Hacker News new | past | comments | ask | show | jobs | submit | andy12_'s submissions login

1. Tokenformer: Rethinking transformer scaling with tokenized model parameters (arxiv.org) 3 points by andy12_ 12 hours ago | past | 1 comment 2. Selective Attention Improves Transformer (arxiv.org) 1 point by andy12_ 24 days ago | past | 1 comment 3. The AdEMAMix Optimizer: Better, Faster, Older (arxiv.org) 2 points by andy12_ 51 days ago | past

Consider applying for YC's W25 batch! Applications are open till Nov 12. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: