ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

GraphVQA: Language-Guided Graph Neural Networks for Scene Graph Question Answering

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

Official Implementation of Unveiling User Preferences: A Knowledge Graph and LLM-Driven Approach for Conversational Recommendation

A GlobalProtect VPN client (GUI), which runs in a Docker container and exposes the VPN connection to the users as a SOCKS5 proxy

A GlobalProtect VPN client for Linux, written in Rust, based on OpenConnect and Tauri, supports SSO with MFA, Yubikey, and client certificate authentication, etc.

Source code for NoteLLM and NoteLLM-2

R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1

Official Repo for Open-Reasoner-Zero

Open replication of DeepSeek R1 for text-to-graph extraction.

⛽️「算法通关手册」：超详细的「算法与数据结构」基础讲解教程，从零基础开始学习算法知识，850+ 道「LeetCode 题目」详细解析，200 道「大厂面试热门题目」。

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

minimal-cost for training 0.5B R1-Zero

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

verl: Volcano Engine Reinforcement Learning for LLMs

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

In-depth study of the graphrag

s1: Simple test-time scaling

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

Reproduce R1 Zero on Logic Puzzle

Graph Foundation Model for Retrieval Augmented Generation

Steam Deck Plugin to apply Framegen mods to games by replacing DLSS DLL with FSR3 DLL

-游戏文字交流AI嘴强王者工具

Fast State-of-the-Art Static Embeddings

Janus-Series: Unified Multimodal Understanding and Generation Models

Fully open reproduction of DeepSeek-R1

NAS媒体库自动化管理工具