Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

AI-Driven Scientific and Algorithmic Discovery

Source code of DreamDojo by the NVIDIA GEAR Team.

This is a repository for reinforcement learning implementation for Unitree robots, based on Mujoco.

Evaluating long-term memory of reinforcement learning algorithms

An interface library for RL post training with environments.

implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

RL gym for vision language models in JAX

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

A fork for TRM

LongLive: Real-time Interactive Long Video Generation

Baby Dragon Hatchling (BDH) – Architecture and Code

MobileLLM-R1

A minimal implementation of DeepMind's Genie world model

Train your Agent model via our easy and efficient framework

Hierarchical Reasoning Model Official Release

Interactive visualizations of the theory behind diffusion models.

Making large AI models cheaper, faster and more accessible

User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice routing providing a content-based sparse attention mechanism.