A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

Scenic: A Jax Library for Computer Vision Research and Beyond

PyTorch implementations of deep reinforcement learning algorithms and environments

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

A curated list of awesome C frameworks, libraries, resources and other shiny things. Inspired by all the other awesome-... projects out there.

Truly independent web browser

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Template repo for building and publishing Docker images (and using them on an HPC cluster with Singularity)

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Code of the paper "OmniJet-α: The first cross-task foundation model for particle physics" (https://arxiv.org/abs/2403.05618).

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Benchmarking tools for Python

Details for the Science4Cast competition

A simple interface to GPIO devices with Raspberry Pi

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

A new markup-based typesetting system that is powerful and easy to learn.

🏡 Open source home automation that puts local control and privacy first.

C++ framework for embedded programming on top of Espressif's ESP-IDF.

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

TensorFlow Lite Micro for Espressif Chipsets

Espressif Audio Development Framework

Espressif deep-learning library for AIoT applications

MicroPython - a lean and efficient Python implementation for microcontrollers and constrained systems

a simple and scalable agent for training adaptive policies with sequence-based RL

Implementation of strong types in C++

CalEPD is an Epaper component driver for the ESP-IDF framework with GFX and font support, optional touch interface, compatible with ESP32 / S2 / S3 / C3

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Machine Learning Engineering Open Book

The Art of Debugging