A from-scratch implementation of Denoising Diffusion Probabilistic Models with a focus on probabilistic clarity.

Android app that turns your device into an IP Camera

Reverse engineer how LLMs interpret prompts

AI agents can now use real Android and iOS apps, just like a human.

🟩⬜ Generates a snake game from a github user contributions graph and output a screen capture as animated svg or gif

BharatMLStack is an open-source, end-to-end machine learning infrastructure stack built at Meesho to support real-time and batch ML workloads at Bharat scale

Mobile-Agent: The Powerful GUI Agent Family

The full minitorch student suite.

Ultralytics YOLO 🚀

Fine tune Gemma 3 on an object detection task

Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)

Automatic Let's Encrypt TLS Certificate installation for dokku

ETH Global Agentic Hackathon winner, AI-powered multiverse—where MMORPG meets Web3

Flexible level editor

JavaScript wiki. Focuses mainly on JS/HTML5/WebGL related tech.

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

Object-Detection From Drone Surveillance (VisDrone Dataset)

A lightweight library for portable low-level GPU computation using WebGPU.

A Beautiful and Feature-rich Music & Video Player with Youtube Support, Built in Flutter

A Beautiful and Feature-rich Music & Video Player with Youtube Support, Built in Flutter

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

MARS5 speech model (TTS) from CAMB.AI

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

A list of engineering manager resource links.

A modern, highly customizable, responsive Jekyll template for course websites.

Multi-Layer Key-Value sharing experiments on Pythia models