LIMO: Less is More for Reasoning

A jounery to real multimodel R1 ! We are doing on large-scale experiment

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Cache-Augmented Generation: A Simple, Efficient Alternative to RAG

Efficient, Flexible and Portable Structured Generation

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

The LLM Evaluation Framework

Fully open reproduction of DeepSeek-R1

SPLADE: sparse neural search (SIGIR21, SIGIR22)

An Innovative Agent Framework Driven by KG Engine

Creation of annotated datasets from scratch using Generative AI and Foundation Computer Vision models

[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Build Text Rerankers with Deep Language Models

Repair invalid JSON documents

Leveraging passage embeddings for efficient listwise reranking with large language models.

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

RAGChecker: A Fine-grained Framework For Diagnosing RAG

Supercharge Your LLM Application Evaluations 🚀

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A simple, fast and user-friendly alternative to 'find'