Yudong Jin

lingbot-world-v2. Infinite Worlds with Versatile Interactions

os-taxonomy. JavaScript

PointSplat. [ECCV 2026] PointSplat: Compact Gaussian Splatting via Human-Centric Prediction

vggt-omega. [CVPR 2026 Oral] VGGT Omega

mutagen. Fast file synchronization and network forwarding for remote development

llm_wiki. LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

ViGeo. ViGeo: Towards Consistent Video Geometry Estimation

cmux. Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

.tmux. Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

GENMO. Python

Syn4D. [ECCV 2026] Syn4D: A Multiview Synthetic 4D Dataset

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

mihomo. A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

youth-engagement-index. R

lingbot-map. A feed-forward 3D foundation model for reconstructing scenes from streaming data

Vista4D. Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

ReImagine. Official implementation of ReImagine

clash-verge-rev. A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

codex. Lightweight coding agent that runs in your terminal

EgoX. Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

4C4D. [CVPR 2026] 4C4D: 4 Camera 4D Gaussian Splatting

Scal3R. [CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

oh-my-codex. OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

Cosmos-Drive-Dreams. Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

reshade. A generic post-processing injector for games and video software.

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

codex-plugin-cc. Use Codex from Claude Code to review code or delegate tasks.

ZipMap. [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

WildWorld. [ECCV 2026] WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

claude-hud. A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

StreamingTalker. Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral

inspatio-world. Python

worldfm. Python

GEM-X. Monocular whole-body 3D human pose estimation using the SOMA body model

MatAnyone2. [CVPR 2026 Highlight] MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

claudian. An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault

impeccable. The design language that makes your AI harness better at design.

LichtFeld-Studio. Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

ghostty-config. A beautiful config generator for Ghostty terminal.

ghostty. 👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

awesome-ai-research-writing. Elevate your AI research writing, no more tedious polishing ✨

claude-code-local-for-vscode. Claude Code VS Code extension patched for Force Local mode — run CLI locally, proxy file ops to remote server via VS Code Remote SSH

AnuPpuccin. Personal theme for Obsidian

easy_ViTPose. Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

hallo3. [CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

WiLoR. WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

CameraHMR. Python

3DiMo. Project page for "3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation"

MV-Performer. [SIGGRAPH Asia 2025] The official repo for the conference paper "MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis".

torchcodec. PyTorch media decoding and encoding

Dyn-HaMR. 🔥(CVPR 2025 Highlight) Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera

lingbot-world. Advancing Open-source World Models

lingbot-depth. Masked Depth Modeling for Spatial Perception

VideoMaMa. Official implementation of "VideoMaMa: Mask-Guided Video Matting via Generative Prior", CVPR 2026

Koala-36M. Official implementation of the paper "Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content".

shadowsocks-rust. A Rust port of shadowsocks

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

PyAV. Pythonic bindings for FFmpeg's libraries.

VerseCrafter. VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

UniSH. Official Codebase for our CVPR 2026 paper UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass

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

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

pngquant. Lossy PNG compressor — pngquant command based on libimagequant library

Spatia. [CVPR2026] Long-horizon, spatially consistent video generation enabled by persistent 3D scene point clouds and dynamic-static disentanglement.

FlashVSR. [CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

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

cap4d. Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

Human3R. [ICLR 2026] An unified model for 4D human-scene reconstruction

diffusion-vas. [CVPR 2025] Official code for Using Diffusion Priors for Video Amodal Segmentation

4D-Humans. 4DHumans: Reconstructing and Tracking Humans with Transformers

starfield.js. An interactive star field background effect with html canvas

particles.js. A lightweight JavaScript library for creating particles

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"

PromptHMR. PromptHMR: Promptable Human Mesh Recovery

Video-Depth-Anything. [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

ml-sharp. Sharp Monocular View Synthesis in Less Than a Second

MHR. Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

zensical. A modern static site generator by the Material for MkDocs team

HunyuanVideo-1.5. HunyuanVideo-1.5: A leading lightweight video generation model

sam-body4d. 🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

Shadowrocket-ADBlock-Rules-Forever. 提供多款 Shadowrocket 规则，拥有强劲的广告过滤功能。每日 8 时重新构建规则。

Light-X. [ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control

LBM. Latent Bridge Matching for Fast Image-to-Image Translation (ICCV 2025 Highlight)

NeuS2. [ICCV 2023] Official code for NeuS2

StrayVisualizer. Visualize Data From Stray Scanner https://keke.dev/blog/2021/03/10/Stray-Scanner.html

One4D. [ECCV 2026] One4D: Unified 4D Generation and Reconstruction

Wan2.2-TI2V-5B-Turbo. 4-steps distilled version of Wan2.2-TI2V-5B

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.

sam3. The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

nerd-fonts. Iconic font aggregator, collection, & patcher. 3,600+ icons, 50+ patched fonts: Hack, Source Code Pro, more. Glyph collections: Font Awesome, Material Design Icons, Octicons, & more

Depth-Anything-3. Depth Anything 3

Flash-Sparse-Attention. 🚀🚀 Efficient implementations of Native Sparse Attention

SageAttention. [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

SpargeAttn. [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

radial-attention. [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

warp. ⚡ Soothing pastel theme for Warp

catppuccin. 😸 Soothing pastel theme for the high-spirited!

PKU-DyMVHumans. [CVPR 2024] DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

PE-Field. Python

LongLive. Long Video Gen Infrastructure

iina. The modern video player for macOS.

decord. An efficient video loader for deep learning with smart shuffling that's super easy to digest

video_reader-rs. A library to fastly decode video with ffmpeg and rust

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

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

OmniWorld. [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

vipe. ViPE: Video Pose Engine for Geometric 3D Perception

GEN3C. [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

lyra. Project Lyra: Open Generative 3D World Models

native-sparse-attention-pytorch. Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

4DGT. [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

GIMM-VFI. [NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation

video2x. A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Practical-RIFE. More practical frame interpolation approach.

frame-interpolation. FILM: Frame Interpolation for Large Motion, In ECCV 2022.

ECCV2022-RIFE. ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

dinov3. Reference PyTorch implementation and models for DINOv3

DWPose. "Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

prope. Cameras as Relative Positional Encoding

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

MoGA. Official code release for ICCV2025 paper (Highlight): MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction

finetrainers. Scalable and memory-optimized training of diffusion models

higgs-audio. Text-audio foundation model from Boson AI

ZeroOmega. Manage and switch between multiple proxies quickly & easily.

SmartProxy. Firefox/Chrome browser extension. SmartProxy will automatically enable/disable proxy for the sites you visit, based on customizable patterns.

supervision. We write your reusable computer vision tools. 💜

sekai-codebase. [NeurIPS 2025] Sekai: A Video Dataset towards World Exploration

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

Diffuman4D. [ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

FLARE. Python

MoVieS. [CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

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

Lumos. [ICLR 2026] Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

AnimatableGaussians. Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

GeometryCrafter. [ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

IC-Light. More relighting!

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

zoxide. A smarter cd command. Supports all major shells.

Rectangle. Move and resize windows on macOS with keyboard shortcuts and snap areas

rerun. Visualize, query, and stream to train on multimodal robotics data.

zju-connect. ZJU RVPN 客户端的 Go 语言实现

Difix3D. [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

HunyuanVideo-Avatar. Python

LTX-Video. Official repository for LTX-Video

mini-splatting. Python

BaiduPCS-Go. iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

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

Academic-project-page-template. A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

docker-easyconnect. 使深信服（Sangfor）开发的非自由的 VPN 软件 EasyConnect 和 aTrust 运行在 docker 或 podman 中，并作为网关和/或提供 socks5、http 代理服务

readest. Readest is a modern, feature-rich ebook reader designed for avid readers offering seamless cross-platform access, powerful tools, and an intuitive interface to elevate your reading experience.

RealisDance. The official implementation of RealisDance

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

supersplat. 3D Gaussian Splat Editor

UniAnimate-DiT. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

pydantic. Data validation using Python type hints

Uni3C. Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]

FramePack. Lets make video diffusion practical!

hydra. Hydra is a framework for elegantly configuring complex applications

DiffSynth-Studio. Enjoy the magic of Diffusion models!

cursor.

brush_avatar. Browser viewer for GaussianAvatars based on Brush

ReCamMaster. [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

stable-virtual-camera. Stable Virtual Camera: Generative View Synthesis with Diffusion Models

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

GAS. [ICCV 2025] GAS: Generative Avatar Synthesis from a Single Image

DepthCrafter. [CVPR 2025 Highlight] DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

LHM. [ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

HunyuanVideo-I2V. HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

joblib. Computing with Python functions.

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

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

TrajectoryCrafter. [ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

fillerbuster. Fillerbuster: Multi-View Scene Completion for Casual Captures

humanrf. Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

pippo. Pippo: High-Resolution Multi-View Humans from a Single Image

cherry-studio. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Human3Diffusion. [NeurIPS 2024] Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models

DeepSeek-R1.

DualGS_Dataset.

ext4fuse. EXT4 implementation for FUSE

RobustVideoMatting. Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

vggsfm. VGGSfM: Visual Geometry Grounded Deep Structure From Motion

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.

pytorch-book. PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

obsidian-image-converter. ⚡️ Convert, compress, resize, annotate, markup, draw, crop, rotate, flip, align images directly in Obsidian. Drag-resize, rename with variables, batch process. WEBP, JPG, PNG, HEIC, TIF.

brush. 3D Reconstruction for all

SMPLer-X. [NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

mmhuman3d. OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

COCO-WholeBody. ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

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

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

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

EnvGS. [CVPR 2025] EnvGS: Modeling View-Dependent Appearance with Environment Gaussian

Sarasa-Gothic. Sarasa Gothic / 更纱黑体 / 更紗黑體 / 更紗ゴシック / 사라사 고딕

MotionCtrl. Official Code for MotionCtrl [SIGGRAPH 2024]

ExAvatar_RELEASE. Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

GaussianAvatars. [CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"