A framework for large scale recommendation algorithms.

基于Python的开源量化交易平台开发框架

Official repository for Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation. (DINOv3)

Run frontier AI locally.

Implement a reasoning LLM in PyTorch from scratch, step by step

A very simple GRPO implement for reproducing r1-like LLM thinking.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

This repository provides a 3D implementation of DINOv2 for self-supervised pretraining on volumetric (3D) medical images using Lightly, MONAI, and Pytorch Lightning!

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

MONAI Tutorials

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

一些奇思妙想，使用大语言模型制作各种小应用

Fully open reproduction of DeepSeek-R1

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

🤗 smolagents: a barebones library for agents that think in code.

The python library for real-time communication

LLMs-from-scratch项目中文翻译

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

A fundamental toolkit designed for music, song, and audio generation

Reference PyTorch implementation and models for DINOv3

CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages [ACL 2025]

Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.

All-In-One Music Structure Analyzer

[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

A curated list of recent diffusion models for video generation, editing, and various other applications.

Text-audio foundation model from Boson AI

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…