arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-08-07 至 2026-08-07 共收录 4
2608.06351 2026-08-07 cs.AI 新提交

Challenges in Evaluating Explanation Methods for Static and Evolving Data

静态与演化数据的解释方法评估面临的挑战

Jerzy Stefanowski

机构 * Poznan University of Technology(波兹南工业大学)

AI总结 本文针对可解释人工智能的评估不足,以DetoxAI系统为例展开研究,探索了演化数据流的解释适配方法,最后关联了数据、模型与解释协同演化的跟踪挑战。

Comments 13 pages, 1 figure = this paper is a preprint of the workshop [Explainable AI in Space] paper for IJCAI ECAI 2026 conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11313 2026-08-07 cs.CV

Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval

Weijia Liu, Jiuxin Cao, Bo Miao, Zhiheng Fu, Xuelin Zhu, Jiawei Ge, Bo Liu, Mehwish Nasim, Ajmal Mian

机构 * Southeast University(东南大学) The University of Adelaide(阿德莱德大学) The Hong Kong Polytechnic University(香港理工大学) The University of Western Australia(西澳大学)

Comments Accepted by IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04811 2026-08-07 cs.LG cs.SI 版本更新

HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing

HCRide:面向以人为中心的网约车服务,协调乘客公平性与司机偏好

Lin Jiang, Yu Yang, Guang Wang

机构 * Department of Computer Science, Florida State University(佛罗里达州立大学计算机科学系) Department of Computer Science and Engineering, Lehigh University(莱斯利大学计算机科学与工程系)

AI总结 本研究设计了基于Habic算法的HCRide网约车系统,在不损害效率的前提下协调乘客公平性与司机偏好,经深圳和纽约数据集验证,其效率、公平性及司机偏好满意度均优于现有基线。

Comments 9 pages, 4 figures. Accepted as a regular paper in the Human-Centred Artificial Intelligence Track at IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04780 2026-08-07 cs.LG cs.AI cs.SI 版本更新

Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration

面向灾后公平电力恢复的不确定性感知预测后优化框架

Lin Jiang, Dahai Yu, Rongchao Xu, Tian Tang, Guang Wang

机构 * Department of Computer Science, Florida State University(计算机科学系,佛罗里达州立大学) Askew School of Public Administration and Policy, Florida State University(公共行政与政策学院,佛罗里达州立大学)

AI总结 针对灾后电力恢复的公平性与效率问题,提出含公平共形分位数回归、时空注意力强化学习的EPOPR框架,使平均停电时长降3.60%、社区间不公平度降14.19%。

Comments 9 pages, 12 figures. Accepted as a regular paper in the AI and Social Good Track at IJCAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏