AI agents running research on single-GPU nanochat training automatically

World-Gymnast: Training Robots with Reinforcement Learning in a World Model

An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers

Various transformers for FSDP research

[CoRL 2024] Official codebase of paper "ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data"