#Training Systems

共 1 篇
tags Deep Reading 33 Paper Reading 24 Code Reading 16 Computer Vision 12 Generative AI 5 Recommendation System 5 3D Generation 4 Agentic RL 3 Training Systems 1
还有 95 个标签 →

2026

2026.07
  1. SAO 论文精读:单轨迹异步优化、双边重要性采样与 Agentic RL 稳定训练

    精读 SAO 如何通过单轨迹异步采样、双边 Token 级重要性门控、快速价值模型更新和 Skip-Observation GAE 稳定训练长时域推理与编码智能体