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 7945 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 7945 篇

2410.18686 2025-12-22 cs.LG 79%

Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification

具有语义空间对齐的层次多模态大语言模型用于增强的时间序列分类

Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学)

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

AI总结 HiTime通过层次多模态大语言模型和语义空间对齐,提升时间序列分类的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.16164 2025-12-19 cs.CV cs.AI 79%

C-DGPA: Class-Centric Dual-Alignment Generative Prompt Adaptation

面向类别的双对齐生成提示适应:C-DGPA

Chao Li, Dasha Hu, Chengyang Li, Yuming Jiang, Yuncheng Shen

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

AI总结 C-DGPA通过双分支架构协同优化边缘分布和条件分布对齐,提升无监督领域适应中提示学习的领域不变性和语义判别性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.12913 2025-12-19 cs.CL 79%

MAIN: Mutual Alignment Is Necessary for instruction tuning

MAIN:互斥对齐是指令微调的必要条件

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

机构 * Peking University(北京大学) Microsoft Corporation(微软公司)

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

AI总结 本文提出MAIN框架,通过互斥约束增强指令与响应的一致性,提升LLM在多种基准上的性能。

Comments Accepted by EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15464 2025-12-17 cs.CV cs.LG 79%

SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome

SIGMMA:基于层次图的多尺度多模态对比对齐:组织病理图像与空间转录组

Dabin Jeong, Amirhossein Vahidi, Ciro Ramírez-Suástegui, Marie Moullet, Kevin Ly, Mohammad Vali Sanian, Sebastian Birk, Yinshui Chang, Adam Boxall, Daniyal Jafree, Lloyd Steele, Vijaya Baskar MS, Muzlifah Haniffa, Mohammad Lotfollahi

机构 * Wellcome Sanger Institute(沃森桑格研究所) Cambridge Centre for AI in Medicine(剑桥人工智能医学中心) Institute of AI for Health(人工智能与健康研究所) Cambridge Stem Cell Institute(剑桥干细胞研究所)

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

AI总结 SIGMMA通过多尺度多模态对比对齐,提升组织病理图像与空间转录组的跨模态对应表示,提高基因表达预测和跨模态检索性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12896 2025-12-16 cs.LG 79%

Probability Estimation for Predicted-Occupancy Grids in Vehicle Safety Applications Based on Machine Learning

基于机器学习的车辆安全应用中预测占用网格的概率估计

Parthasarathy Nadarajan, Michael Botsch

机构 * Technische Hochschule Ingolstadt(图宾根工业大学)

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

AI总结 本文提出基于随机森林算法的机器学习方法,用于高效计算车辆安全应用中的预测占用网格,以提升关键性估计和轨迹规划能力。

Comments 2016 IEEE Intelligent Vehicles Symposium

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11251 2025-12-15 cs.LG 79%

Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

Insight Miner: 一个用于跨领域对齐的时间序列分析数据集与自然语言

Yunkai Zhang, Yawen Zhang, Ming Zheng, Kezhen Chen, Chongyang Gao, Ruian Ge, Siyuan Teng, Amine Jelloul, Jinmeng Rao, Xiaoyuan Guo, Chiang-Wei Fang, Zeyu Zheng, Jie Yang

机构 * UC Berkeley(加州大学伯克利分校) Mineral(矿石) Northwestern University(西北大学)

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

AI总结 Insight Miner 是一个大规模多模态模型,通过代理工作流生成高质量时间序列描述,提升跨领域时间序列分析能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03579 2025-12-04 cs.LG math.PR math.ST stat.TH 79%

Optimal Transportation and Alignment Between Gaussian Measures

高斯测度间的最优运输与对齐

Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan, Aaditya Ramdas, Ziv Goldfeld

机构 * Carnegie Mellon University, Department of Statistics(卡内基梅隆大学统计学系) Amazon Web Services (AWS) LogAnalytics(亚马逊网络服务(AWS)日志分析) Carnegie Mellon University, Machine Learning Department(卡内基梅隆大学机器学习系) Cornell University, Department of Electrical and Computer Engineering(康奈尔大学电子与计算机工程系)

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

AI总结 本文提出了一种针对高斯分布的最优运输与格罗莫夫-沃瑟斯坦对齐的闭式解,扩展到内积GW对齐,并应用于知识蒸馏和异构聚类。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10746 2025-12-04 cs.CL 79%

RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems

RECAP:医疗对话系统中透明的推理时间情感对齐

Adarsh Srinivasan, Jacob Dineen, Muhammad Umar Afzal, Muhammad Uzair Sarfraz, Irbaz B. Riaz, Ben Zhou

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

AI总结 RECAP通过结构化情感推理提升医疗对话系统的情感响应质量,实现透明和可审计的同理心沟通。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00641 2025-12-02 cs.CV cs.AI 79%

Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition

具有对抗域对齐的图注意力网络用于鲁棒跨域面部表情识别

Razieh Ghaedi, AmirReza BabaAhmadi, Reyer Zwiggelaar, Xinqi Fan, Nashid Alam

机构 * Manchester Metropolitan University(曼彻斯特 Metropolitan 大学) University of Tehran(泰姬大学) Aberystwyth University(阿伯里斯特维斯大学)

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

AI总结 GAT-ADA通过结合图注意力网络与对抗域对齐技术,提升跨域面部表情识别的鲁棒性,实现98.0%的准确率。

Comments 17 pages, 5 figures. Accepted at the 17th Asian Conference on Machine Learning (ACML 2025), Taipei, Taiwan, December 9-12, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20627 2025-11-26 cs.AI 79%

Fighting AI with AI: Leveraging Foundation Models for Assuring AI-Enabled Safety-Critical Systems

用AI对抗AI:利用基础模型确保AI赋能的安全关键系统

Anastasia Mavridou, Divya Gopinath, Corina S. Păsăreanu

机构 * KBR Inc.(KBR公司) NASA Ames(美国国家航空航天局阿姆斯研究中心)

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

AI总结 本文提出利用AI技术解决安全关键系统中AI保证问题,通过REACT和SemaLens两个组件实现需求工程与感知系统验证。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19155 2025-11-25 cs.AI 79%

EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction

EEG-VLM:一种具有多级特征对齐和视觉增强语言引导推理的分层视觉-语言模型,用于基于EEG图像的睡眠阶段预测

Xihe Qiu, Gengchen Ma, Haoyu Wang, Chen Zhan, Xiaoyu Tan, Shuo Li

机构 * School of Electronic and Electrical Engineering, Shanghai University of Engineering Science(上海工程技术大学电子与电气工程学院) Department of Control Science and Engineering, College of Electronics and Information Engineering, Tongji University(同济大学电子信息工程学院控制科学与工程系) Tencent Youtu Lab(腾讯云视觉实验室) Case Western Reserve University(凯斯西储大学)

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

AI总结 EEG-VLM通过多级特征对齐和视觉增强语言引导推理,提升基于EEG图像的睡眠阶段分类的准确性和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18824 2025-11-25 cs.CV cs.CL 79%

Assessing the alignment between infants' visual and linguistic experience using multimodal language models

利用多模态语言模型评估婴儿的视觉和语言经验一致性

Alvin Wei Ming Tan, Jane Yang, Tarun Sepuri, Khai Loong Aw, Robert Z. Sparks, Zi Yin, Virginia A. Marchman, Michael C. Frank, Bria Long

机构 * Department of Psychology, Stanford University(心理学系,斯坦福大学) Department of Psychology, University of California, San Diego(心理学系,加州大学圣地亚哥分校) Department of Psychology, Tsinghua University(心理学系,清华大学)

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

AI总结 基于多模态语言模型评估婴儿视觉与语言经验一致性,揭示日常学习中视觉与语言对齐的稀有性及跨儿童差异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.01558 2025-11-25 cs.CV cs.AI 79%

VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval

VideoLights: 用于联合视频亮点检测和时刻检索的特征细化与跨任务对齐变换器

Dhiman Paul, Md Rizwan Parvez, Nabeel Mohammed, Shafin Rahman

机构 * North South University(北南大学) Qatar Computing Research Institute (QCRI)(卡塔尔计算研究 institute)

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

AI总结 VideoLights通过引入特征细化、跨模态融合和联合任务反馈机制,提升视频亮点检测与时刻检索的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03186 2025-11-14 cs.LG 79%

Superposition disentanglement of neural representations reveals hidden alignment

André Longon, David Klindt, Meenakshi Khosla

机构 * UC San Diego(圣迭戈大学) Cold Spring Harbor Laboratory(冷泉港实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07419 2025-11-13 cs.LG 79%

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Zhongyang Li, Ziyue Li, Tianyi Zhou

机构 * Johns Hopkins University(约翰霍普金斯大学) University of Maryland, College Park(马里兰大学学院公园分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07155 2025-11-11 cs.RO cs.LG 79%

Dynamics-Decoupled Trajectory Alignment for Sim-to-Real Transfer in Reinforcement Learning for Autonomous Driving

Thomas Steinecker, Alexander Bienemann, Denis Trescher, Thorsten Luettel, Mirko Maehlisch

机构 * University of the Bundeswehr Munich(联邦国防军慕尼黑大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06653 2025-11-11 cs.CV cs.CL 79%

HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment

Ruijia Wu, Ping Chen, Fei Shen, Shaoan Zhao, Qiang Hui, Huanlin Gao, Ting Lu, Zhaoxiang Liu, Fang Zhao, Kai Wang, Shiguo Lian

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

Comments Accepted by AAAI 2026 as an Oral Presentation (13 pages, 7 figures, 7 tables)

Journal ref AAAI2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.02615 2025-11-10 cs.LG 79%

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen, Hoang-Bao Le, Tai Nguyen, Tien Nguyen, TrungTin Nguyen, Nhat Ho, Pengtao Xie, Roger Wattenhofer, James Zou, Daniel Sonntag, Mathias Niepert

机构 * German Research Centre for Artificial Intelligence (DFKI)(德国人工智能研究中心) Max Planck Research School for Intelligent Systems (IMPRS-IS)(马克斯·普朗克智能系统研究学校) University of Stuttgart(斯图加特大学) University Medical Center Gottingen(哥廷根大学医学中心) Max Planck Institute for Multidisciplinary Sciences(马克斯·普朗克多学科科学研究所) ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems(细胞系统数学分析卓越中心) School of Mathematical Sciences, Queensland University of Technology(昆士兰科技大学数学科学学院) University of Oldenburg(奥尔登堡大学) University of Texas at Austin(德克萨斯大学奥斯汀分校) University of California San Diego(加州大学圣地亚哥分校) MBZUAI(马克斯·普朗克人工智能研究所) ETH Zurich(苏黎世联邦理工学院) Stanford University(斯坦福大学)

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

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03280 2025-11-06 cs.LG stat.AP 79%

A Probabilistic Approach to Pose Synchronization for Multi-Reference Alignment with Applications to MIMO Wireless Communication Systems

Rob Romijnders, Gabriele Cesa, Christos Louizos, Kumar Pratik, Arash Behboodi

机构 * University of Amsterdam(阿姆斯特丹大学) QUvA-Lab(QUvA实验室) Qualcomm AI Research(高通人工智能研究)

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

Comments To appear in NeurIPS workshop: AI and ML for Next-Generation Wireless Communications (AI4NextG)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11857 2025-11-06 cs.CL 79%

Post Persona Alignment for Multi-Session Dialogue Generation

Yi-Pei Chen, Noriki Nishida, Hideki Nakayama, Yuji Matsumoto

机构 * RIKEN AIP(日本理化学研究所Advanced Institute for Physical Research) The University of Tokyo(东京大学)

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

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04104 2025-11-05 cs.CL cs.HC 79%

Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue

Keara Schaaij, Roel Boumans, Tibor Bosse, Iris Hendrickx

机构 * Centre for Language Studies, Centre for Language and Speech Technology, Radboud University,Nijmegen, The Netherlands(语言研究所以及语言与语音技术中心,拉德堡德大学,尼姆egen,荷兰) Behavioural Science Institute, Radboud University, Nijmegen, The Netherlands(行为科学研究所,拉德堡德大学,尼姆egen,荷兰)

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

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in TSD 2025. Lecture Notes in Computer Science, vol 16029

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09485 2025-11-05 cs.RO cs.AI cs.GR 79%

Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation

Yuxin Liu, Zhenghao Peng, Xuanhao Cui, Bolei Zhou

机构 * University of California, Los Angeles(加州大学洛杉矶分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19311 2025-10-30 cs.CV cs.AI 79%

DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignment

Weizhi Chen, Yupeng Deng, Jin Wei, Jingbo Chen, Jiansheng Chen, Yuman Feng, Zhihao Xi, Diyou Liu, Kai Li, Yu Meng

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院 aerospace information research institute) School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences(中国科学院大学电子电气与通信工程学院) School of Information Network Security, People’s Public Security University of China(中国人民公安大学信息网络安全学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.01342 2025-10-28 cs.LG stat.ML 79%

Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors

Zexi Li, Zhiqi Li, Jie Lin, Tao Shen, Jun Xiao, Yike Guo, Tao Lin, Chao Wu

机构 * Zhejiang University(浙江大学) Georgia Institute of Technology(佐治亚理工学院) Westlake University(西湖大学) Hong Kong University of Science and Technology(香港科技大学)

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

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15648 2025-10-28 cs.CR cs.LG cs.SE 79%

deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses

Georgios Androutsopoulos, Antonio Bianchi

机构 * Purdue University(普渡大学)

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

Comments At IEEE S&P 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21520 2025-10-27 cs.CL 79%

Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models

Omer Moussa, Mariya Toneva

机构 * Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所)

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

Comments Published at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17833 2025-10-22 q-bio.NC cs.AI 79%

Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

Ángela López-Cardona, Sebastián Idesis, Mireia Masias-Bruns, Sergi Abadal, Ioannis Arapakis

机构 * Universitat Politècnica de Catalunya(加泰罗尼亚理工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16540 2025-10-21 cs.CV cs.AI 79%

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Jihoon Kwon, Kyle Min, Jy-yong Sohn

机构 * Seoul National University(首尔国立大学) Oracle(Oracle公司) Yonsei University(延世大学) Intel Labs(英特尔实验室)

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

Comments Accepted at NeurIPS 2025 (poster). This is the camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.15004 2025-10-20 cs.SE cs.AI 79%

Automated Snippet-Alignment Data Augmentation for Code Translation

Zhiming Zhang, Qingfu Zhu, Xianzhen Luo, Yixuan Wang, Bohan Li, Wanxiang Che

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11401 2025-10-17 cs.CL 79%

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment

Jingcheng Deng, Zhongtao Jiang, Liang Pang, Liwei Chen, Kun Xu, Zihao Wei, Huawei Shen, Xueqi Cheng

机构 * Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院人工智能安全重点实验室,计算技术研究所) University of Chinese Academy of Sciences(中国科学院大学) Kuaishou Technology(快手科技)

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

详情

展开后加载摘要…

URL PDF HTML 收藏