互联网Hattrick: Solving Multi-Class TE using Neural Models SIGCOMM ’25: ACM SIGCOMM 2025 Conference September 8 – 11, 2025 Coimbra, Portugal Conference Sponsors: SIGCOMM https://... hhx 1周前 (12-30)
未分类MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency 会议:ICML 2025(第42届国际机器学习大会) Dongzhi Jiang∗ 1 , Renrui Zhang∗† 1 , Ziyu Guo2 , Yanwei Li‡3 , Yu Qi‡4 , Xinyan Chen‡1Liuhui Wang‡5 , Jianha... hcl 2周前 (12-27)
区块链ExClique: An Express Consensus Algorithm for High-Speed Transaction Process in Blockchains Zhao C, Zhou Y, Zhang S, et al. ExClique: An Express Consensus Algorithm for High-Speed Transaction Process in Blockchains[C]//IEEE INFOCO... 韦帆 2周前 (12-26)
互联网RedTE: Mitigating Subsecond Traffic Bursts with Real-time and Distributed Traffic Engineering ACM SIGCOMM ’24: Proceedings of the ACM SIGCOMM 2024 Conference https://doi.org/10.1145/3651890.3672231 一、全文概述 RedTE是一种基于分布式... hhx 2周前 (12-24)
未分类Mastering Multi-Drone Volleyball throughHierarchical Co-Self-Play Reinforcement Learning 一、研究背景与挑战 任务定义:3v3 多无人机排球(Multi-Drone Volleyball)该任务要求三台无人机组成一个团队与另一个三机团队进行排球比赛。它同时具有以下挑战性: 高层策略与低层控制耦合:需要在物理环境中做出战术决策(如团队配合、球路选择)并执... hcl 3周前 (12-19)
区块链Sailfish: Towards Improving the Latency of DAG-based BFT N. Shrestha, R. Shrothrium, A. Kate and K. Nayak, “Sailfish: Towards Improving the Latency of DAG-Based BFT,” 2025 IEEE Sympos... 韦帆 3周前 (12-18)
人工智能DiffFP: Learning Behaviors from Scratch via Diffusion-based FictitiousPlay 作者:Akash Karthikeyan, Yash Vardhan Pant 问题背景与动机 自我对弈(self-play)强化学习在博弈性和多智能体任务中已被证明能够学习复杂策略,但在连续动作空间、对手多样性 以及 泛化性 方面仍存在显著挑战,包括: 传... hcl 4周前 (12-12)
区块链ContribChain: A Stress-Balanced Blockchain Sharding Protocol with Node Contribution Awareness X. Huang et al., “ContribChain: A Stress-Balanced Blockchain Sharding Protocol with Node Contribution Awareness,” IEEE INFOCOM... 韦帆 4周前 (12-12)
互联网PhyDNNs: Bringing Deep Neural Networks to the Physical Layer 打破传统边界,让 AI 更快更省能——PhyDNNs 正在重塑通信与智能终端未来! 在智能设备与实时交互应用高速发展的今天,从增强现实 (AR) 到虚拟现实 (VR),从智能驾驶到无人机,都对实时计算提出了前所未有的要求。然而,深度神经网络(DNN)传统的... 前康 4周前 (12-11)
人工智能A Survey on Self-Play Methods in Reinforcement Learning 论文要点 论文提出了一个统一框架来刻画 self-play(智能体与自身或自身历史版本交互以改进策略)的各种方法,按策略更新机制、对手选择与人口管理、博弈类型(零和/非零和、可转性/非可转性)等维度进行分类,并回顾了代表性算法、应用场景与理论/实践挑战,同时列出了未来研究... hcl 1个月前 (12-05)