harnessRL

AI & ML interests

None defined yet.

Recent Activity

zhouxiangxin  authored a paper about 5 hours ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

zhouxiangxin  authored a paper about 5 hours ago

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

zhouxiangxin  authored a paper about 5 hours ago

TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL

View all activity

Team members 10