Qing Shuai

lingbot-world-v2. Infinite Worlds with Versatile Interactions

lingbot-video. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

EdgeBench. EdgeBench: Unveiling scaling laws of learning from real-world environments

gzh-design-skill. 把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

DanceOPD. 🔥 DanceOPD: On-Policy Generative Field Distillation

video_to_data. Nvidia Isaac Video to Data Pipeline

DeepSpec. DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

figures4papers. My Python scripts to make high-quality figures for publications in top AI conferences and journals.

orange-line-illustration. 🍊 New Yorker-style minimalist editorial illustration skill for AI agents — one idea, one accent, lots of silence. Free for open-source use; commercial license for closed-source.

3dcodebench. Benchmarking Agentic Procedural 3D Modeling Via Code

codegraph. Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

GRAIL. A digital data-generation pipeline that synthesizes humanoid loco-manipulation data from 3D assets and video priors.

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

Code-as-Room. A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.

Nova3D. Editable, part-aware 3D generation from text or reference images. Open-source client for nova3d.xyz.

forgent3d. Using AI to generate 3D models

learning-beyond-gradients. Heuristic Learning Blog Post

text-to-cad. A collection of agent skills for CAD, robotics and hardware design

cadquery. A python parametric CAD scripting framework based on OCCT

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

articraft. An Agentic System for Scalable Articulated 3D Asset Generation

vggt-omega. [CVPR 2026 Oral] VGGT Omega

Pixal3D. [SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

Awesome-WAM. A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

whole_body_tracking. Python

PhysForge. [ICML 2026] PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

Claude-Code-Game-Studios. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Kami. 👩‍🚒 Good content deserves good paper.

VIGA. VIGA: Vision-as-Inverse-Graphics Agent

ai4animationpy. A Python framework for AI-driven character animation using neural networks.

sapiens2. 1K resolution vision transformers pretrained on 1B human images.

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

lyra. Project Lyra: Open Generative 3D World Models

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Awesome-RL-for-Video-Generation. A curated list of papers on reinforcement learning for video generation

CopyAnySkill. 一键复制任意skill，自动跟踪同步更新。

auto-deep-researcher-24x7. 🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

multica. The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

1566. 从嘉靖帝学习的极简主义Agent团队管理，免去上朝和微操

ai-tools. AI通用工具

LATENT. Official implementation of Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

Fast-SAM-3D-Body. [ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery

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

AutoResearchClaw. Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

autodebug. 自动循环debug的skill

exa-mcp-server. Exa MCP for web search and web crawling!

autoresearch. AI agents running research on single-GPU nanochat training automatically

Skill-Research-Rebuttal.

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

Research-Paper-Writing-Skills. Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.

CARI4D. [CVPR 2026] CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

Skill-Research-Figure. 用来画专业学术论文tikz图和手绘风格SVG图的Claude Code Skills

skills. Public repository for Agent Skills

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

Vibe3DScene. Create your own 3D scene with words anywhere.

planning-with-files. Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

nanobot. Lightweight, open-source AI agent for your tools, chats, and workflows.

HY3D-Bench. Python

GigaHands. [CVPR 2025] GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities

Gen2Humanoid. Python

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AI-Research-SKILLs. Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

hoifhli_release. Python

vibetensor. Our first fully AI generated deep learning system

InfiniDepth. [CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

UniVideo. [ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos

wxbackup. 微备份是一款面向NAS的微信备份/恢复工具(付费)，支持鸿蒙/苹果/安卓微信数据备份至NAS，亦可从NAS恢复至鸿蒙/苹果/安卓微信，实现长期保存与随时查看数据。支持全量/增量备份、全量/部分恢复。❶保持8011、24011、9014、20360~20367这些端口不被占用且不被防火墙限制。❷如遇问题，可在【帮助-查看教程】或【WxBackup GitHub】查阅。

banana-slides. 一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

HY-Motion-1.0. HY-Motion model for 3D human motion or 3D character animation generation.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Wan-Move. [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Depth-Anything-3. Depth Anything 3

sam-3d-body. The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.

ViMoGen. [ICLR 2026] Official Code for "the Quest for Generalizable Motion Generation: Data, Model, and Evaluation"

anny. Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.

realtime-video. Krea Realtime 14B. An open-source realtime AI video model.

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

dlp3d.ai. Open-source Autonomous 3D Characters on the Web

Emu3.5. Native Multimodal Models are World Learners

SyncHuman. [NeurIPS 2025]SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.

AICGSecEval. A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

AI-Infra-Guard. A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

DepthLM_Official. [ICLR 2026 Oral (top 1.2%)] Official implementation of DepthLM

DeepSeek-OCR. Contexts Optical Compression

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

map-anything. MapAnything: Universal Feed-Forward Metric 3D Reconstruction

HuMo. HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

TexVerse. Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

VeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

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

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

FastVideo. A unified inference and post-training framework for accelerated video generation.

MixGRPO. [ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

ddpo-pytorch. DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support

flow_grpo. [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

xrtailor. OpenXRLab GPU Cloth Simulation Engine

MotionMillion-Codes. Python

MotionGPT3. MotionGPT3: Human Motion as a Second Modality, a MoT-based framework for unified motion understanding and generation

SpaTrackerV2. [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

PartPacker. Efficient Part-level 3D Object Generation via Dual Volume Packing

MultiTalk. [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

HSMR. [CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

xrfeitoria. OpenXRLab Synthetic Data Rendering Toolbox

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

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

AniMo. [CVPR2025] "AniMo: Species-Aware Model for Text-Driven Animal Motion Generation"

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

efficient-motion-reconstruction. code for our Siggraph Asia Motion Reconstruction Paper

pixel3dmm. [Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

RoboMaster. [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control

IDOL. IDOL: Instant Photorealistic 3D Human Creation from a Single Image. An open-source project for fast, high-fidelity, and generalizable 3D human reconstruction from a single image.

HunyuanCustom. HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Seed1.5-VL. Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

AutoKeyframe. [SIGGRAPH 2025] AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing

PrimitiveAnything. [SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

Awesome-Human-Motion. An aggregation of human motion understanding research.

MVHumanNet_plusplus. Python

awesome-gpt4o-images. Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.

FramePack. Lets make video diffusion practical!

HoloPart. HoloPart: Generative 3D Part Amodal Segmentation

character-dna-addon. Imports MetaHuman head and body components into Blender from a their DNA files, lets you customize them, then send them back to MetaHuman Creator.

272-dim-Motion-Representation. The modified 272-dimensional motion representation processing script.

Unimotion. Pytorch implementation of Unimotion: Unifying 3D Human Motion Synthesis and Understanding.

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

RelativePose. Python

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

ready_to_react. [ICLR 2025] Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation

MagicArticulate. [CVPR 2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”

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

edm2. EDM2 and Autoguidance -- Official PyTorch implementation

edm. Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Semantic-Gesticulator-Official. Python

VersatileMotion. Official pytorch implementation of VersatileMotion based on MMEngine

F5-TTS. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

DeepSeek-R1.

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

MotionLCM. [ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

GameFactory. [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

lac. 百度NLP：分词，词性标注，命名实体识别，词重要性

SystemAnimatorOnline. XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online

MatchAnything. Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

JOSH. [ICLR 2026] Official Implementation for Paper "Joint Optimization for 4D Human-Scene Reconstruction in the Wild"

aeneas. aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

gentle. gentle forced aligner

Montreal-Forced-Aligner. Command line utility for forced alignment using Kaldi

mar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

ai-game-devtools. Your AI Game Dev Hub. The ultimate resource hub for AI-powered game development tools. Discover cutting-edge LLMs, World Model, Agent, Code, Image, Texture, Shader, 3D Model, Animation, Video, Audio, Music, Singing Voice and Analytics. 🔥

Chinese-BERT-wwm. Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

LMM. Large Motion Model for Unified Multi-Modal Motion Generation

DeepSeek-V3. Python

DiTCtrl. [CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

stmc. Implementation of "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation" from CVPR Workshop on Human Motion Generation 2024.

GaussianSpeech. [ICCV 2025] GaussianSpeech: Audio-Driven Gaussian Avatars

diffusion-motion-inbetweening. The official implementation of Flexible Motion In-betweening with Diffusion Models, SIGGRAPH 2024

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

AnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

Gesture-Generation-from-Trimodal-Context. Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity (SIGGRAPH Asia 2020)

markitdown. Python tool for converting files and office documents to Markdown.

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

Motion-2-to-3. Code for "Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation", ICCV 2025

SynCamMaster. [ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

StableAnimator. [CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

mv-extractor. Extract frames and motion vectors from H.264 and MPEG-4 encoded video.

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

motionfix. MotionFix: Text-Driven 3D Human Motion Editing [SIGGRAPH ASIA 2024]

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

LLaMA-Mesh. Unifying 3D Mesh Generation with Language Models

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

AnimateDiff. Official implementation of AnimateDiff.

flame-head-tracker. FLAME head tracker for single image reconstruction and monocular video tracking. [Note: This tracker operates offline and is not intended for real-time applications.]

MotionClone. [ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Hunyuan3D-1. Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

smplfitter. The Fast Way From Vertices to Parametric 3D Humans

Awesome-Human-Motion-Video-Generation. 【Accepted by TPAMI】Human Motion Video Generation: A Survey (https://ieeexplore.ieee.org/document/11106267)

joker. Official Code Base of the Paper: "Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions"

diffusion-e2e-ft. [WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

spann3r. [3DV'25 Award Candidate] 3D Reconstruction with Spatial Memory

ViewCrafter. [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

VHAP. A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.

EMOPortraits. Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

PuzzleAvatar. [SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

GVHMR. Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026

ViViD. ViViD: Video Virtual Try-on using Diffusion Models

Portrait-4D. Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 24); Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer (ECCV 2024)

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

MagicMan. Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"

sapiens. High-resolution models for human tasks.

youtube-gesture-dataset. This repository contains scripts to build Youtube Gesture Dataset.

MotionFollower. [ICCV2025] MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion

One-Shot_Free-View_Neural_Talking_Head_Synthesis. Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

TalkSHOW. This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].