Ask HN: How do you sift through new research?

I work in computer vision and regularly follow Arxiv for new papers. Sometimes I find a gem, but a lot of the papers I find are from curated sources who do a bit of sifting.

I’m curious: how do you sift through new research? Do you have automated methods to highlight papers by keyword? Or something else? Do you rely heavily on curation?

4 points | by zerojames 12 days ago

1 comments

  • velyan 12 days ago
    Hey I am curious what's your current process? And would you like to input and output?

    I am actually building something targeting content overwhelm and automating the curation process.

    You can join the whitelist here: https://collate.one/preview

    If you're a MacOS user I can give you free access to pilot version to try?

    Also if you wanna get daily summaries of the papers you have you can also try this small app I built: https://collate.one/newsletter

    Keen to know more about your problem...

    [-]
    • zerojames 11 days ago
      Summaries are less interesting than my getting the information in the first place. My general hierarchy for sifting is:

      Title -> Abstract -> skim directly to the section(s) that are most interesting or answer a question I have.

      For most papers, I can gauge interest based on the title. But there are so many!

      I have a secondary problem of being able to find research on a topic: quantitative linguistics. Arxiv has a category on Computation and Linguistics, but it is mostly LLMs.

      [-]
      • velyan 11 days ago
        Yup, so you'd like to:

        1. Given your resources, be able to the filter out the sections that are relevant to your topic of interest 2. Find resources that related to a topic

        In order of severity pain points, is this correct? What is the goal of your research?

        [-]
        • velyan 11 days ago
          What the newsletter app does: it groups materials in up to 5 topics and generates an article for each topic based on the resources you've provided