AI 开源项目榜。
A curated collection of adversarial attack and defense on graph data.
Liquid Audio - Speech-to-Speech audio models by Liquid AI
🤖 GRAIL is a fully digital data-generation pipeline that synthesizes humanoid loco-manipulation data from world models. 🌟 CoRL 2026 (Best Paper Award Finalist)
A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]
Collection of models for Core ML
A simplified, lightweight ETL Framework based on Apache Spark
Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
PyTorch implementations of algorithms for density estimation
A collection of datasets that pair questions with SQL queries.
Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence
Generate long Sora 2 videos that exceed OpenAI's native 12-second limit
Python library to train neural networks with a strong focus on hydrological applications.
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.
CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.
A content-aware cropping library for Android
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
A list of the most popular AI Topic repositories on GitHub based on the number of stars they have received.| AI相关主题Github仓库排名，每日自动更新。
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)
The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, and multi-image queries for generating captions or responses.
MindWork AI Studio is a free, independent cross-platform desktop app for local and cloud LLMs across providers, built to democratize AI access.
food image to recipe with deep convolutional neural networks.
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
Reinforced Recommendation toolkit built around pytorch 1.7
Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.
Hyperspectral-Classification Pytorch
Scaling and Benchmarking Self-Supervised Visual Representation Learning
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022