AI 开源项目榜。

PyTorch实现高分遥感语义分割（地物分类）

A rapid prompt app development framework based on GPT

resources about federated learning and privacy in machine learning

Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE

200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns.

TernausNetV2: Fully Convolutional Network for Instance Segmentation

OpenAI-powered semantic search for any YouTube playlist – featuring the All-In Podcast. 💪

Image Segmentation framework based on Tensorflow and TF-Slim library

实时互动的GPT数字人技术笔记，不是数字人开源项目

A Machine Learning System for Data Enrichment.

BERT for Multitask Learning

KohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.

Mengzi Pretrained Models

Multi-Objective Reinforcement Learning algorithms implementations.

Interesting LLM projects that I created for my YouTube channel using Ollama's open-source models.

[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

MiVOLO age & gender transformer neural network

AWS Generative AI CDK Constructs are sample implementations of AWS CDK for common generative AI patterns.

It's like Claude Code + Linear + GitHub PR

Reverse engineered Linux driver for the Apple Neural Engine (ANE).

APPS: Automated Programming Progress Standard (NeurIPS 2021)

Semantic3D segmentation with Open3D and PointNet++

Awesome things about domain generalization, including papers, code, etc.

Implementation code of the paper: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction, NeurIPS 2018

Music recommender using deep learning with Keras and TensorFlow

Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation

[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning