News for hackers. Stuff that matters.
Re:Understanding Transformers via N-gram Statistics by cschmidt on Sunday May 18, 2025 @09:34AM (#44021324)
This paper was accepted as a poster to NeurIPS 2024, so it isn't just a pre-print. There is a presentation video and slides here:

https://neurips.cc/virtual/2024/poster/94849

The underlying data has been open sourced as discussed on his blog here https://timothynguyen.org/2024/11/07/open-sourced-my-work-on...

There are no comments on this comment yet.