[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Low overhead tracing library and trace visualizer for pipelined CUDA kernels

React + Dear ImGui + Static Hermes

simple immediate lightweight tensors

Truly independent web browser

A character-level discrete diffusion transformer trained on Tiny Shakespeare

code release for HouseCrafter (ICCV 2025 Highlight)

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection, AAAI 25

Contexts Optical Compression

Public repository for Skills

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

[SIGGGRAPHASIA2025] PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

A Dynamic-Aware LIO Framework Via Spatio-Temporal Normal Analysis

MapLibre Native - Interactive vector tile maps for iOS, Android and other platforms.

JavaScript/TypeScript-native, low-boilerplate, object-capability RPC system

A procedural Blender pipeline for photorealistic training image generation

Preprocess Audio for training

An easy to understand TTS / SVS / SVC framework

A solution to visualize and explore 3D models in your browser.

DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registration

Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and m…

Official repository for the paper "Orientation Matters: Making 3D Generative Models Orientation-Aligned" (NeurIPS 2025)

The open-source CapCut alternative

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.