wandb

EspNetespnet/espnet

An end-to-end speech processing toolkit for speech recognition, text-to-speech, translation, enhancement, and more.

cleanrlvwxyzjn/cleanrl

A deep reinforcement learning library offering high-quality, single-file implementations of algorithms like PPO, DQN, and SAC for research and education.

PokemonRedExperimentsPWhiddy/PokemonRedExperiments

A reinforcement learning framework for training AI agents to play Pokémon Red using PyBoy emulation.

scGPTbowang-lab/scGPT

A transformer-based foundation model pretrained on millions of single-cell profiles for generative AI tasks in single-cell multi-omics.