multi-Agent Self-Organizing Networks

Qi Liao, Parijat Bhattacharjee

机构 * Nokia Bell Labs(诺基亚贝尔实验室) Nokia(诺基亚)

专题命中 其他安全 :safety(abstract);分类 cs.LG

Journal ref IEEE ICMLCN 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02211 2025-06-04 cs.AI 57%

Improving LLM-Generated Code Quality with GRPO

Maxime Robeyns, Laurence Aitchison

机构 * University of Bristol(布里斯托大学)

专题命中 其他安全 :safety(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02150 2025-06-04 cs.CV cs.AI 57%

Implicit Deformable Medical Image Registration with Learnable Kernels

Stefano Fogarollo, Gregor Laimer, Reto Bale, Matthias Harders

机构 * Department of Computer Science Interactive Graphics and Simulation Group (IGS), University of Innsbruck, Technikerstraße 21 Innsbruck, Austria(因计算机科学系交互式图形与模拟组(IGS),因斯布鲁克大学) Interventional Oncology-Microinvasive Therapy (SIP), Department of Radiology, Medical University Innsbruck, Innsbruck, Austria(介入肿瘤学-微侵袭疗法(SIP),放射学系,因斯布鲁克医学院)

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

Comments MICCAI 2025 Provisional Accept

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21863 2025-06-04 cs.CV cs.CL 57%

GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning

Shikhhar Siingh, Abhinav Rawat, Chitta Baral, Vivek Gupta

机构 * School of Computing and Augmented Intelligence, Arizona State University(计算与增强智能学院,亚利桑那州立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.04328 2025-06-04 cs.CV cs.CL cs.MM cs.SD eess.AS eess.IV 57%

Ola: Pushing the Frontiers of Omni-Modal Language Model

Zuyan Liu, Yuhao Dong, Jiahui Wang, Ziwei Liu, Winston Hu, Jiwen Lu, Yongming Rao

机构 * Tsinghua University(清华大学) Tencent Hunyuan Research(腾讯文睿实验室) S-Lab, NTU(国立科技大学S实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2209.09139 2025-06-04 cs.CE cs.LG cs.NA math.NA 57%

Machine Learning based Extraction of Boundary Conditions from Doppler Echo Images for Patient Specific Coarctation of the Aorta: Computational Fluid Dynamics Study

Vincent Milimo Masilokwa Punabantu, Malebogo Ngoepe, Amit Kumar Mishra, Thomas Aldersley, John Lawrenson, Liesl Zuhlke

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments Article to be submitted to Springer Nature Cardiovascular Engineering and Technology Journal

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01849 2025-06-03 cs.LG cs.CR 57%

Trojan Horse Hunt in Time Series Forecasting for Space Operations

Krzysztof Kotowski, Ramez Shendy, Jakub Nalepa, Przemysław Biecek, Piotr Wilczyński, Agata Kaczmarek, Dawid Płudowski, Artur Janicki, Evridiki Ntagiou

机构 * KP Labs(KP实验室) Silesian University of Technology(桑特大学) Warsaw University of Technology(华沙技术大学) European Space Agency(欧洲航天局) European Space Operations Center(欧洲空间运营中心)

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01312 2025-06-03 cs.CL 57%

Growing Through Experience: Scaling Episodic Grounding in Language Models

Chunhui Zhang, Sirui, Wang, Zhongyu Ouyang, Xiangchi Yuan, Soroush Vosoughi

机构 * Department of Computer Science, Dartmouth College(达特茅斯学院计算机科学系) School of Computer Science, Georgia Institute of Technology(佐治亚理工学院计算机科学学院)

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

Comments Accepted at The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01253 2025-06-03 cs.CL 57%

CoRE: Condition-based Reasoning for Identifying Outcome Variance in Complex Events

Sai Vallurupalli, Francis Ferraro

机构 * Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County(计算机科学与电气工程系马里兰大学巴尔的摩县)

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

Comments Accepted to Findings of the Association for Computational Linguistics 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01111 2025-06-03 cs.SD cs.AI eess.AS 57%

FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion

Shunian Chen, Xinyuan Xie, Zheshu Chen, Liyan Zhao, Owen Lee, Zhan Su, Qilin Sun, Benyou Wang

机构 * The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01095 2025-06-03 cs.AI 57%

Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communication

Khe-Han Toh, Hong-Kuan Teo

机构 * AI Department(人工智能部门) GTM Department(GTM部门)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00875 2025-06-03 cs.CL 57%

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning

Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin

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

Comments ACL2025 main conference, long paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00788 2025-06-03 cs.SE cs.AI 57%

Behavioral Augmentation of UML Class Diagrams: An Empirical Study of Large Language Models for Method Generation

Djaber Rouabhia, Ismail Hadjadj

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00573 2025-06-03 cs.LG stat.ML 57%

Neural Estimation for Scaling Entropic Multimarginal Optimal Transport

Dor Tsur, Ziv Goldfeld, Kristjan Greenewald, Haim Permuter

机构 * Ben-Gurion University(本·古里安大学) Cornell University(康奈尔大学) MIT-IBM Watson AI Lab(麻省理工-IBM沃森人工智能实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.02460 2025-06-03 cs.CL 57%

Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications

Zhe Chen, Yusheng Liao, Shuyang Jiang, Pingjie Wang, Yiqiu Guo, Yanfeng Wang, Yu Wang

机构 * Shanghai Jiao Tong University(上海交通大学) Fudan University(复旦大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

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

Comments ACL 2025 Main Conference. Project website: https://github.com/Jack-ZC8/Omni-RAG-Medical

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.08534 2025-06-03 cs.CL 57%

Neural Topic Modeling with Large Language Models in the Loop

Xiaohao Yang, He Zhao, Weijie Xu, Yuanyuan Qi, Jueqing Lu, Dinh Phung, Lan Du

机构 * Faculty of IT, Monash University, Australia(莫纳什大学信息学院, 澳大利亚) CSIRO’s Data61, Australia(CSIRO数据61, 澳大利亚) Amazon, America(亚马逊, 美国)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00417 2025-06-03 cs.AI 57%

World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks

Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Gaosheng Zhao, Dusit Niyato, Geng Sun, Shiwen Mao, Dong In Kim

机构 * College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学) College of Computer Science and Technology, Jilin University(计算机科学与技术学院,吉林大学) Department of Electrical and Computer Engineering, Auburn University(电气与计算机工程系,阿伯茨罕大学) Department of Electrical and Computer Engineering, Sungkyunkwan University(电气与计算机工程系,成均馆大学)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments 7 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00152 2025-06-03 cs.LG econ.EM stat.ML 57%

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective

Erfan Loghmani

机构 * Foster School of Business University of Washington(华盛顿大学福斯特商学院)

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

Comments 10+12 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00049 2025-06-03 cs.IR cs.AI 57%

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

Arjun Rao, Hanieh Alipour, Nick Pendar

机构 * SAP(SAP公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03868 2025-06-03 cs.CL 57%

Can Language Models Reason about Individualistic Human Values and Preferences?

Liwei Jiang, Taylor Sorensen, Sydney Levine, Yejin Choi

机构 * University of Washington(华盛顿大学) Google DeepMind(谷歌DeepMind) Stanford University(斯坦福大学) Allen Institute for Artificial Intelligence(人工智能研究院)

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

Comments Camera Ready at ACL Main 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24355 2025-06-02 cs.CL 57%

Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model

Sihan Tan, Taro Miyazaki, Kazuhiro Nakadai

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15678 2025-06-02 cs.LG 57%

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata, Matthias Bethge, Joshua B. Tenenbaum, Eric Schulz

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24067 2025-06-02 cs.LG 57%

Primal-Dual Neural Algorithmic Reasoning

Yu He, Ellen Vitercik

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

Comments The 42nd International Conference on Machine Learning, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03328 2025-06-02 cs.RO cs.LG 57%

Foundation Models for Rapid Autonomy Validation

Alec Farid, Peter Schleede, Aaron Huang, Christoffer Heckman

机构 * Zoox Inc.(Zoox公司)

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23184 2025-05-30 cs.LG cs.SE 57%

Two Is Better Than One: Rotations Scale LoRAs

Hongcan Guo, Guoshun Nan, Yuan Yang, Diyang Zhang, Haotian Li, Zhican Chen, Qinchuan Zhou, Yuhan Ran, Xinye Cao, Sicong Leng, Xiaofeng Tao, Xudong Jiang

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Nanyang Technological University(南洋理工大学) University of Bristol(布里斯托大学)

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

Comments 27pages, 16figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23043 2025-05-30 cs.CV cs.AI 57%

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation

Jihai Zhang, Tianle Li, Linjie Li, Zhengyuan Yang, Yu Cheng

机构 * The Chinese University of Hong Kong(香港中文大学) Microsoft(微软公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16359 2025-05-30 cs.CV cs.AI cs.MM 57%

Audio Visual Segmentation Through Text Embeddings

Kyungbok Lee, You Zhang, Zhiyao Duan

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.00006 2025-05-30 cs.SE cs.AI 57%

Personality-Guided Code Generation Using Large Language Models

Yaoqi Guo, Zhenpeng Chen, Jie M. Zhang, Yang Liu, Yun Ma

机构 * Peking University(北京大学) Nanyang Technological University(南洋理工大学) King’s College London(伦敦大学国王学院)

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

Comments Accepted by the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) Main Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22638 2025-05-29 cs.CR cs.LG 57%

SimProcess: High Fidelity Simulation of Noisy ICS Physical Processes

Denis Donadel, Gabriele Crestanello, Giulio Morandini, Daniele Antonioli, Mauro Conti, Massimo Merro

机构 * University of Verona(威尼斯大学) University of Padua(帕多瓦大学) EURECOM

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments In 11th ACM Cyber-Physical System Security Workshop (CPSS '25), August 25-29, 2025, Hanoi, Vietnam

详情

展开后加载摘要…

URL PDF HTML 收藏