Hit enter to search or ESC to close

Paper Digest

Serve tens of thousands of users using machine generated contents everyday

We are a New York based research group serving people across the world. We were founded in 2018 by Dr. Chang Wang.


Our mission is to help people stay current with the latest tech trends, generate contents based on facts and reason over unstructured data. We own a platform providing a full spectrum of machine learning and natural language processing functions e.g. content generation, search, summarization, question answering, etc. We also maintain a large / clean / up-to-date corpus with hundreds of millions of documents.


We provide services to both personal users and business collaborators. We also provide customized solutions to business users  (scroll down to see contact info).


“Paper Digest” is our trademark registered in the US and other countries and regions.


You may also like to check out our Frequently Asked Questions page.

Currently, we offer the following services:

  • Daily paper digest (introduced in early 2018)
    • subscribers receive customized daily updates on papers published on previous day;
  • Conference paper digest (introduced in mid 2019)
    • one-sentence highlight for every paper published in a conference;
  • Search Engine (introduced in early 2020)
    • paper search
    • patent search
    • grant search
    • code search
    • expert search
    • reviewer search
  • Real-time topic tracking (introduced in early 2020)
    • track papers related to dozens of trending topics;
  • “Best paper” digest (introduced in early 2021)
    • present 10-15 most influential papers for each conference / journal by year;
  • Literature Review (introduced in late 2021)
    • generate a literature review around any given research topic in seconds, covering
      • papers (introduced in 2021)
      • patents (introduced in 2022)
      • clinical trials (introduced in 2023)
  • Other AI for Tech Services (made public in early 2022)
    • Tech Domain: Single Document/ MultiDocument Summarization, Question Answering, Paraphrase, etc.
    • Open Domain: Single Document Summarization, Question Answering, Paraphrase, etc.

Data & Compute Resource
We track and analyze new papers appearing in major academic websites (including arxiv, biorxiv, pubmed, medrxiv, google scholarsemantic scholar academic graph (under odc attribution license), paperswithcode, bing academic, ieee, acm, etc) as well as thousands of other conferences and journals.


We also track other technology related data like  patents, clinical trials and government grants. Our person related data is provided by Expert Graph.


Part of our compute resource is generously provided by AWS educational technology (EdTech) startup accelerator.

We have developed exclusive techniques to produce high quality text analysis results. Different from most other AI systems, our system builds on “semantics”.


We have also built a fairly complicated natural language processing platform to support customer oriented services.


The platform contains:

  • a central knowledge graph storing hundreds of millions of documents;
  • search components providing different kinds of search results;
  • a number of site crawlers tracking documents in real-time;
  • a pipeline with dozens of built-in natural language processing and machine learning components to analyze & generate text.

Our users come from more than 200 countries or territories across the world. Top 10 countries (based on the number of full pages that have been viewed) are: United States, China, India, Canada, Great Britain, Germany, South Korea, Sweden, France, Russian Federation. Most of our users are researchers, engineers, professors and graduate students. Some business men, reporters and investors also use our services to read literature review, track trending topics and the most recent research progresses.

  • team@paperdigest.org
  • 12 E 49th St, 9th Floor, New York, NY, USA, 10017