人工智能Detecting Influence Structures in Multi-Agent Reinforcement Learning ① 研究背景:从“策略学习”走向“影响建模” 在多智能体强化学习(MARL)中,一个几乎所有工作都默认但很少被真正刻画的问题是:智能体之间到底是如何相互影响的?论文开篇就明确指出:“理解智能体之间的相互影响对于有效学习策略至关重要”在MARL系统中,所有智能体都处在一个共... 前康 6小时前
人工智能SWASH: A Flexible Communication Framework with Sliding Window-Based Cache Sharing for Scalable DGNN Training Proceedings of the ACM on Management of Data, Volume 3, Issue 3 (June 2025) hps://doi.org/10.1145/3725360 EISSN: 2836-6573 1. 摘要(... hhx 17小时前
新型网络体系结构From Concept to Measurement: A Survey of How the Blockchain Trilemma Is Analyzed arXiv:2505.03768v4, October 2025 Mansur Masama Aliyu, Niclas Kannengiesser, Ali Sunyaev Karlsruhe Institute of Technology / Technical... 杨, 宗霖 1天前
新型网络体系结构A Comprehensive Survey of Blockchain Scalability: Shaping Inner-Chain and Inter-Chain Perspectives Baochao Chen, Liyuan Ma, Hao Xu, Juncheng Ma, Dengcheng Hu, Xiulong Liu, Jie Wu, Jianrong Wang, Keqiu Li 天津大学 / Temple University htt... 杨, 宗霖 1天前
人工智能Hydro: Adaptive Query Processing of ML Queries 1. 摘要(Abstract) Hydro提出了一种面向机器学习查询的数据库管理系统(ML-centric DBMS),核心创新在于将自适应查询处理(Adaptive Query Processing,AQP)技术全面引入UDF密集型查询场景,从而彻底解决传统静态查询优化... hhx 1周前 (03-30)
新型网络体系结构Alibaba HPN: A Data Center Network for Large Language Model Training SIGCOMM ’24: ACM SIGCOMM 2024 Conference, August 4–8, 2024, Sydney, NSW, Australia https://dl.acm.org/doi/10.1145/3651890.3672265 ... 杨, 宗霖 1周前 (03-29)
新型网络体系结构MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs NSDI ’24: 21st USENIX Symposium on Networked Systems Design and Implementation, April 16–18, 2024, Santa Clara, CA, USA https://ww... 杨, 宗霖 1周前 (03-29)
NFTPegasus: A Universal Framework for Scalable Deep Learning Inference SIGCOMM ’25: ACM SIGCOMM 2025 Conference September 8 – 11, 2025 Coimbra, Portuga 1. 摘要(Abstract) Pegasus针对当前Inte... hhx 2周前 (03-27)
未分类Reinforcement Learning with Fuzzy Human Attention-GuidedGraph for Heterogeneous Multiagent Systems ① 研究背景 在多智能体系统(Multi-Agent Systems, MAS)中,如何实现高效协同一直是核心问题。从自动驾驶车队到分布式网络控制,再到你正在研究的跨域协同场景,本质上都面临一个共同挑战:多个异构智能体如何在复杂环境中做出协调一致的决策。 然而现实世... 前康 2周前 (03-25)
互联网Securing BGP ASAP: ASPA and other Post-ROV Defenses ① 研究背景:ROV之后,BGP真的安全吗? 在过去十多年中,围绕 BGP(边界网关协议)安全 的核心改进,主要集中在基于 RPKI 的 ROV(Route Origin Validation)机制。这一机制通过密码学信任链验证路由前缀的“起源合法性”,在一定程度上缓解了... 前康 2周前 (03-23)