arXivDaily arXiv每日学术速递 周一至周五更新

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 7978 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 7978 篇

2508.00574 2025-08-04 cs.CL cs.AI 62%

SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought

Jianwei Wang, Ziming Wu, Fuming Lai, Shaobing Lian, Ziqian Zeng

机构 * Tencent Inc.(腾讯公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19651 2025-08-04 cs.LG cs.CL 62%

Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs

Yuanyuan Xu, Wenjie Zhang, Ying Zhang, Xuemin Lin, Xiwei Xu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22920 2025-08-01 cs.CL cs.AI 62%

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

Jindong Li, Yali Fu, Jiahong Liu, Linxiao Cao, Wei Ji, Menglin Yang, Irwin King, Ming-Hsuan Yang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22902 2025-08-01 cs.HC cs.AI cs.CL cs.MA 62%

Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting

Hashim Hayat, Maksim Kudrautsau, Evgeniy Makarov, Vlad Melnichenko, Tim Tsykunou, Piotr Varaksin, Matt Pavelle, Adam Z. Oskowitz

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22633 2025-08-01 cs.LG cs.AI 62%

H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity

Wei Guo, Siyuan Lu, Yiqi Tong, Zhaojun Hu, Fuzhen Zhuang, Xiao Zhang, Tao Fan, Jin Dong

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 Technology, Heilongjiang University(黑龙江大学计算机科学与技术学院) School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院) School of Statistics, Renmin University of China(中国人民大学统计学院) Zhongguancun Laboratory, China(中关村实验室) School of Computer Science and Technology, Shandong University(山东大学计算机科学与技术学院) WeBank Co., Ltd, Shenzhen, China(WeBank有限公司,深圳,中国) Beijing Academy of Blockchain and Edge Computing(北京区块链与边缘计算研究院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22529 2025-07-31 cs.LG cs.AI 62%

Accident-Driven Congestion Prediction and Simulation: An Explainable Framework Using Advanced Clustering and Bayesian Networks

Kranthi Kumar Talluri, Galia Weidl, Vaishnavi Kasuluru

机构 * Aschaffenburg University of Applied Sciences(阿施法亨堡应用科学大学) Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)(加泰罗尼亚电信技术中心(CTTC))

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21107 2025-07-30 cs.CL cs.AI 62%

Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams

Rob Manson

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

Comments 29 pages, 22 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.20191 2025-07-29 cs.LG cs.AI 62%

Partial Domain Adaptation via Importance Sampling-based Shift Correction

Cheng-Jun Guo, Chuan-Xian Ren, You-Wei Luo, Xiao-Lin Xu, Hong Yan

机构 * School of Mathematics, Sun Yat-Sen University(中山大学数学学院) School of Statistics and Mathematics, Guangdong University of Finance and Economics(广东财经大学统计与数学学院) Department of Electrical Engineering, City University of Hong Kong(香港城市大学电子工程系)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.13887 2025-07-29 cs.HC cs.CL cs.CY 62%

AI as a deliberative partner fosters intercultural empathy for Americans but fails for Latin American participants

Isabel Villanueva, Tara Bobinac, Binwei Yao, Junjie Hu, Kaiping Chen

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19526 2025-07-29 cs.LG cs.AI 62%

Quantizing Text-attributed Graphs for Semantic-Structural Integration

Jianyuan Bo, Hao Wu, Yuan Fang

机构 * Singapore Management University(新加坡国立管理大学) Beijing Normal University(北京师范大学)

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

Comments Accepted at KDD'2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.07003 2025-07-28 cs.AI cs.LG cs.RO 62%

RACER: Rational Artificial Intelligence Car-following-model Enhanced by Reality

Tianyi Li, Alexander Halatsis, Raphael Stern

机构 * Department of Civil Engineering(土木工程系) Department of Aerospace Engineering(航空航天工程系) Department of Civil, Environmental, and Geo-Engineering(土木、环境与地球工程系)

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

Journal ref "RACER: Rational Artificial Intelligence Car-Following-Model Enhanced by Reality," in IEEE Transactions on Intelligent Transportation Systems,

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22116 2025-07-23 cs.CL cs.AI 62%

Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model

Jintao Zhang, Zirui Liu, Mingyue Cheng, Shilong Zhang, Tingyue Pan, Yitong zhou, Qi Liu, Yanhu Xie

机构 * University of Science and Technology of China(中国科学技术大学) The First Affiliated Hospital of University of Science and Technology of China(中国科学技术大学第一附属医院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08622 2025-07-22 cs.AI cs.CL cs.CV 62%

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models

Donghoon Kim, Minji Bae, Kyuhong Shim, Byonghyo Shim

机构 * Seoul National University(首尔国立大学) Sungkyunkwan University(庆熙大学)

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

Comments ICLR 2025 (Official Code: https://github.com/DonghoonKim-1938/VGD)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10015 2025-07-18 cs.CV cs.AI cs.LG 62%

(Almost) Free Modality Stitching of Foundation Models

Jaisidh Singh, Diganta Misra, Boris Knyazev, Antonio Orvieto

机构 * University of Tübingen(图宾根大学) Zuse School ELIZA(Zuse学校ELIZA) ELLIS Institute Tübingen(图宾根ELLIS研究所) MPI-IS Tübingen(图宾根MPI-IS研究所) SAIT AI Lab Montréal(蒙特利尔SAIT人工智能实验室) Tübingen AI Center(图宾根人工智能中心)

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

Comments Pre-print

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10157 2025-07-16 cs.CL cs.CY 62%

SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users

Xinnong Zhang, Jiayu Lin, Xinyi Mou, Shiyue Yang, Xiawei Liu, Libo Sun, Hanjia Lyu, Yihang Yang, Weihong Qi, Yue Chen, Guanying Li, Ling Yan, Yao Hu, Siming Chen, Yu Wang, Xuanjing Huang, Jiebo Luo, Shiping Tang, Libo Wu, Baohua Zhou, Zhongyu Wei

机构 * Shanghai Innovation Insititute(上海创新研究院) Fudan University(复旦大学) University of Rochester(罗切斯特大学) Indiana University(印第安纳大学) Xiaohongshu Inc.(小红书公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10620 2025-07-16 cs.LG cs.AI 62%

LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions

Chenxi Liu, Hao Miao, Cheng Long, Yan Zhao, Ziyue Li, Panos Kalnis

机构 * Nanyang Technological University(南洋理工大学) The Hong Kong Polytechnic University(香港理工大学) University of Electronic Science and Technology of China(电子科学与技术大学) Technical University of Munich(慕尼黑技术大学) King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹大学)

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

Comments Accepted at SSTD 2025 (Tutorial). arXiv admin note: text overlap with arXiv:2505.02583

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10349 2025-07-15 cs.LG cs.AI 62%

TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting

Zhiyuan Zhao, Sitan Yang, Kin G. Olivares, Boris N. Oreshkin, Stan Vitebsky, Michael W. Mahoney, B. Aditya Prakash, Dmitry Efimov

机构 * Georgia Institute of Technology(佐治亚理工学院) Amazon(亚马逊公司)

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

Comments 9 pages, 4 figures, 7 tables, published at KDD 2025 workshop on AI for Supply Chain: Today and Future

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08829 2025-07-15 cs.LG cs.AI 62%

Efficient Triple Modular Redundancy for Reliability Enhancement of DNNs Using Explainable AI

Kimia Soroush, Nastaran Shirazi, Mohsen Raji

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07868 2025-07-11 cs.CL cs.AI 62%

Alpay Algebra V: Multi-Layered Semantic Games and Transfinite Fixed-Point Simulation

Bugra Kilictas, Faruk Alpay

机构 * Bahçeşehir University(巴切希尔大学)

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

Comments 18 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.05030 2025-07-08 cs.CY cs.AI cs.HC 62%

Perspectives on How Sociology Can Advance Theorizing about Human-Chatbot Interaction and Developing Chatbots for Social Good

Celeste Campos-Castillo, Xuan Kang, Linnea I. Laestadius

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03774 2025-07-08 cs.CL cs.AI 62%

Alpay Algebra IV: Symbiotic Semantics and the Fixed-Point Convergence of Observer Embeddings

Bugra Kilictas, Faruk Alpay

机构 * Bahcesehir University(巴切塞希尔大学)

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

Comments 19 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.04954 2025-07-08 cs.CV cs.CL cs.LG 62%

Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation

Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho

机构 * School of Computing Science, University of Glasgow(计算科学学院,格拉斯哥大学)

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

Comments Accepted by BioNLP@ACL 2024

Journal ref Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, ACL 2024, pp. 624-634

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01059 2025-07-03 cs.MA cs.AI cs.CL cs.CV cs.RO 62%

Automated Vehicles Should be Connected with Natural Language

Xiangbo Gao, Keshu Wu, Hao Zhang, Kexin Tian, Yang Zhou, Zhengzhong Tu

机构 * Texas A&M University(德克萨斯农工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01054 2025-07-03 cs.LG cond-mat.mtrl-sci cs.AI 62%

XxaCT-NN: Structure Agnostic Multimodal Learning for Materials Science

Jithendaraa Subramanian, Linda Hung, Daniel Schweigert, Santosh Suram, Weike Ye

机构 * Toyota Research Institute(丰田研究机构)

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

Comments 10 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08641 2025-07-03 cs.LG cs.AI cs.CV 62%

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers

Simon Roschmann, Quentin Bouniot, Vasilii Feofanov, Ievgen Redko, Zeynep Akata

机构 * Helmholtz Munich(海德堡-慕尼黑研究所) Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) MDSI(慕尼黑数据科学研究所) Paris Noah’s Ark Lab(巴黎诺亚实验室)

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

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00191 2025-07-02 cs.LG cs.AI 62%

Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions

Eray Erturk, Fahad Kamran, Salar Abbaspourazad, Sean Jewell, Harsh Sharma, Yujie Li, Sinead Williamson, Nicholas J Foti, Joseph Futoma

机构 * USC(美国大学) Apple Inc(苹果公司)

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

Comments Accepted to ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00024 2025-07-02 cs.LG cond-mat.mtrl-sci cs.AI 62%

AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcity

Yeyong Yu, Xilei Bian, Jie Xiong, Xing Wu, Quan Qian

机构 * School of Computer Engineering & Science(计算机工程与科学学院) Shanghai University(上海大学) Center of Materials Informatics and Data Science, Materials Genome Institute(材料信息与数据科学中心、材料基因组研究所) Key Laboratory of Silicate Cultural Relics Conservation (Shanghai University)(硅酸盐文化 relics 保护重点实验室(上海大学)) Ministry of Education(教育部) Shanghai Institute for Advanced Communication and Data Science(上海高级通信与数据科学研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23423 2025-07-01 cs.CL cs.AI 62%

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs

Felipe Nuti, Tim Franzmeyer, João Henriques

机构 * University of Oxford(牛津大学)

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

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23055 2025-07-01 cs.LG cs.AI 62%

Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis

Hiro Taiyo Hamada, Ippei Fujisawa, Genji Kawakita, Yuki Yamada

机构 * R&D Department Araya inc.(阿莱亚公司研发部) Department of Computational Neuroscience(计算神经科学系) Kyusyu University(九州大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22520 2025-07-01 cs.HC cs.AI cs.CE cs.CY 62%

Exploring Artificial Intelligence Tutor Teammate Adaptability to Harness Discovery Curiosity and Promote Learning in the Context of Interactive Molecular Dynamics

Mustafa Demir, Jacob Miratsky, Jonathan Nguyen, Chun Kit Chan, Punya Mishra, Abhishek Singharoy

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

详情

展开后加载摘要…

URL PDF HTML 收藏