zhaoyang97/Paper-Notes

📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。

What it solves

It addresses the challenge of keeping up with the overwhelming volume of academic research in AI. By providing concise summaries, it allows users to understand the core contributions of top-tier AI papers in about five minutes.

How it works

This project serves as a comprehensive, organized repository of over 23,000 AI paper notes. It categorizes research by major academic conferences (such as CVPR, NeurIPS, and ACL) and organizes them into more than 40 specific research fields, including LLM reasoning, robotics, and computer vision. Users can browse these notes directly through the project's website.

Who it’s for

It is designed for researchers, students, and AI practitioners who need to stay updated on the latest developments across various AI sub-fields without reading every full-length paper from scratch.

Highlights

  • Over 23,000 paper notes covering AI, LLM, NLP, and CV.
  • Coverage of major conferences including ACL, CVPR, ICLR, AAAI, NeurIPS, ICCV, ICML, and ECCV.
  • Organized into 40+ research directions such as Agent, RAG, AIGC, and Autonomous Driving.
  • Continuously updated with new research and conference proceedings.

Related

  • Project
    raphaelmansuy/edgequake

    EdgeQuake is a Rust‑based, single‑binary Graph‑RAG system that stores documents as a knowledge graph in PostgreSQL (pgvector + Apache AGE). It works with any OpenAI‑compatible LLM—cloud or local—via a simple Docker quick‑start, provides a web UI, REST API, SDKs, and production‑grade features (multi‑tenant auth, encrypted provider keys, safe migrations). Benchmarks show accuracy comparable to LightRAG but much faster cached queries.

  • Project
    pymupdf/pymupdf4llm

    A lightweight extension for PyMuPDF that converts PDFs and other documents into structured Markdown, JSON, and plain text optimized for RAG pipelines and LLM ingestion.

  • Project
    AmberLJC/LLMSys-PaperList

    A curated, categorized collection of academic papers and technical resources focused on the systems engineering behind Large Language Models, including training, serving, and agentic architectures.

  • Project
    Future-Scholars/paperlib

    An open-source academic paper management tool that simplifies metadata scraping and organization, featuring LLM-powered summarization and semantic search.