Mingxian Lin

Vidu-S1. Vidu S1: A Real-Time Interactive Video Generation Model

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

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

DreamX-World. DreamX-World: A General-Purpose Interactive World Model

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

lingbot-world. Advancing Open-source World Models

UCPE. 📷 [CVPR'26] Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

diamond. DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Orchestra-o1. Official Repository of Orchestra-o1: Omnimodal Agent Orchestration

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

OmniGameArena. OmniGameArena

LongLive. Long Video Gen Infrastructure

AniGen. [SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

OpenSpatial. Python

triattention. TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

SpatialEdit. [Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

GameVerse. GameVerse: Can Vision-Language Models Learn from Video-based Reflection?

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

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

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

open-p2p. Official Repo for paper: Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

NitroGen. A Foundation Model for Generalist Gaming Agents

slime. slime is an LLM post-training framework for RL Scaling.

HumanLift. Code for 'Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement [Siggraph Asia 2025]'

V-ReasonBench. Python

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

JiT. PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Myo-Trainer. Mobicom'25 Artifact Evaluation: Myo-Trainer: A Vision-based Muscle-Aware Motion Feedback System for In-Home Resistance Training

cambrian-s. Cambrian-S: Towards Spatial Supersensing in Video

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

LLM101n. LLM101n: Let's build a Storyteller

QeRL. [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

trl. Train transformer language models with reinforcement learning.

habitat-sim. A flexible, high-performance 3D simulator for Embodied AI research.

habitat-lab. A modular high-level library to train embodied AI agents across a variety of tasks and environments.

anonymous_github. Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

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

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

2D-SpaceEdit. [ICCV 2025 Workshop] This is the official code for the paper "2D Instance Editing in 3D Space"

VGGT-Long. Official implement of VGGT-Long

Skywork-R1V. Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

CUT3R. Official implementation of Continuous 3D Perception Model with Persistent State

transformer. Transformer: PyTorch Implementation of "Attention Is All You Need"

IBSR_jittor. Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

phys-reach-grasp. Python

FramePack. Lets make video diffusion practical!

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

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

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

open-r1. Fully open reproduction of DeepSeek-R1

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

easy-dataset. A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

Visual-RFT. Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

Deformable-Radial-Kernel-Splatting. [CVPR 2025] Code for Deformable Radial Kernel Splatting

finetune-Qwen2-VL. Python

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

Llama3.2-Vision-Finetune. An open-source implementaion for fine-tuning Llama3.2-Vision series by Meta.

Qwen-VL-Series-Finetune. An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

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

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Cradle. The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

metaurban. [ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

thinking-in-space. Official repo and evaluation implementation of VSI-Bench

unrealcv. UnrealCV: Connecting Computer Vision to Unreal Engine

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.

unrealzoo-gym. [ICCV 2025 Highlights] Large-scale photo-realistic virtual worlds for embodied AI

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Depth-Anything-V2. [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

mochi. The best OSS video generation models, created by Genmo

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

generative-models. Generative Models by Stability AI

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

MeshAnything. [ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

dual_quaternions. dual quaternions libraries

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

dex-retargeting. Various retargeting optimizers to translate human hand motion to robot hand motion.

llama3. The official Meta Llama 3 GitHub site

mujoco_menagerie. A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

finalcountdown. Simple countdown applet for Ubuntu

InterScene. [3DV 2024] Official repo of "Synthesizing Physically Plausible Human Motions in 3D Scenes"

TriplaneGaussian. TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

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

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

meshgpt-pytorch. Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

common-3d-test-models. Repository containing common 3D test models in original format with original source if known and obj mesh

human_body_prior. VPoser: Variational Human Pose Prior

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

amass. Data preparation and loader for AMASS

SC-GS. [CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

mesh-gpt. MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

threestudio. A unified framework for 3D content generation.

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

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

MotionCLIP. Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

open_clip. An open source implementation of CLIP.

llama. Inference code for Llama models

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Eureka. Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

CogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型

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

DMRF. Dynamic Mesh-Aware Radiance Fields (ICCV2023): Raytracing rendering and interactive simulating mesh with NeRF

dgrasp. Official code release for CVPR 2022 paper D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions

stable-diffusion.cpp. Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

blender_freestyle_line_drawing. Python

UniDexGrasp. Official code for "UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy" (CVPR 2023)

Machine-Learning-is-ALL-You-Need. 🔥🌟《Machine Learning 格物志》: ML + DL + RL basic codes and notes by sklearn, PyTorch, TensorFlow, Keras & the most important, from scratch!💪 This repository is ALL You Need!

CALM. Python

GAMES-105. Python

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

IsaacGymEnvs. Isaac Gym Reinforcement Learning Environments

FLEX. Code for our CVPR'23 paper - "FLEX: Full-Body Grasping Without Full-Body Grasps"

DeepMimic. Motion imitation with deep reinforcement learning.

SAMP. Stochastic Scene-Aware Motion Prediction https://samp.is.tue.mpg.de/

SinMDM. Single Motion Diffusion Model

polyscope. A C++ & Python viewer for 3D data like meshes and point clouds

NeRF-Texture. [SIGGRAPH 2023, TPAMI 2024] Code for NeRF-Texture: Texture Synthesis with Neural Radiance Fields

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

stable-diffusion-webui. Stable Diffusion web UI

brax. Massively parallel rigidbody physics simulation on accelerator hardware.

Pytorch-Robust-Motion-In-betweening. Reimplementation of robust motion in-betweening

pyphysx. Python Wrapper for Nvidia PhysX simulator.

PhysX. NVIDIA PhysX SDK

researchgpt. A LLM based research assistant that allows you to have a conversation with a research paper

BingGPT. Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

FreeNeRF. [CVPR23] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

video-diffusion-pytorch. Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

WeChatExtension-ForMac. A plugin for Mac WeChat

TaskMatrix. Python

ChatGPT-Shortcut. 🚀💪Maximize your efficiency and productivity. The ultimate hub to manage, customize, and share prompts. (English/中文/Español/العربية). 让生产力加倍的 AI 快捷指令。更高效地管理提示词，在分享社区中发现适用于不同场景的灵感。

powerlevel10k. A Zsh theme

pix2pix3D. pix2pix3D: Generating 3D Objects from 2D User Inputs

Palette-Image-to-Image-Diffusion-Models. Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

ControlNet. Let us control diffusion models!

SinDDM. Official pytorch implementation of the paper: "SinDDM: A Single Image Denoising Diffusion Model"

Diffusion-Models-pytorch. Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

non-stationary_texture_syn. Code used for texture synthesis using GAN

PyMeshLab. The open source mesh processing python library

DirectVoxGO. Direct voxel grid optimization for fast radiance field reconstruction.

SceneDreamer. [TPAMI 2023] SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

sdf. Simple SDF mesh generation in Python

NeRFFaceEditing. [SIGGRAPH Asia'22][TPAMI '25] NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields

ucasproposal. LaTeX Proposal Template for the University of Chinese Academy of Sciences

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Models in PyTorch

DREDS. [ECCV 2022] Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects

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

cubvh. Mesh tools.

instant-nsr-pl. Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

NeuS. Code release for NeuS

Deformation-Transfer-for-Triangle-Meshes. Reproduction of the paper "Deformation Transfer for Triangle Meshes" of Robert W.Sumner et al.

NeuMesh. Code for "MeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing", ECCV 2022 Oral

sige. [NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

HFS. HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022)

guided-diffusion. Python

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

stable-diffusion. A latent text-to-image diffusion model

nerfacc. A General NeRF Acceleration Toolbox in PyTorch.

nvdiffrecmc. Official code for the NeurIPS 2022 paper "Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising".

pywt. PyWavelets - Wavelet Transforms in Python

diffsim. Scalable Differentiable Physics for Learning and Control (ICML2020)

nerfplusplus. improves over nerf in 360 capture of unbounded scenes

nerf-factory. An awesome PyTorch NeRF library

sdf. Parallelized triangle mesh --> continuous signed distance field on CPU

stylegan3-editing. Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" (AIM ECCVW 2022) https://arxiv.org/abs/2201.13433

nvdiffrec. Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

BungeeNeRF. [ECCV22] BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering

NeuRIS. Python

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

CubicStylization_Cpp. C++

OccludedPASCAL3D. The OccludedPASCAL3D+ is a dataset generated via superimposing occluder to PASCAL3D+ dataset for multiple computer vision tasks.

Mask2Former. Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

AvatarCLIP. [SIGGRAPH 2022 Journal Track] AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

UNIST. Pytorch Implementation of "UNIST: Unpaired Neural Implicit Shape Translation Network", CVPR 2022

ARF-svox2. Artistic Radiance Fields

libigl-tutorial-data. Data for libigl tutorial

quartet. A tetrahedral mesh generator that does isosurface stuffing with an acute tetrahedral tile.

Mac-Tips. Mac 软件和使用技巧整理，发掘Mac快捷键、技巧和工具，不做多选，只做单选！

libigl-python-bindings. libigl python bindings

Tutorial-on-PhD-Application. Tutorial on PhD Application

TetWild. Robust Tetrahedral Meshing in the Wild.

IRON. Inverse rendering by optimizing neural SDF and materials from photometric images

MeshUDF. Fast and Differentiable Meshing of Unsigned Distance Field Networks

GPU-Marching-Cubes. A GPU implementation of the Marching Cubes algorithm for extracting surfaces from volumes using OpenCL and OpenGL

v-hacd. Automatically exported from code.google.com/p/v-hacd

3PSDF. Python

ViP. Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers

spaghetti. Python

JNeRF. JNeRF is a NeRF benchmark based on Jittor. JNeRF re-implemented instant-ngp and achieved same performance with original paper.

CoACD. [SIGGRAPH2022] Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search

CAPRI-Net. Code for CAPRI-Net