arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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 3278 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 偏好对齐 3278 篇

2306.02841 2023-12-19 cs.IR 50%

CTRL: Connect Collaborative and Language Model for CTR Prediction

Xiangyang Li, Bo Chen, Lu Hou, Ruiming Tang

专题命中 偏好对齐 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.02687 2023-04-07 eess.SY cs.RO cs.SY 50%

Emergent Coordination through Game-Induced Nonlinear Opinion Dynamics

Haimin Hu, Kensuke Nakamura, Kai-Chieh Hsu, Naomi Ehrich Leonard, Jaime Fernández Fisac

专题命中 偏好对齐 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2201.04874 2022-11-16 eess.SY cs.SY 50%

A Minimax Framework for Two-Agent Scheduling with Inertial Constraints

Feihong Yang, Yuan Shen

专题命中 偏好对齐 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.09030 2022-06-22 cs.MA cs.RO 50%

Responsibility-associated Multi-agent Collision Avoidance with Social Preferences

Yiwei Lyu, Wenhao Luo, John M. Dolan

专题命中 偏好对齐 :safety(abstract)

Comments accepted at the 25th IEEE International Conference on Intelligent Transportation Systems (ITSC 2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.06169 2021-09-15 econ.GN q-fin.EC stat.AP 50%

A General Framework to Forecast the Adoption of Novel Products: A Case of Autonomous Vehicles

Subodh Dubey, Ishant Sharma, Sabyasachee Mishra, Oded Cats, Prateek Bansal

专题命中 偏好对齐 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2108.01294 2021-08-04 cs.RO 50%

An Analysis of Human-Robot Information Streams to Inform Dynamic Autonomy Allocation

Christopher X. Miller, Temesgen Gebrekristos, Michael Young, Enid Montague, Brenna Argall

专题命中 偏好对齐 :safety(abstract)

Comments 7 pages, 4 figures, IROS 2021 Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.13667 2021-06-28 cs.RO 50%

Move Beyond Trajectories: Distribution Space Coupling for Crowd Navigation

Muchen Sun, Francesca Baldini, Peter Trautman, Todd Murphey

专题命中 偏好对齐 :safety(abstract)

Comments 12 pages

Journal ref Robotics: Science and Systems, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
1408.1776 2014-08-11 cs.SE 50%

Context-awareness of the IoT through the on-the-fly preference modeling

Radoslaw Klimek, Leszek Kotulski

专题命中 偏好对齐 :trustworthy(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏