AI 开源项目榜。

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

Examples and experiments around ML for upcoming Coding Train videos

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

An open-source ML pipeline development platform

中文法律LLaMA (LLaMA for Chinese legel domain)

code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer

Open Language Pre-trained Model Zoo

Unsupervised anomaly detection for microservice log data using Transformer embeddings, graph-based modeling, and ensemble scoring.

Ship RAG based LLM web apps in seconds.

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.

DOM to Semantic-Markdown for use with LLMs

Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)

Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

NVIDIA Federated Learning Application Runtime Environment

A Dataset of Python Challenges for AI Research

Voice-first local agent orchestration runtime for auditable DAG workflows.

Minimal Claude Code statusline HUD powered by Rust.

Delegate tasks to Codex and Gemini directly from within Claude Code.

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.

Metric learning and retrieval pipelines, models and zoo.

Low-latency hardware-accelerated WebRTC video streaming and remote control for Raspberry Pi & NVIDIA Jetson

Multiple Agents, Parallel Flow

Beautiful and Easy to use Stable Diffusion WebUI

🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"