大模型对齐与安全 - arXivDaily 专题

2412.10831 2025-03-20 cs.CV 50%

Low-Biased General Annotated Dataset Generation

Dengyang Jiang, Haoyu Wang, Lei Zhang, Wei Wei, Guang Dai, Mengmeng Wang, Jingdong Wang, Yanning Zhang

机构 * Northwestern Polytechnical University（西北工业大学）； State Grid Corporation of China（中国国家电网有限公司）； Zhejiang University of Technology（浙江工业大学）； Baidu Inc（百度公司）

专题命中 AI治理与伦理：alignment(abstract)

Comments CVPR2025 Accepted Paper

2503.09024 2025-03-13 cs.RO cs.SY eess.IV eess.SY 50%

Traffic Regulation-aware Path Planning with Regulation Databases and Vision-Language Models

Xu Han, Zhiwen Wu, Xin Xia, Jiaqi Ma

机构 * University of California Los Angeles（加利福尼亚大学洛杉矶分校）

专题命中 AI治理与伦理：safety(abstract)

Comments 7 pages, 7 figures, submitted to ICRA

2412.11464 2025-03-13 cs.CV 50%

High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation

Quan-Sheng Zeng, Yunheng Li, Daquan Zhou, Guanbin Li, Qibin Hou, Ming-Ming Cheng

机构 * Nankai University（南开大学）； Sun Yat-sen University（中山大学）； ByteDance Inc.（字节跳动公司）

专题命中 AI治理与伦理：alignment(abstract)

Comments Revised version according to comments from reviewers of ICLR2025

2503.03270 2025-03-06 cs.CV cs.CR 50%

Reduced Spatial Dependency for More General Video-level Deepfake Detection

Beilin Chu, Xuan Xu, Yufei Zhang, Weike You, Linna Zhou

机构 * School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）

专题命中 AI治理与伦理：safety(abstract)

Comments 5 pages, 2 figures. Accepted to ICASSP 2025

2502.19822 2025-02-28 cs.HC 50%

Empowering Social Service with AI: Insights from a Participatory Design Study with Practitioners

Yugin Tan, Kai Xin Soh, Renwen Zhang, Jungup Lee, Han Meng, Biswadeep Sen, Yi-Chieh Lee

专题命中 AI治理与伦理：safety(abstract)

2501.11752 2025-02-20 cs.CV 50%

Are generative models fair? A study of racial bias in dermatological image generation

Miguel López-Pérez, Søren Hauberg, Aasa Feragen

机构 * Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València（瓦伦西亚理工大学以人为本技术大学研究所）； Technical University of Denmark（丹麦技术大学）

专题命中 AI治理与伦理：trustworthy(abstract)

Comments Under review

2502.11024 2025-02-18 cs.CV 50%

TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules

Ruoyu Zhang, Lulu Wang, Yi He, Tongling Pan, Zhengtao Yu, Yingna Li

机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）； Yunnan Key Laboratory of Computer Technologies Application（云南省计算机技术应用重点实验室）； Hongyun Honghe Group Honghe Cigarette Factory（红云红河集团红河卷烟厂）

专题命中 AI治理与伦理：alignment(abstract)

2405.13459 2025-02-18 cs.CV 50%

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards

Xiaoyu Yang, Jie Lu, En Yu

机构 * Australian Artificial Intelligence Institute (AAII)（澳大利亚人工智能研究所（AAII））； University of Technology Sydney（悉尼科技大学）

专题命中 AI治理与伦理：alignment(abstract)

Comments ICLR 2025 Poster

2302.12167 2025-02-11 econ.GN math.OC q-fin.EC 50%

A Principal-Agent Model for Optimal Incentives in Renewable Investments

René Aïd, Annika Kemper, Nizar Touzi

专题命中 AI治理与伦理：alignment(abstract)

2502.03549 2025-02-11 cs.CV 50%

Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

Jingyi Yang, Zitong Yu, Xiuming Ni, Jia He, Hui Li

机构 * University of Science and Technology of China（中国科学技术大学）； Great Bay University（大湾区大学）； Anhui Tsinglink Information Technology Co.,Ltd.（安徽清听信息技术有限公司）

专题命中 AI治理与伦理：alignment(abstract)

Comments Accepted to ICLR 2025

2407.11548 2025-01-06 cs.IR 50%

A PLMs based protein retrieval framework

Yuxuan Wu, Xiao Yi, Yang Tan, Huiqun Yu, Guisheng Fan, Gaowei Zheng

专题命中 AI治理与伦理：alignment(abstract)

Comments 16 pages, 12 figures

2412.11938 2024-12-17 eess.IV cs.CV 50%

Are the Latent Representations of Foundation Models for Pathology Invariant to Rotation?

Matouš Elphick, Samra Turajlic, Guang Yang

专题命中 AI治理与伦理：alignment(abstract)

Comments Samra Turajlic and Guang Yang are joint last authors

2411.01007 2024-11-05 cs.HC 50%

When Two Wrongs Don't Make a Right" -- Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology

Emely Rosbach, Jonas Ammeling, Sebastian Krügel, Angelika Kießig, Alexis Fritz, Jonathan Ganz, Chloé Puget, Taryn Donovan, Andrea Klang, Maximilian C. Köller, Pompei Bolfa, Marco Tecilla, Daniela Denk, Matti Kiupel, Georgios Paraschou, Mun Keong Kok, Alexander F. H. Haake, Ronald R. de Krijger, Andreas F. -P. Sonnen, Tanit Kasantikul, Gerry M. Dorrestein, Rebecca C. Smedley, Nikolas Stathonikos, Matthias Uhl, Christof A. Bertram, Andreas Riener, Marc Aubreville

专题命中 AI治理与伦理：alignment(abstract)

2010.14129 2024-10-30 cs.CV cs.MM 50%

Mining Generalized Features for Detecting AI-Manipulated Fake Faces

Yang Yu, Rongrong Ni, Yao Zhao

专题命中 AI治理与伦理：alignment(abstract)

Comments 14 pages, 9 figures. This work has been submitted to the IEEE for possible publication

2409.04508 2024-09-10 cs.HC 50%

Toward LLM-Powered Social Robots for Supporting Sensitive Disclosures of Stigmatized Health Conditions

Alemitu Bezabih, Shadi Nourriz, C. Estelle Smith

专题命中 AI治理与伦理：safety(abstract)

2409.02433 2024-09-05 cs.SE 50%

From Literature to Practice: Exploring Fairness Testing Tools for the Software Industry Adoption

Thanh Nguyen, Luiz Fernando de Lima, Maria Teresa Badassarre, Ronnie de Souza Santos

专题命中 AI治理与伦理：trustworthy(abstract)

2408.16700 2024-08-30 cs.CV 50%

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models

Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Xingqian Xu, Humphrey Shi, Nicu Sebe

专题命中 AI治理与伦理：safety(abstract)

Comments Under review. Code: https://github.com/Moreno98/GradBias

2407.14023 2024-07-22 cs.SE 50%

Towards Extracting Ethical Concerns-related Software Requirements from App Reviews

Aakash Sorathiya, Gouri Ginde

专题命中 AI治理与伦理：safety(abstract)

2406.11323 2024-07-01 cs.IR 50%

Transparency, Privacy, and Fairness in Recommender Systems

Dominik Kowald

专题命中 AI治理与伦理：trustworthy(abstract)

Comments Habilitation (post-doctoral thesis) at Graz University of Technology for the scientific subject "Applied Computer Science" (accepted in June 2024)

2406.13912 2024-06-21 cs.CV 50%

From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment

Yusuke Hirota, Ryo Hachiuma, Chao-Han Huck Yang, Yuta Nakashima

专题命中 AI治理与伦理：alignment(abstract)

2312.04314 2024-06-04 cs.CV 50%

GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

Zuyao Chen, Jinlin Wu, Zhen Lei, Zhaoxiang Zhang, Changwen Chen

专题命中 AI治理与伦理：alignment(abstract)

2405.16430 2024-05-28 cs.RO cs.MA 50%

GAMEOPT+: Improving Fuel Efficiency in Unregulated Heterogeneous Traffic Intersections via Optimal Multi-agent Cooperative Control

Nilesh Suriyarachchi, Rohan Chandra, Arya Anantula, John S. Baras, Dinesh Manocha

专题命中 AI治理与伦理：safety(abstract)

Comments Journal Version

2404.12558 2024-04-22 cs.HC 50%

Just Like Me: The Role of Opinions and Personal Experiences in The Perception of Explanations in Subjective Decision-Making

Sharon Ferguson, Paula Akemi Aoyagui, Young-Ho Kim, Anastasia Kuzminykh

专题命中 AI治理与伦理：trustworthy(abstract)

Comments Presented at the Trust and Reliance in Evolving Human-AI Workflows (TREW) Workshop at CHI 2024

2404.06777 2024-04-11 cs.NI 50%

Responsible Federated Learning in Smart Transportation: Outlooks and Challenges

Xiaowen Huang, Tao Huang, Shushi Gu, Shuguang Zhao, Guanglin Zhang

专题命中 AI治理与伦理：safety(abstract)

2309.14504 2024-03-05 cs.HC 50%

People's Perceptions Toward Bias and Related Concepts in Large Language Models: A Systematic Review

Lu Wang, Max Song, Rezvaneh Rezapour, Bum Chul Kwon, Jina Huh-Yoo

专题命中 AI治理与伦理：safety(abstract)

2210.05332 2024-02-07 cs.CV 50%

Gender Stereotyping Impact in Facial Expression Recognition

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

专题命中 AI治理与伦理：safety(abstract)

Comments Presented at SoGood 2022, The 7th Workshop on Data Science for Social Good, held in conjunction with ECML PKDD 2022, in September 2022, at Grenoble, France

2202.12861 2024-02-06 cs.MA cs.RO math.OC 50%

Hierarchical Control for Head-to-Head Autonomous Racing

Rishabh Saumil Thakkar, Aryaman Singh Samyal, David Fridovich-Keil, Zhe Xu, Ufuk Topcu

专题命中 AI治理与伦理：safety(abstract)

Journal ref Field Robotics, 4, 46-69 (2024)

2311.18420 2024-01-31 cs.CV 50%

TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing

Lianrui Mu, Jianhong Bai, Xiaoxuan He, Jiangnan Ye, Xiaoyu Liang, Yuchen Yang, Jiedong Zhuang, Haoji Hu

专题命中 AI治理与伦理：alignment(abstract)

2311.10861 2023-11-21 econ.GN q-fin.EC 50%

First, Do No Harm: Algorithms, AI, and Digital Product Liability

Marc J. Pfeiffer

专题命中 AI治理与伦理：safety(abstract)

Comments 22 pages

2305.15003 2023-11-14 cs.MA 50%

Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions

Ashwin George, Luciano Cavalcante Siebert, David Abbink, Arkady Zgonnikov

专题命中 AI治理与伦理：safety(abstract)

1. AI治理与伦理 1852 篇

Low-Biased General Annotated Dataset Generation

Traffic Regulation-aware Path Planning with Regulation Databases and Vision-Language Models

High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation

Reduced Spatial Dependency for More General Video-level Deepfake Detection

Empowering Social Service with AI: Insights from a Participatory Design Study with Practitioners

Are generative models fair? A study of racial bias in dermatological image generation

TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards

A Principal-Agent Model for Optimal Incentives in Renewable Investments

Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

A PLMs based protein retrieval framework

Are the Latent Representations of Foundation Models for Pathology Invariant to Rotation?

When Two Wrongs Don't Make a Right" -- Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology

Mining Generalized Features for Detecting AI-Manipulated Fake Faces

Toward LLM-Powered Social Robots for Supporting Sensitive Disclosures of Stigmatized Health Conditions

From Literature to Practice: Exploring Fairness Testing Tools for the Software Industry Adoption

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models

Towards Extracting Ethical Concerns-related Software Requirements from App Reviews

Transparency, Privacy, and Fairness in Recommender Systems

From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment

GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

GAMEOPT+: Improving Fuel Efficiency in Unregulated Heterogeneous Traffic Intersections via Optimal Multi-agent Cooperative Control

Just Like Me: The Role of Opinions and Personal Experiences in The Perception of Explanations in Subjective Decision-Making

Responsible Federated Learning in Smart Transportation: Outlooks and Challenges

People's Perceptions Toward Bias and Related Concepts in Large Language Models: A Systematic Review

Gender Stereotyping Impact in Facial Expression Recognition

Hierarchical Control for Head-to-Head Autonomous Racing

TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing

First, Do No Harm: Algorithms, AI, and Digital Product Liability

Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions