Starred repositories
We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.
Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforceme…
Efficient vision foundation models for high-resolution generation and perception.
A lightweight suite of motion imitation methods for training controllers.
[SIGGRAPH Asia 2025] Implementation of "StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data"
[T-RO 2025] Code for Autonomous Robust Manipulation via Optimization with Uncertainty-aware Reachability
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
A large-scale benchmark and learning environment.
🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation
Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills"
[CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
GRADE: Generating Animated Dynamic Environments for Robotics Research
PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）
A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.
Data collection, saving and publishing code for ARIO dataset. Collect multi-sensor rostopic data and store it in a specific structure.
[RSS 2025 Best Systems Paper Finalist] 💐Official implementation of "Learning Humanoid Standing-up Control across Diverse Postures"
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
MAGI-1: Autoregressive Video Generation at Scale
[Actively Maintained🔥] A list of Embodied AI papers accepted by top conferences (ICLR, NeurIPS, ICML, RSS, CoRL, ICRA, IROS, CVPR, ICCV, ECCV).
[AAAI 2026] OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
Official repository for "AM-RADIO: Reduce All Domains Into One"
Minimal reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
Affordance-based Robot Manipulation with Flow Matching
[CVPR 2023] Query-Centric Trajectory Prediction
[CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.