大模型对齐与安全 - arXivDaily 专题

2310.06219 2023-10-11 cs.SE 50%

Runtime Monitoring of Human-centric Requirements in Machine Learning Components: A Model-driven Engineering Approach

Hira Naveed

专题命中 AI治理与伦理：safety(abstract)

2307.10650 2023-07-21 cs.IR 50%

Language-Enhanced Session-Based Recommendation with Decoupled Contrastive Learning

Zhipeng Zhang, Piao Tong, Yingwei Ma, Qiao Liu, Xujiang Liu, Xu Luo

专题命中 AI治理与伦理：alignment(abstract)

2305.11465 2023-05-22 cs.MA cs.RO 50%

Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation

Hikaru Asano, Ryo Yonetani, Mai Nishimura, Tadashi Kozuno

专题命中 AI治理与伦理：safety(abstract)

Comments To appear in the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

2305.09319 2023-05-17 cs.IR 50%

Fairness and Diversity in Information Access Systems

Lorenzo Porcaro, Carlos Castillo, Emilia Gómez, João Vinagre

专题命中 AI治理与伦理：trustworthy(abstract)

Comments Presented at the European Workshop on Algorithmic Fairness (EWAF'23) Winterthur, Switzerland, June 7-9, 2023

2305.09243 2023-05-17 cs.SI 50%

LogDoctor: an open and decentralized worker-centered solution for occupational management in healthcare

Sami Barrit, Alexandre Niset

专题命中 AI治理与伦理：safety(abstract)

2304.09218 2023-04-20 cs.CV 50%

Generative models improve fairness of medical classifiers under distribution shifts

Ira Ktena, Olivia Wiles, Isabela Albuquerque, Sylvestre-Alvise Rebuffi, Ryutaro Tanno, Abhijit Guha Roy, Shekoofeh Azizi, Danielle Belgrave, Pushmeet Kohli, Alan Karthikesalingam, Taylan Cemgil, Sven Gowal

专题命中 AI治理与伦理：safety(abstract)

2302.11360 2023-02-24 cs.IR 50%

Commonality in Recommender Systems: Evaluating Recommender Systems to Enhance Cultural Citizenship

Andres Ferraro, Gustavo Ferreira, Fernando Diaz, Georgina Born

专题命中 AI治理与伦理：alignment(abstract)

Comments extended version of "Measuring Commonality in Recommendation of Cultural Content: Recommender Systems to Enhance Cultural Citizenship", published at RecSys 2022

2206.11134 2022-11-28 cs.CV 50%

Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization

Peixian Chen, Kekai Sheng, Mengdan Zhang, Mingbao Lin, Yunhang Shen, Shaohui Lin, Bo Ren, Ke Li

专题命中 AI治理与伦理：alignment(abstract)

2208.01285 2022-08-03 cs.MA cs.GT 50%

Evaluating Inter-Operator Cooperation Scenarios to Save Radio Access Network Energy

Xavier Marjou, Tangui Le Gléau, Vincent Messié, Benoit Radier, Tayeb Lemlouma, Gaël Fromentoux

专题命中 AI治理与伦理：safety(abstract)

Comments 5 pages, 2 figures, 2 tables

2206.08938 2022-06-22 q-fin.RM 50%

Baseline validation of a bias-mitigated loan screening model based on the European Banking Authority's trust elements of Big Data & Advanced Analytics applications using Artificial Intelligence

Alessandro Danovi, Marzio Roma, Davide Meloni, Stefano Olgiati, Fernando Metelli

专题命中 AI治理与伦理：trustworthy(abstract)

Comments 13 pages, 4 tables, 7 figures

2206.07555 2022-06-16 cs.HC 50%

Respect as a Lens for the Design of AI Systems

William Seymour, Max Van Kleek, Reuben Binns, Dave Murray-Rust

专题命中 AI治理与伦理：safety(abstract)

Comments To appear in the Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES '22)

2205.09731 2022-05-20 cs.CV 50%

Towards Unified Keyframe Propagation Models

Patrick Esser, Peter Michael, Soumyadip Sengupta

专题命中 AI治理与伦理：alignment(abstract)

Comments CVPRW 2022 - AI for Content Creation Workshop. Code at https://github.com/runwayml/guided-inpainting

2202.11572 2022-03-21 cs.RO 50%

GAMEOPT: Optimal Real-time Multi-Agent Planning and Control for Dynamic Intersections

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

专题命中 AI治理与伦理：safety(abstract)

Comments Submitted to ITSC 2022

2112.01121 2021-12-03 cs.CV 50%

"Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving

Jack Stelling, Amir Atapour-Abarghouei

专题命中 AI治理与伦理：safety(abstract)

Comments 2021 IEEE International Conference on Big Data (IEEE BigData 2021)

2111.03635 2021-11-08 cs.CV 50%

BBC-Oxford British Sign Language Dataset

Samuel Albanie, Gül Varol, Liliane Momeni, Hannah Bull, Triantafyllos Afouras, Himel Chowdhury, Neil Fox, Bencie Woll, Rob Cooper, Andrew McParland, Andrew Zisserman

专题命中 AI治理与伦理：alignment(abstract)

2104.02818 2021-11-02 cs.HC 50%

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning

Aditi Mishra, Utkarsh Soni, Jinbin Huang, Chris Bryan

专题命中 AI治理与伦理：safety(abstract)

2007.12123 2021-10-19 cs.RO math.LO math.OC 50%

Receding Horizon Control Based Online Motion Planning with Partially Infeasible LTL Specifications

Mingyu Cai, Hao Peng, Zhijun Li, Hongbo Gao, Zhen Kan

专题命中 AI治理与伦理：safety(abstract)

Journal ref IEEE Control Systems Letters, 2021

2102.00971 2021-02-02 q-bio.BM 50%

Methodology-centered review of molecular modeling, simulation, and prediction of SARS-CoV-2

Kaifu Gao, Rui Wang, Jiahui Chen, Limei Cheng, Jaclyn Frishcosy, Yuta Huzumi, Yuchi Qiu, Tom Schluckbier, Guo-Wei Wei

专题命中 AI治理与伦理：safety(abstract)

Comments 99 pages, 17 figures

2007.16116 2020-08-19 astro-ph.CO astro-ph.GA 50%

Patterns of galaxy spin directions in SDSS and Pan-STARRS show parity violation and multipoles

Lior Shamir

专题命中 AI治理与伦理：alignment(abstract)

Comments ApSS, accepted. arXiv admin note: substantial text overlap with arXiv:1912.05429

1912.05429 2019-12-18 astro-ph.GA astro-ph.CO 50%

Large-scale patterns of galaxy spin rotation show cosmological-scale parity violation and multipoles

Lior Shamir

专题命中 AI治理与伦理：alignment(abstract)

Comments To be submitted. Comments welcome

1705.02321 2017-05-08 cs.GT 50%

Fairness Incentives for Myopic Agents

Sampath Kannan, Michael Kearns, Jamie Morgenstern, Mallesh Pai, Aaron Roth, Rakesh Vohra, Z. Steven Wu

专题命中 AI治理与伦理：safety(abstract)

0912.3984 2010-01-14 cs.MA 50%

Multi-Agent Model using Secure Multi-Party Computing in e-Governance

Durgesh Kumar Mishra, Samiksha Shukla

专题命中 AI治理与伦理：safety(abstract)

Journal ref Journal of Computing, Volume 1, Issue 1, pp 195-199, December 2009

1. AI治理与伦理 1852 篇

Runtime Monitoring of Human-centric Requirements in Machine Learning Components: A Model-driven Engineering Approach

Language-Enhanced Session-Based Recommendation with Decoupled Contrastive Learning

Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation

Fairness and Diversity in Information Access Systems

LogDoctor: an open and decentralized worker-centered solution for occupational management in healthcare

Generative models improve fairness of medical classifiers under distribution shifts

Commonality in Recommender Systems: Evaluating Recommender Systems to Enhance Cultural Citizenship

Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization

Evaluating Inter-Operator Cooperation Scenarios to Save Radio Access Network Energy

Baseline validation of a bias-mitigated loan screening model based on the European Banking Authority's trust elements of Big Data & Advanced Analytics applications using Artificial Intelligence

Respect as a Lens for the Design of AI Systems

Towards Unified Keyframe Propagation Models

GAMEOPT: Optimal Real-time Multi-Agent Planning and Control for Dynamic Intersections

"Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving

BBC-Oxford British Sign Language Dataset

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning

Receding Horizon Control Based Online Motion Planning with Partially Infeasible LTL Specifications

Methodology-centered review of molecular modeling, simulation, and prediction of SARS-CoV-2

Patterns of galaxy spin directions in SDSS and Pan-STARRS show parity violation and multipoles

Large-scale patterns of galaxy spin rotation show cosmological-scale parity violation and multipoles

Fairness Incentives for Myopic Agents

Multi-Agent Model using Secure Multi-Party Computing in e-Governance