Images and videoRepoPrecise[NeurIPS 2026] Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Modelsdiffusiongrpo-training19Python4 wk agoTencent-HunyuanShare or keepTake it
GitHubReporlcliA CLI Interface for continual learningasync-rlgrpo-trainingon-policy-self-distillation6PythonApache-2.08 wk agopolygrammeShare or keepTake it