Zhengyi "Zen" Luo

newton. An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

ProtoMotions. ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

slack-mcp-server. The most powerful MCP Slack Server with no permission requirements, Apps support, GovSlack, DMs, Group DMs and smart history fetch logic.

crosspoint-reader. Firmware for the Xteink X3 and X4 e-readers

kimodo. Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

SOMA-X. SOMA: Unifying Parametric Human Body Models

soma-retargeter. SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

epub-reader-g2. EPUB reader for Even Realities G2 smart glasses

robocasa. RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

BFM-Zero. BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

InstinctLab. Python

robot_viewer. JavaScript

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

alfred-noteplan-quick-capture. Alfred Workflow to quickly capture notes and tasks in NotePlan

holosoma. Python

MimicKit. A lightweight suite of motion imitation methods for training controllers.

mjlab. Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

viser. Web-based 3D visualization in Python

motion_tracking_controller. C++

GMR. [ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

active-adaptation. Python

whole_body_tracking. Python

Muon. Muon is an optimizer for hidden layers in neural networks

LeggedLab. Direct IsaacLab Workflow for Legged Robots

InterMimic. [CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

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

PBHC. Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills"

OpenHomie. Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

ASAP. [RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

umi-on-legs.github.io. JavaScript

RoboVerse. RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

trl. Train transformer language models with reinforcement learning.

uv. An extremely fast Python package and project manager, written in Rust.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

exorl. ExORL: Exploratory Data for Offline Reinforcement Learning

nerfies.github.io. JavaScript

HOVER. HOVER

InternUtopia. A simulation platform for versatile Embodied AI research and developments.

scene_synthesizer. Python package to create manipulation scenes.

webots. Webots Robot Simulator

mujoco_playground. An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

tianshou. An elegant PyTorch deep reinforcement learning library.

PufferLib. Puffing up reinforcement learning

humenv. HumEnv is an SMPL humanoid environment enabling systematic model comparison and reproducibility

metamotivo. The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

metrx. A library containing a collection of distance and similarity measures for data analysis

unitree_mujoco. C++

CLoSD. CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

dklab_realsync. dkLab RealSync: replicate developer's files over SSH in realtime

rl_games. RL implementations

minimal-stable-PPO. A minimal and stable PPO.

near. Imitation Learning from Observation Through Generative Modelling

OmniIsaacGymEnvs. Reinforcement Learning Environments for Omniverse Isaac Gym

lecture-notebooks. Jupyter Notebook

human2humanoid. [IROS 2024] Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation. [CoRL 2024] OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning

scalingup. [CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down

dial-mpc. Official implementation for the paper "Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing". DIAL-MPC is a novel sampling-based MPC framework for legged robot full-order torque-level control with both precision and agility in a training-free manner.

ParaHome. Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions

SkillMimic. [CVPR 2025 Highlight] SkillMimic: Learning Basketball Interaction Skills from Demonstrations

ksim-legacy. MuJoCo simulation code

rfcl. (ICLR 2024) Reverse Forward Curriculum Learning

PHC. Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

BodyTransformer. Body Transformer: Leveraging Robot Embodiment for Policy Learning

ManiSkill. Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

mink. Python inverse kinematics based on MuJoCo.

unitree_rl_gym. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

hitchhiking-rotations. Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024

dm_control. Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

SMPLOlympics. Python

SMPL2AddBiomechanics. Enable inputting a SMPL sequence into AddBiomechanics to fit an OpenSim skeleton model to the sequence.

ddpo. Code for the paper "Training Diffusion Models with Reinforcement Learning"

momentum. A library for human kinematic motion and numerical optimization solvers to apply human motion

omomo_release. Official Implementation of the Paper: Object Motion Guided Human Motion Synthesis (SIGGRAPH Asia 2023 (TOG))

TCDM. Code release for "Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps"

pykan. Kolmogorov Arnold Networks

bps_torch. A Pytorch implementation of the bps code using chamfer distance on GPU

bps. Efficient Learning on Point Clouds with Basis Point Sets

phys-fullbody-grasp. Physically Plausible Full-Body Hand-Object Interaction Synthesis

OC_SORT. [CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Inter-X. [CVPR 2024] Official implementation of the paper "Towards Versatile Human-Human Interaction Analysis"

DeepSDF_OakInk. Python

FoundationPose. [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

fld. Repository for our paper: FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning, Proceedings of the 12th International Conference on Learning Representations (ICLR)

UniDexGrasp2. UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning

PacerPlus. Official implementation of the paper "PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios" (CVPR 2024).

mujoco_wasm. Simulate and Render MuJoCo Models in the Browser!

onnx. Open standard for machine learning interoperability

WHAM. Python

paper.js. The Swiss Army Knife of Vector Graphics Scripting – Scriptographer ported to JavaScript and the browser, using HTML5 Canvas. Created by @lehni & @puckey

mujoco_mpc. Real-time behaviour synthesis with MuJoCo, using Predictive Control

arctic. [CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

MMVR. Repository for the SCA 2022 paper "Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices"

metrabs. Estimate absolute 3D human poses from RGB images.

IsaacLab. Unified framework for robot learning built on NVIDIA Isaac Sim

vid2player3d. Official implementation for SIGGRAPH 2023 paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"

IsaacGymEnvs. Isaac Gym Reinforcement Learning Environments

OneEuroFilter. Simple Python and Julia implementations of the 1€ Filter. The codes can be used as a pseudocode for implementing the algorithm in other languages.

depRL. Repository for our ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

tonic. Tonic RL library

PoseFormer. The project is an official implementation of our paper "3D Human Pose Estimation with Spatial and Temporal Transformers".

pydreamer. PyTorch implementation of DreamerV2 model-based RL algorithm

dreamerv2. Mastering Atari with Discrete World Models

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"

PhysHOI. [Technical Report 2023] PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction

rsl_rl. A fast and simple implementation of learning algorithms for robotics.

TMR. Official PyTorch implementation of the paper "TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis" ICCV 2023

hamer. HaMeR: Reconstructing Hands in 3D with Transformers

DeepMimic. Motion imitation with deep reinforcement learning.

myo_sim. Musculoskeletal Models in MuJoCo

loco-mujoco. Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

pacer. Official implementation of PACER, Pedestrian Animation ControllER, of CVPR 2023 paper: "Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion".

RoboGen. A generative and self-guided robotic agent that endlessly propose and master new skills.

grounded-intuition-gpt-vision. Resources for Grounded Intuition of GPT-Vision's Abilities with Scientific Images

Motion-X. [NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

UHC. Official Implementation of the Universal Humanoid Controller in Mujoco. Supports Kinpoly (NeurIPS 2021) and EmbodiedPose (NeurIPS 2022).

egohumans. [ICCV, 2023] Multiple humans in 3D captured by dynamic and static cameras in 4K.

CALM. Python

TM2T. Official implementation of "TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts (ECCV2022)"

motion-latent-diffusion. [CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model

differentiable-blocksworld. [NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

UnrealEgo. The official implementation of our ECCV 2022 paper, "UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture".

T2M-GPT. (CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”

siMLPe. A Simple Baseline for Human Motion Prediction

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

diffmimic. [ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

PoseGPT. Python

AGRoL. Code release for "Avatars Grow Legs Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model", CVPR 2023

geoopt. Riemannian Adaptive Optimization Methods with pytorch optim

warp. A Python framework for GPU-accelerated simulation, robotics, and machine learning.

adv_param_pose_prior. Adversarial Parametric Pose Prior

segment-anything. 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.

smpl2bvh. This repository contains an example script to convert from a SMPL model to a bvh file.

robopianist. [CoRL '23] Dexterous piano playing with deep reinforcement learning.

aitviewer. A set of tools to visualize and interact with sequences of 3D data.

HybrIK. Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

transformer-inertial-poser. Python implementation accompanying the Transformer Inertial Poser paper at SIGGRAPH Asia 2022

Open3D. Open3D: A Modern Library for 3D Data Processing

EmbodiedPose. Official implementation of NeurIPS 2022 paper: "Embodied Scene-aware Human Pose Estimation".

ASE. Adversarial skill embeddings for training reusable controllers for physically simulated characters.

scenepic. Powerful, easy to use, and portable visualization toolkit for mixed 3D and 2D content

GLAMR. [CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.

ViTPose. The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

Transform2Act. [ICLR 2022 Oral] Official PyTorch Implementation of "Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design".

DCPose. This is an official implementation of our CVPR 2021 paper "Deep Dual Consecutive Network for Human Pose Estimation" (https://openaccess.thecvf.com/content/CVPR2021/papers/Liu_Deep_Dual_Consecutive_Network_for_Human_Pose_Estimation_CVPR_2021_paper.pdf)

planercnn. PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image

PoseTriplet. [CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

autograd. Efficiently computes derivatives of NumPy code.

ProHMR. Repository for "Probabilistic Modeling for Human Mesh Recovery"

neurecon. Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

ZEN. A BERT-based Chinese Text Encoder Enhanced by N-gram Representations

nimblephysics. Nimble: Physics Engine for Biomechanics and Deep Learning

PyTorch-RL. PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

ACTOR. Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021

graf. Official code release for "GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis"

humor. Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

clifs. Contrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP

gradescope-nbgrader. Python

Mujoco-modeler. GUI for adjusting the geometry of Mujoco models

awesome-tips.

imagepacker. Takes a Wavefront OBJ with textures and attempts to squash them into a single texture file.

iOS-ARKit-Headset-View. Make your ARKit experiment compatible with mobile VR/AR headsets*. A Template using SceneKit. Useful for playing with head-worn Mixed Reality, Augmented Reality, Virtual Reality with headtracking, or a mix of everything.

GRAB. GRAB: A Dataset of Whole-Body Human Grasping of Objects

ScaDiver. Project for the paper "A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters"

MEVA. Official implementation of ACCV 2020 paper "3D Human Motion Estimation via Motion Compression and Refinement" (Identical repo to https://github.com/KlabCMU/MEVA, will be kept in sync)

RFC. [NeurIPS 2020] Official PyTorch Implementation of "Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis". NeurIPS 2020.

pigraphs. PiGraphs: Learning Interaction Snapshots from Observations

prox. Resolving 3D Human Pose Ambiguities with 3D Scene Constraints https://prox.is.tue.mpg.de

I2L-MeshNet_RELEASE. Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020

KeypointNet. Jupyter Notebook

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

movienet-tools. Tools for movie and video research

SPIN. Repository for the paper "Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop"

VideoPose3D. Efficient 3D human pose estimation in video using 2D keypoint trajectories

VIBE. Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

tiny-differentiable-simulator. Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

ALAE. [CVPR2020] Adversarial Latent Autoencoders

pytorch-a2c-ppo-acktr-gail. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

EgoPose. [ICCV 2019] Official PyTorch Implementation of "Ego-Pose Estimation and Forecasting as Real-Time PD Control". ICCV 2019.

AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

DenseFusion. "DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion" code repository

Deep_Object_Pose. Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

streameye. A simple MJPEG streamer for Linux

pyyolo. Simple python wrapper for YOLO.

cam2web. Streaming camera to web as MJPEG stream or individual JPEG snapshots. Providing embedded web UI for watching camera directly from a web browser.

stash. StaSh - Shell for Pythonista

CardboardPassthrough. An application that lets you see through the camera while working with cardboard.

android-wearcamera. Remotely control a phone camera with an Android Wear smartwatch

vlc. VLC media player - plays everything, runs anywhere. Code here: https://code.videolan.org/videolan/vlc

Sunshine-Version-2. The official repository for Developing Android Apps