Dexbotic: Open-Source Vision-Language-Action Toolbox

Code Release for floq: Training Critics via Flow-Matching for Scaling Compute In Value-Based RL

Official implementation of the paper "GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation"

The official implementation of "Dual Goal Representations"

Robot kinematics implemented in pytorch

Training framework for Large Behavioral Models

Official Code for "Relative Entropy Pathwise Policy Optimization"

Reference PyTorch implementation and models for DINOv3

Synchronized Curriculum Learning for RL Agents

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

A curated awesome list of lists of interview questions. Feel free to contribute! 🎓

Papers from the computer science community to read and discuss.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Collection of reinforcement learning algorithms

Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Robotics research demonstrating reliability and robustness in the real world (continuously updated)

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

🔥Highlighting the top ML papers every week.

Open-source implementation of AlphaEvolve

The official implementation of "Horizon Reduction Makes RL Scalable"

A Python library for dynamic dispatch based on module versions and backends.

Implementation of the world model architecture for self driving out of Wayve

Implementation of Amplify, Actionless Motion Priors for Robot Learning from Videos

Judo: a hackable sampling-based MPC toolbox

Implementation of Denoising Diffusion Probabilistic Model in Pytorch