Viewing profile — zavrel

LLMs and RAG have made it so much easier to prototype and incorporate AI in production systems, but evaluation has really become a whole lot harder. Comparing different outputs fro…

Allows you to organize and share your paper collections, get personalized reading recommendations based on that, read papers and annotate the PDFs, and ask questions to papers usin…

Zeta Alpha, of course ;-) https://search.zeta-alpha.com/

More discussion around this post on twitter: https://twitter.com/ZetaVector/status/1631590029926494211?s=...

That's right, we only counted the tweets for arXiv papers (base on URL), not for the other publication venues. Looking into how to improve that.

Citations are of course only a distant proxy for real world impact. What would you recommend as a better early indicator? We also looked at Tweet count, but that seems more biased …

We used the Google Scholar counts - and in particular a snapshot of end of february for this ranking. There is no perfect number, but at least this one is generally accepted as rea…

The arXiv version is from 2021 so it is not counted towards 2022.

There was great work last year on distributed training and inference: Petals: Collaborative Inference and Fine-tuning of Large Models Alexander Borzunov, Dmitry Baranchuk, Tim Dett…