paper-rec

paper-rec

A Gradio demo that recommends ten recent machine learning and AI papers from arXiv, based on titles, abstracts or keywords you give it. It suits researchers and students.

Made by bluebalam on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: paper-rec is a Gradio demo on Hugging Face Spaces that recommends machine learning and AI papers. So many papers appear each day that choosing the next one to read is hard. This demo picks from the latest arXiv papers and tailors the list to what you liked before.

Who it suits: It suits researchers, students and engineers who follow machine learning and want a short reading list without scanning every new paper.

Industry | Who uses it | How they use it | Example
Academia | PhD students | Find new papers close to ones they already liked | Enter the title of a paper from their reading list
Industry research | ML engineers | Keep up with a topic without scanning daily listings | Enter a few topic keywords
Education | Course instructors | Gather recent papers on a subject for a class | Enter an abstract that matches the lesson

Anyone who needs papers outside machine learning and AI can skip it, since the demo is aimed at that field.

Where to use it:

• A web browser, straight from the Space page on Hugging Face
• Windows, macOS or Linux with Python, as a local copy

Use case | Who | What they get back
Find the next paper to read | Researchers | A top-10 list of recommended articles
Explore a topic by keywords | Students | Recent arXiv papers close to the keywords

How to set it up: Using it online needs nothing. A local copy needs these first.

• Python and pip
• The huggingface_hub package, to fetch the files
• The packages in requirements.txt, plus Gradio

1. Install the Hugging Face Hub package.
2. Download the Space into a folder called paper-rec.
3. Move into that folder.
4. Install Gradio, then the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download bluebalam/paper-rec --repo-type space --local-dir paper-rec
cd paper-rec
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Open the Space page on Hugging Face and enter the title or abstract of papers you liked, or both. You can also type keywords for topics you care about. The demo then gives you ten recommended articles.

Example: You enter the title of a paper you enjoyed last month. The demo answers with ten recent papers that match your taste, picked from the latest arXiv submissions.

For newcomers and experts: If you are new, start with one paper you liked and paste its title. You will get a list of ten papers to try, so you do not have to search by hand.

If you know the field, the input is free text, a title, an abstract or keywords, and the output is a fixed top-10 list from recent arXiv papers. The source does not say how similarity is computed, so read app.py for the method.

You enter titles, abstracts or keywords
The demo compares them with recent arXiv papers
You get ten recommended articles

Good to know:

• It covers recent arXiv papers in machine learning and AI, so older or other-field papers may not appear
• The method behind the ranking is in app.py, not in the README
• License: mit
• Cost to run: none named
• Data it reaches: arXiv paper listings and the text you enter

On Hugging Face, 13 November 2026

• Likes: 10
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/bluebalam/paper-rec
• Files: https://huggingface.co/spaces/bluebalam/paper-rec/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.