fregu856/papers

I categorize, annotate and write comments for all research papers I read (600+ papers since 2018).

What it solves

Reading many research papers is hard. This project provides a structured way to keep track of what you read, with categories and personal comments, making it easier to review and recall.

How it works

The author maintains a list of papers, each with a date, a paper number, a title, a link to the PDF and an annotated PDF, the venue and year, and categories. Each entry includes a personal comment summarizing the paper and the author's thoughts. The papers are organized by year, and there is a list of categories for filtering.

Who it's for

This is primarily a personal reference for the author, but it is publicly available and can serve as a resource for researchers and students who want to see how an experienced researcher reads and evaluates papers.

Highlights

  • More than 550 papers read and annotated since 2018.
  • Papers are organized into 38 categories covering many ML and healthcare topics.
  • Each entry includes a link to the paper, an annotated PDF, and a personal comment.
  • The author shares practical tips in a blog post about reading 300 papers.

Related

  • Project
    yandexdataschool/deep_vision_and_graphics

    A course repository from Yandex School of Data Analysis that teaches deep learning applied to computer vision, with weekly lectures, seminars, and homework covering topics from convolutional networks to diffusion models and neural rendering.

  • Project
    ZZZHANG-jx/Recommendations-Document-Image-Processing

    This repository is a carefully organised collection of academic papers, datasets, and benchmark results for document image processing, covering tasks such as shadow removal, dewarping, deblurring, and appearance enhancement. It serves as a reference hub for researchers and developers looking to understand or apply state-of-the-art methods to clean up photographed documents.

  • Project
    ilastik/ilastik

    An interactive machine learning toolkit for segmenting, classifying, tracking, and counting cells and other experimental image data.

  • Project
    qurator-spk/eynollah

    Eynollah is a Python library and command‑line tool for deep‑learning based document layout analysis, image binarization, enhancement, OCR, and reading‑order detection. It supports 10 layout classes, offers both CNN‑RNN and Transformer OCR models, outputs PAGE‑XML, and can be installed via PyPI or Docker. Pre‑trained ONNX models enable fast inference; full TensorFlow/PyTorch checkpoints are available for fine‑tuning. The project targets high‑quality processing of historical and heterogeneous scanned documents.