guoriyue/VRL

AlphaGRPO[ICML 2026] and SpectraReward[NeurIPS 2026 Spotlight✨]

An LLM post-training framework with vLLM for RL Scaling

Multimodal RL training framework for diffusion & omni models

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Configuration-driven reinforcement learning for text-to-image, text-to-video, and image-to-video generation.

slime is an LLM training framework for RL Scaling.