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 8057 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8057 篇

2410.23298 2025-03-27 cs.RO cs.LG 57%

Trajectory Prediction for Autonomous Driving using Agent-Interaction Graph Embedding

Jilan Samiuddin, Benoit Boulet, Di Wu

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments This article has been presented in the 27th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2024), Edmonton, Alberta, Canada on 26th September, 2024. Number of pages: 7, Number of figures: 8

Journal ref 27th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.10234 2025-03-27 cond-mat.stat-mech cs.LG math.ST stat.ML stat.TH 57%

Review and Prospect of Algebraic Research in Equivalent Framework between Statistical Mechanics and Machine Learning Theory

Sumio Watanabe

机构 * RIKEN Center for Advanced Intelligence Project(理化学研究所高级智能中心)

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
2312.07352 2025-03-25 cs.CV cs.AI 57%

CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools

Chinedu Innocent Nwoye, Kareem Elgohary, Anvita Srinivas, Fauzan Zaid, Joël L. Lavanchy, Nicolas Padoy

机构 * University of Strasbourg(斯特拉斯堡大学) CNRS(法国国家科学研究中心) INSERM(法国国家健康与医学研究院) ICube(ICube实验室) University of Basel(巴塞尔大学) IHU Strasbourg(斯特拉斯堡大学医院研究所)

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments Surgical tool tracking dataset paper, 11 pages, 10 figures, 3 tables, CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16467 2025-03-24 cs.HC cs.AI cs.RO 57%

Enhancing Explainability with Multimodal Context Representations for Smarter Robots

Anargh Viswanath, Lokesh Veeramacheneni, Hendrik Buschmeier

机构 * Bielefeld University(比勒费尔德大学) University of Bonn(波恩大学)

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

Comments Presented at 3rd Workshop on Explainability in Human-Robot Collaboration at HRI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12287 2025-03-24 cs.CL 57%

CUE-M: Contextual Understanding and Enhanced Search with Multimodal Large Language Model

Dongyoung Go, Taesun Whang, Chanhee Lee, Hwa-Yeon Kim, Sunghoon Park, Seunghwan Ji, Jinho Kim, Dongchan Kim, Young-Bum Kim

机构 * Naver Corp(Naver公司) Naver Search(Naver搜索)

专题命中 其他安全 :safety(abstract);分类 cs.CL

Comments Preprint. Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.20109 2025-03-24 cs.CV cs.AI cs.MM 57%

GiVE: Guiding Visual Encoder to Perceive Overlooked Information

Junjie Li, Jianghong Ma, Xiaofeng Zhang, Yuhang Li, Jianyang Shi

机构 * Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) City University of Hong Kong(香港城市大学)

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

Comments This paper was accepted by ICME 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03035 2025-03-24 cs.RO cs.AI 57%

SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments

Zachary Ravichandran, Varun Murali, Mariliza Tzes, George J. Pappas, Vijay Kumar

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments Accepted to the International Conference on Robotics and Automation (ICRA) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.02798 2025-03-24 cs.CY cs.HC 57%

AI and personalized learning: bridging the gap with modern educational goals

Kristjan-Julius Laak, Jaan Aru

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.15946 2025-03-21 cs.LG 57%

Multivariate Time Series Anomaly Detection in Industry 5.0

Lorenzo Colombi, Michela Vespa, Nicolas Belletti, Matteo Brina, Simon Dahdal, Filippo Tabanelli, Elena Bellodi, Mauro Tortonesi, Cesare Stefanelli, Massimiliano Vignoli

机构 * University of Ferrara(费拉拉大学) Bonfiglioli S.P.A.(邦菲利奥利股份公司)

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
2409.18042 2025-03-21 cs.CV cs.CL 57%

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

Kai Chen, Yunhao Gou, Runhui Huang, Zhili Liu, Daxin Tan, Jing Xu, Chunwei Wang, Yi Zhu, Yihan Zeng, Kuo Yang, Dingdong Wang, Kun Xiang, Haoyuan Li, Haoli Bai, Jianhua Han, Xiaohui Li, Weike Jin, Nian Xie, Yu Zhang, James T. Kwok, Hengshuang Zhao, Xiaodan Liang, Dit-Yan Yeung, Xiao Chen, Zhenguo Li, Wei Zhang, Qun Liu, Jun Yao, Lanqing Hong, Lu Hou, Hang Xu

机构 * Hong Kong University of Science and Technology(香港科技大学) The University of Hong Kong(香港大学) Huawei Noah’s Ark Lab(华为诺亚方舟实验室) The Chinese University of Hong Kong(香港中文大学) Sun Yat-sen University(中山大学) Southern University of Science and Technology(南方科技大学)

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

Comments Accepted by CVPR 2025. Project Page: https://emova-ollm.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14928 2025-03-20 cs.CV cs.AI cs.SD eess.AS 57%

Shushing! Let's Imagine an Authentic Speech from the Silent Video

Jiaxin Ye, Hongming Shan

机构 * Fudan University(复旦大学)

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

Comments Project Page: https://imagintalk.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.13684 2025-03-20 cs.CV cs.AI 57%

SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning

Hongjun Wang, Sagar Vaze, Kai Han

机构 * The University of Hong Kong(香港大学) University of Oxford(牛津大学)

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

Comments v3: Fix bold typos in table 2 and 3; v2: Update DINOv2 results; Accepted as a conference paper at ICLR 2024; Project page: https://visual-ai.github.io/sptnet

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13473 2025-03-19 eess.SP cs.AI cs.CV cs.RO 57%

Robust Detection of Extremely Thin Lines Using 0.2mm Piano Wire

Jisoo Hong, Youngjin Jung, Jihwan Bae, Seungho Song, Sung-Woo Kang

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
2503.12080 2025-03-18 cs.HC cs.AI 57%

Comparing Human Expertise and Large Language Models Embeddings in Content Validity Assessment of Personality Tests

Nicola Milano, Michela Ponticorvo, Davide Marocco

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
2503.12207 2025-03-18 cs.CY 57%

ReDefining Code Comprehension: Function Naming as a Mechanism for Evaluating Code Comprehension

David H. Smith, Max Fowler, Paul Denny, Craig Zilles

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12043 2025-03-18 cs.SE cs.AI 57%

An LLM-Integrated Framework for Completion, Management, and Tracing of STPA

Ali Raeisdanaei, Juho Kim, Michael Liao, Sparsh Kochhar

机构 * Blue Sky Solar Racing(蓝天太阳能赛车团队) University of Toronto(多伦多大学)

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
2501.09291 2025-03-18 cs.MM cs.AI cs.SD eess.AS 57%

LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport

Kyeongha Rho, Hyeongkeun Lee, Valentio Iverson, Joon Son Chung

机构 * KAIST(韩国科学技术院) University of Waterloo(滑铁卢大学)

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

Comments 5 pages, 2 figures; Accepted to ICASSP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.02464 2025-03-18 cs.CV cs.AI cs.RO 57%

Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

Yuliang Guo, Sparsh Garg, S. Mahdi H. Miangoleh, Xinyu Huang, Liu Ren

机构 * Bosch Research North America(博世北美研究院) Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心) Carnegie Mellon University(卡内基梅隆大学) Simon Fraser University(西蒙菲莎大学)

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
2503.10229 2025-03-14 cs.CL 57%

R.U.Psycho? Robust Unified Psychometric Testing of Language Models

Julian Schelb, Orr Borin, David Garcia, Andreas Spitz

机构 * University of Konstanz(康斯坦茨大学) Recosys

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
2503.09418 2025-03-13 cs.LG 57%

Efficient dynamic modal load reconstruction using physics-informed Gaussian processes based on frequency-sparse Fourier basis functions

Gledson Rodrigo Tondo, Igor Kavrakov, Guido Morgenthal

机构 * Bauhaus-Universität Weimar(魏玛包豪斯大学) University of Cambridge(剑桥大学)

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
2503.08240 2025-03-12 cs.LG math.DG 57%

Tangentially Aligned Integrated Gradients for User-Friendly Explanations

Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew

机构 * School of Electrical and Mechanical Engineering, The University of Adelaide(阿德莱德大学电气与机械工程学院) School of Computer and Mathematical Sciences, The University of Adelaide(阿德莱德大学计算机与数学科学学院) Information Sciences Division, Defence Science and Technology Group(澳大利亚国防科学与技术集团信息科学部)

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

Comments To appear in the proceedings of the 32nd Irish Conference on Artificial Intelligence and Cognitive Science

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02162 2025-03-12 cs.CV cs.LG 57%

X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning

Jianzhong You, Yuan Gao, Sangwook Kim, Chris Mcintosh

机构 * Peter Munk Cardiac Centre(彼得·芒克心脏中心) University Health Network (UHN)(大学健康网络) University of Toronto (U of T)(多伦多大学) Ted Rogers Centre for Heart Research(泰德·罗杰斯心脏研究中心) Toronto General Hospital Research Institute(多伦多综合医院研究所) Vector Institute(矢量研究所)

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

Comments 11 pages, 1 figure, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07587 2025-03-11 cs.CV cs.AI cs.RO 57%

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru

Dunant Cusipuma, David Ortega, Victor Flores-Benites, Arturo Deza

机构 * Artificio

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

Comments A pre-print. 26 pages. Link to Code + Data: https://huggingface.co/datasets/Artificio/robusto-1

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07493 2025-03-11 cs.CV cs.AI 57%

V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation

Guiwei Zhang, Tianyu Zhang, Mohan Zhou, Yalong Bai, Biye Li

机构 * Du Xiaoman Financial(度小满金融)

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

Comments 11 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07096 2025-03-11 cs.AI 57%

Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration

Zhao Jin, Lu Jin, Yizhe Luo, Shuo Feng, Yucheng Shi, Kai Zheng, Xinde Yu, Mingliang Xu

机构 * Zhengzhou University(郑州大学) University of Electronic Science and Technology(电子科技大学)

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
2503.06410 2025-03-11 cs.AI 57%

Performant LLM Agentic Framework for Conversational AI

Alex Casella, Wayne Wang

机构 * Thoughtly(思利科技) Boston University(波士顿大学)

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

Comments 6 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03135 2025-03-11 cs.LG 57%

Bridging Molecular Graphs and Large Language Models

Runze Wang, Mingqi Yang, Yanming Shen

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

Comments AAAI 2025 camera ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.04460 2025-03-11 eess.IV cs.CV cs.LG 57%

U-net based prediction of cerebrospinal fluid distribution and ventricular reflux grading

Melanie Rieff, Fabian Holzberger, Oksana Lapina, Geir Ringstad, Lars Magnus Valnes, Bogna Warsza, Kent-Andre Mardal, Per Kristian Eide, Barbara Wohlmuth

机构 * Technical University of Munich(慕尼黑工业大学) Oslo University Hospital Rikshospitalet(奥斯陆大学医院理克斯医院) Sorlandet Hospital(索兰医院) University of Oslo(奥斯陆大学) Simula Research Laboratory(Simula研究实验室)

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

Comments 13 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.05109 2025-03-10 cs.HC cs.CY 57%

Can Large Language Models Grasp Concepts in Visual Content? A Case Study on YouTube Shorts about Depression

Jiaying "Lizzy" Liu, Yiheng Su, Praneel Seth

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

Comments 11 pages

Journal ref CHI Conference on Human Factors in Computing Systems (CHI EA 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.02975 2025-03-10 cs.RO cs.LG cs.SY eess.SY 57%

Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation

Francisco Giral, Ignacio Gómez, Ricardo Vinuesa, Soledad Le Clainche

机构 * Universidad Politécnica de Madrid(马德里理工大学) KTH Royal Institute of Technology(瑞典皇家理工学院)

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