Juze Zhang

aloha4franka. CAD files, ROS2 descriptions, and packages to use the aloha gripper on the FR3/Panda of Franka Robotics or any other cobot.

HOIM3_Toolbox. Python

language_of_motion. This repository contains the official implementation of "The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion".

Humanoid-GPT. [CVPR 2026] Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

HoloMotion. HoloMotion: A Foundation Model for Whole-Body Humanoid Control

bolei_awesome_posters. CVPR and NeurIPS poster examples and templates

Awesome-World-Model-for-Robotics-Policy.

embodied-ai-start. [PKU EPIC Lab] 面向小白的具身智能入门指南

lerobot_franka_teleop. A teleoperation framework with joint-level master-slave isomorphic mapping and end-effector pose teleoperation for Franka Research 3, built on LeRobot.

ufactory_teleop. Teleoperation solutions for UFACTORY robotic arms like Lite 6, xArm 5/6/7 and 850

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

EgoVerse. EgoVerse: Egocentric Data for Robot Learning from Around the World

SOMA-X. SOMA: Unifying Parametric Human Body Models

KungFuAthleteBot. A highly dynamic martial arts motion dataset (848 samples, Ground/Jump subsets) for humanoid robots, with GMR retargeting, height adjustment, and RL training pipeline (PPO & FastSAC) for Unitree G1, featuring fall recovery and sim-to-real deployment.

ACG. Code for "ACG: Action Coherence Guidance for Flow-based Vision-Language-Action Models" (ICRA 2026)

seamless_interaction. Foundation Models and Data for Human-Human and Human-AI interactions.

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

BitDance. BitDance & UniWeTok: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.

vla-scratch. Python

oat. [RSS 2026] Ordered Action Tokenization

AnyCam2Ros. Turn any camera (Insta360, RealSense, USB webcam, etc.) into ROS2 image topics. Unified config for VLA deployment and SFT data collection.

reBot-DevArm. Open Source Robotic Arm for All Developers

Panthera-HT_Main. Introduction to the Panthera-HT robotic arm

video2tasks. Video2Tasks: Split multi-task robot videos into single-task segments with auto-generated instruction labels for VLA (pi0, OpenVLA) training

launch-agent-skills. Python

FrankenMotion-Code. [CVPR 2026] FrankenMotion: Part-level Human Motion Generation and Composition

tianshou. An elegant PyTorch deep reinforcement learning library.

agent-skills. Vercel's official collection of agent skills

ViBES. This repository contains the official implementation of "ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body".

LiveTalk. Python

TienKung-Lab. Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots

Fun-Audio-Chat. Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.

VQ-VLA. The offical repo for paper "VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers" (ICCV 2025)

MoLingo. [ CVPR 2026 ] MoLingo: Motion-Language Alignment for Text-to-Motion Generation

mental_health_in_your_words. Mental Health in Your Words: Data-Efficient Anxiety and Depression Screening with Large Language Models

video2robot. End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions

vibe-coding-cn. Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

Latex-Slides-Template-GenAI. A modern, clean LaTeX Beamer presentation template with a sleek design inspired by keynote presentations.

NEO. NEO Series: Native Vision-Language Models from First Principles

3DGen-Playground. 3D generation made easy!

sam-3d-objects. SAM 3D Objects

GENMO. Python

UniMoCap. [Open-source Project] UniMoCap: community implementation to unify the text-motion datasets (HumanML3D, KIT-ML, and BABEL) and whole-body motion dataset (Motion-X).

kalibr. The Kalibr visual-inertial calibration toolbox

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

LiveTalking. Real time interactive streaming digital human

ten-framework. Open-source framework for conversational voice AI agents

Xsens_MTw_XDA_Receive. receive and record data from multiple Xsens MTw Awinda wireless motion trackers

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

marin. Open-source framework for the research and development of foundation models.

WeClone. 🚀 One-stop solution for creating your AI twin from chat history 💡 Fine-tune LLMs with your chat logs to capture your unique style, then bind to a chatbot to bring your digital self to life.

llama.cpp. LLM inference in C/C++

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

CleanS2S. High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

awesome-foundation-agents. About Awesome things towards foundation agents. Papers / Repos / Blogs / ...

SignAvatars. (ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

mink. Python inverse kinematics based on MuJoCo.

TokenHSI. [CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

SpatialLM. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

DiffPoseTalk. DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

OpenManus. No fortress, purely open ground. OpenManus is Coming.

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

moma-1.0. Python

HumanML3D. HumanML3D: A large and diverse 3d human motion-language dataset.

ai-for-grant-writing. A curated list of resources for using LLMs to develop more competitive grant applications.

Show-o. [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

TurboT5. Truly flash T5 realization!

vision-agent. This tool has been deprecated. Use Agentic Document Extraction instead.

AI4Animation. Bringing Characters to Life with Computer Brains in Unity

MoConVQ. C++

paper-reading. 深度学习经典、新论文逐段精读

learning_research. 本人的科研经验

multi-hmr. Pytorch demo code and models for Multi-HMR

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

RVH_Mesh_Registration. Code to fit SMPL model to scans

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

curobo. CUDA Accelerated Robot Library

MotionChain. MotionChain: Conversational Motion Controllers via Multimodal Prompts

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

InteractionGraph. Codebase for SIGGRAPH 2023 Paper: Simulation and Retargeting of Complex Multi-Character Interactions

UltraInertialPoser. Official Code for ACM SIGGRAPH 2024 paper "Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging"

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

segment-anything-fast. A batched offline inference oriented version of segment-anything

MvObjectFitting. A basis version of multi-view object's pose fitting code

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

CloseMoCap. Official implementation of "Reconstructing Close Human Interaction from Multiple Views"

xtuner. A Next-Generation Training Engine Built for Ultra-Large MoE Models

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

IMHD-Dataset. [CVPR 2024] Official repository of paper "I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions".

NeuralDome_Toolbox. Official Dataset Toolbox of the paper "[CVPR 2023]NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions" and "[CVPR2024]HOI-M3: Capture Multiple Humans and Objects Interaction within Contextual Environment"

freemocap. Free Motion Capture for Everyone 💀✨

nerfies.github.io. JavaScript

Dataset-of-Artefact-Aware-Human-Motion-Capture-using-Inertial-Sensors-Integrated-into-Loose-Clothing. Dataset of Artefact Aware Human Motion Capture using Inertial Sensors Integrated into Loose Clothing

InterDiff. [ICCV 2023] Official PyTorch implementation of the paper "InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion"

RobustCap. Code for our SIGGRAPH ASIA 2023 paper "Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture".

LLM-groundedDiffusion. LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)

egoego_release. Official Implementation of the Paper: Ego-Body Pose Estimation via Ego-Head Pose Estimation (CVPR 2023 Award Candidate)

4d_association. Fork of https://github.com/zhangyux15/4d_association

MvSMPLfitting. A multi-view SMPL fitting based on smplify-x

sdfstudio. A Unified Framework for Surface Reconstruction

aot-benchmark. An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

Segment-and-Track-Anything. An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

IKOL. [AAAI 2023] Official PyTorch implementation of the paper "IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation"

xrmocap. OpenXRLab Multi-view Motion Capture Toolbox and Benchmark

COAP. [CVPR'22] COAP: Learning Compositional Occupancy of People

PATImageReconstruction. Matlab codes for PAT image reconstruction from subsampled data based on a novel regularisation term (Hessian Schatten-norm of the filtered image by Gaussian function), using k-Wave Matlab toolbox, FISTA and ADMM algorithm