A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

This is a repository for code, data, and models associated with the paper LLM-RUBRIC: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts, accepted at ACL 2024.

Serper MCP Server supporting search and webpage scraping

Read translation intelligent agent for Google Mail academic paper subscription

Official implementation of MATPO: Multi-Agent Tool-Integrated Policy Optimization.

Verlog: A Multi-turn RL framework for LLM agents

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

[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

[CVPR 2025] Official Implementation of "Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection". The first multi-class UAD model that can compete with single-class SOTAs

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

开源安全产品源码，IDS、IPS、WAF、蜜罐等

MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.

Scaling RL on advanced reasoning models

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Python 数据科学加速：Dask、Ray、Xorbits、mpi4py

Democratizing Reinforcement Learning for LLMs

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

[NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example

A series of math-specific large language models of our Qwen2 series.

s1: Simple test-time scaling

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)