Official code repository of "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion" @ ICCV 2023

A Collection of Variational Autoencoders (VAE) in PyTorch.

Taming Transformers for High-Resolution Image Synthesis

Imitation learning algorithms

Archon is an AI agent that is able to create other AI agents using an advanced agentic coding workflow and framework knowledge base to unlock a new frontier of automated agents.

Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]

Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

FlashMLA: Efficient MLA decoding kernels

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

A library for generative social simulation

A customisable 3D platform for agent-based AI research

s1: Simple test-time scaling

Core ROS packages

🤗 smolagents: a barebones library for agents that think in python code.

Official implementation of "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Simple RL training for reasoning

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

[RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

Multi Task RL Baselines

A toolkit for reproducible reinforcement learning research.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

[ICLR 2024] DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation