jarikoi/interesting-papers

Jari's collection of interesting papers.

What it solves

Keeping track of academic papers worth revisiting can be messy, especially when you want to find them again later. This project turns that problem into a simple, organized, personal library of curated research papers.

How it works

The repository stores papers in folders grouped by topic or theme. A separate inventory file (an Excel spreadsheet) lists each paper with a summary and a "landmark" indicator, so you can scan the collection quickly without opening every folder. Anyone can suggest additions or improvements by opening an issue or submitting a pull request.

Who it’s for

Anyone who reads academic papers and wants a lightweight, human-curated way to collect and browse interesting work — no automated tools or complex setup required.

Highlights

  • Curated by a single author, so the selection reflects personal taste and focus
  • Papers organized by topic into clear directory structures
  • An inventory file gives a bird’s-eye view with summaries and landmark flags
  • Open to community contributions via issues and pull requests

Related

  • Project
    CausalInferenceLab/Causal-Inference-with-Python

    This project is a Korean translation of Matheus Facure's open-source book on causal inference, with all 25 chapters and 5 appendices translated and accompanied by runnable Python code. It helps Korean-speaking data scientists and analysts learn causal concepts from basic to advanced methods in their own language.

  • Project
    AXYZdong/awesome-snn-conference-paper

    A curated repository that gathers top international conference papers and related code on Spiking Neural Networks (SNNs), organized by year and conference, to support researchers in the field.

  • Project
    MIT-MI/how2ai-course

    This is the course website for MIT's MAS.S60 'How to AI (Almost) Anything' (Spring 2025). It provides the course webpage and instructions for running it locally with Jekyll.

  • Project
    js05212/BayesianDeepLearning-Survey

    A continuously updated survey of Bayesian deep learning, curating and categorizing research papers across various application domains such as recommender systems, healthcare, natural language processing, and computer vision. It serves as a comprehensive reference for researchers and practitioners.