arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Microsoft(微软)

2026-06-17 至 2026-06-17 共收录 4
2606.17664 2026-06-17 cs.IR cs.AI 新提交

Temporal Preference Optimization for Unsupervised Retrieval

面向无监督检索的时间偏好优化

HyunJin Kim, Jaejun Shim, Young Jin Kim, JinYeong Bak

机构 * Microsoft, Redmond, USA(微软公司,美国红mond) Sungkyunkwan University, Suwon, South Korea(成均馆大学,韩国首尔)

AI总结 提出TPOUR方法,通过时间检索偏好优化(TRPO)和可学习时间嵌入插值,使无监督稠密检索器能捕捉时间相关性,在时间信息检索任务上超越有监督和无监督基线。

Comments Accepted to ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.18897 2026-06-17 cs.DC cs.AI 版本更新

Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving

并行化工具执行与LLM生成以实现低延迟代理服务

Yifan Sui, Han Zhao, Rui Ma, Zhiyuan He, Hao Wang, Jianxun Li, Kaiqiang Xu, Kai Chen, Yuqing Yang

机构 * Shanghai Jiao Tong University(上海交通大学) Microsoft Research(微软研究院) Stevens Institute of Technology(Stevens 工程学院) Google(谷歌) Hong Kong University of Science and Technology(香港科学与技术大学)

AI总结 提出PASTE系统,通过预测性执行未来工具调用与LLM生成并行,减少任务完成时间43.5%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.14771 2026-06-17 cs.CV cs.AI cs.LG cs.MM cs.NE 版本更新

GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture

GOT-JEPA:基于联合嵌入预测架构的通用目标跟踪与模型自适应及遮挡处理

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin

机构 * Department of Computer Science, National Yang Ming Chiao Tung University(国家阳明交通大学计算机科学系) Research Center for Information Technology Innovation, Academia Sinica(中华学术院信息技术创新研究中心) Microsoft AI(微软人工智能)

AI总结 提出GOT-JEPA框架,通过预测跟踪模型而非图像特征来提升泛化能力,并设计OccuSolver增强遮挡感知,在七个基准上验证了有效性。

Comments Accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). This research focuses on learning model adaptation for adverse and dynamic environments, as well as fine-grained occlusion perception for tracking

Journal ref IEEE Transactions on Circuits and Systems for Video Technology 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01761 2026-06-17 cs.LG cs.AI 版本更新

Position: Modular Memory is the Key to Continual Learning Agents

Position: 模块化记忆是持续学习智能体的关键

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, Barbara Hammer, Tyler L. Hayes, Timm Hess, Christopher Kanan, Dhireesha Kudithipudi, Xialei Liu, Vincenzo Lomonaco, Jorge Mendez-Mendez, Darshan Patil, Ameya Prabhu, Elisa Ricci, Tinne Tuytelaars, Gido M. van de Ven, Liyuan Wang, Joost van de Weijer, Jonghyun Choi, Martin Mundt, Rahaf Aljundi

机构 * University of Bremen(不莱梅大学) Seoul National University(首尔国立大学) Computer Vision Center Barcelona(巴塞罗那计算机视觉中心) University of Florence(佛罗伦萨大学) Microsoft Research(微软研究院) HEC Montreal, Mila--Quebec AI Institute, Canada CIFAR AI Chair(蒙特利尔HEC学院、魁北克人工智能研究所、加拿大CIFAR人工智能 chair) Bielefeld University(比勒海姆大学) Georgia Institute of Technology(佐治亚理工学院) University of Rochester(罗切斯特大学) University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校) Nankai University(南开大学) LUISS University(卢西亚诺大学) Stony Brook University(石溪大学) University of Tübingen(图宾根大学) University of Trento, FBK(特伦托大学,FBK) Tsinghua University(清华大学) University of Groningen(Groningen大学)

AI总结 本文提出通过模块化记忆结合权重内学习与上下文学习,解决持续学习中的灾难性遗忘问题,实现大规模持续适应。

Comments ICML 2026 Position Track Spotlight. This work stems from discussions held at the Dagstuhl seminar on Continual Learning in the Era of Foundation Models (October 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏