Understanding R1-Zero-Like Training: A Critical Perspective

Muon is an optimizer for hidden layers in neural networks

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Reference PyTorch implementation and models for DINOv3

Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)

Implementation of advantage-weighted regression.

Open-source 3D digital assets for simulation and robot training. Free for non-commercial use.

Official Implementation of RoboCLIP (NeurIPS 2023)

RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉

This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.

[ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"

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

Code for Neural Dynamics Augmented Diffusion Policy, ICRA 2025

PyTorch implementation of YAY Robot

Source code for Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Open-source implementation of AlphaEvolve

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

A final sanity checklist to help your CS paper get accepted, not desk rejected.

[CVPR 2025] RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete. Official Repository.

Pytorch implementation of Evolutionary Policy Optimization, from Wang et al. of the Robotics Institute at Carnegie Mellon University

MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Programmer's guide about how to cook at home.

Lets make video diffusion practical!

Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World | CoRL 2025