AI 开源项目榜。

MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Synthesized Logic Language for World Models 🌱🐋🌍

Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

Android TensorFlow Lite Machine Learning Example

国内公司人工智能方向（含机器学习、深度学习、计算机视觉和自然语言处理）岗位的招聘信息（含全职、实习和校招）

使用IndexTTS模型在ComfyUI中实现高质量文本到语音转换的自定义节点。支持中文和英文文本，可以基于参考音频复刻声音特征。

Terminal UI to chat with large language models (LLM) using different model backends, and integrations with your favourite editors!

Deep Learning models for network traffic classification

A cross-platform browser ML framework.

A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

中文领域心理健康对话大模型SoulChat

Awesome resources on Bioinformatics, data science, machine learning, programming language (Python, Golang, R, Perl) and miscellaneous stuff.

Deep learning for audio denoising

Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

[ICML'26] Official repository of Utonia: Toward One Encoder for All Point Clouds

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.

Web Codegen Scorer is a tool for evaluating the quality of web code generated by LLMs.

:mortar_board:RESEARCH [NLP :thought_balloon:] We use different feature sets and machine learning classifiers to determine the best combination for sentiment analysis of twitter.

BabyAI platform. A testbed for training agents to understand and execute language commands.

Demo of a UI testing agent using the OpenAI CUA model and the Responses API.

If you can read ~100 lines of Python, you understand agents.

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose" (Arxiv 2020) and "Predicting Personalized Head Movement From Short Video and Speech Signal" (TMM 2022)

Qwen-Image text to image lora trainer

MDPs and POMDPs in Julia - An interface for defining, solving, and simulating fully and partially observable Markov decision processes on discrete and continuous spaces.

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

A PyTorch Implementation of End-to-End Models for Speech-to-Text