🚀 Efficient implementations for emerging model architectures

Visualizer for neural network, deep learning and machine learning models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

NanoGPT (124M) in 2 minutes

Google Research

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and…

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

This repository contains code for evaluating video-language models on the Wearable Agent Benchmark along with links to download the dataset files.

Python sample codes and textbook for robotics algorithms.

This is an implementation of the paper "Are We Done with Object-Centric Learning?"

Uniform Manifold Approximation and Projection

Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**

fast_argv

Feedforward neural network learning in real time

A python library for self-supervised learning on images.

Official repository for "AM-RADIO: Reduce All Domains Into One"

Open-Sora: Democratizing Efficient Video Production for All

Memray is a memory profiler for Python

PyTorch code and models for the DINOv2 self-supervised learning method.

Materials for the Computer Vision Methods course at CVUT

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

An open source implementation of CLIP.

Room Impulse Response Generator (Python)

Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library

Official implementation of: "PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning" by Villar-Corrales & Behnke. ICML 2025

Reference PyTorch implementation and models for DINOv3