Video stabilization using gyroscope data

AI-powered agents for automating 3D content workflows using Vision-Language Models (VLMs). Content Agents analyze 3D assets and automate material assignment, physics property classification, and te…

Easily dive into different PCB KiCad designs of the most popular microcontroller devboards

Desktop app to manage markdown knowledge bases

[NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

[ECCV 2024] 3D World Model for Autonomous Driving

WebGPU physics engine based on the AVBD solver

Industrial design files for Keychron keyboards and mice. 100+ models with CAD assets in STEP, DXF, DWG, and PDF. Source-available, with commercial use allowed for original compatible accessories wi…

Parametric cad modeling with Javascript

A ~9M parameter LLM that talks like a small fish.

Place to keep various projects related to AI computing

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

[CVPR 2026] Offical implementation of PhysGen: Physically Grounded 3D Shape Generation for Industrial Design

AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.

A replica Game Boy shell made in Autodesk Fusion 360

Emulate Arduino, ESP32 & Raspberry Pi. in your browser. Write code, compile, and run on 19 real boards — Arduino Uno, ESP32, ESP32-C3, Raspberry Pi Pico, Raspberry Pi 3, and more. No hardware, no c…

minimal macOS app switcher for when Cmd+Tab gets way too noisy

Python DSL that compiles element-wise expressions to parallel Rust. All CPU cores, zero serialization.

OpenShell is the safe, private runtime for autonomous AI agents.

A lightweight, open-source, fully local alternative to Logitech Options+ for remapping Logitech HID++ mice.

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Go CLI and library for flashing firmware to Espressif ESP8266 and ESP32-family microcontrollers

Smallest transformer that can add two 10-digit numbers

Files of my DIY ESP32-Gameboy Project

Official repository of HUGS: Human Gaussian Splats (CVPR 2024)

High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.

reading the undocumented mems accelerometer + gyroscope on apple silicon macbooks via iokit hid

CUDA Core Compute Libraries