One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

[arXiv 2025] Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey

JPush's officially supported Flutter plugin (Android & iOS). 极光推送官方支持的 Flutter 插件（Android & iOS）。

Library for building distributed, real-time collaborative web applications

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

The official code of ARPO & AEPO

A collection of AWESOME things about Graph-Related LLMs.

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

Democratizing Reinforcement Learning for LLMs

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

EasyGraph is an open-source network analysis library designed to cover advanced network processing methods. It includes functionalities for detecting structural hole spanners, network embedding, an…

Tongyi Deep Research, the Leading Open-source Deep Research Agent

(Netflix 2025) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

Official code for our paper: "SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models".

[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)

Monaco Editor for React.

Papers about explainability of GNNs

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[Windows / Mac / Linux / Android / iOS] Maybe the best all-rounded service app for Fudan University students. 可能是复旦学生最好的第三方校园服务APP。

[NeurIPS'25] Graph Foundation Model for Retrieval Augmented Generation

Lightweight version of MAPPO to help you quickly migrate to your local environment.

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Realtime database backend based on Operational Transformation (OT)

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

An embeddable code editor for the browser 🍯

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.