Hi all, long time listener / first time caller. Please let me know if this topic belongs somewhere else or requires more detail.

App here: https://arxiv-explorer.streamlit.app

I am introducing the arXiv Explorer , a streamlit app that allows you to catch up on recent arXiv.org activity in any category. We use a combination of NLP tokenization techniques, LDA analyses for topic modeling, and a HuggingFace LLM for single-article summaries. Use cases may include:

A researcher who wants to understand the latest trends in their field without reading 500+ academic papers every week

An academic who learns about recent developments in adjacent fields

An undergraduate looking for research topics in a desired field

A lay-person seeking an introduction of the vocabulary used in a specific academic domain

Any of the above who want to summarize a specific technical article into 5-15 “conversational” chunks

Please check out the application and GitHub repository and let me know if you have questions or improvements! This is my first time really diving into statefulness , LLMs , and external visualization libraries (pyLDAvis) for Streamlit apps, and I’m very proud of the results.

For avoidance of doubt, I am in no way affiliated with arXiv.org , and I want to thank arXiv for providing use of its open access interoperability.

Thanks everyone!

Thanks for stopping by! We use cookies to help us understand how you interact with our website. By clicking “Accept all”, you consent to our use of cookies. For more information, please see our privacy policy .

Strictly necessary cookies

These cookies are necessary for the website to function and cannot be switched off. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms.

Performance cookies

These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us understand how visitors move around the site and which pages are most frequently visited.

Functional cookies

These cookies are used to record your choices and settings, maintain your preferences over time and recognize you when you return to our website. These cookies help us to personalize our content for you and remember your preferences.

Targeting cookies

These cookies may be deployed to our site by our advertising partners to build a profile of your interest and provide you with content that is relevant to you, including showing you relevant ads on other websites.

Reject all Accept all