Hacker Newsnew | past | comments | ask | show | jobs | submit | thw20's submissionslogin
1.Towards understanding multiple attention sinks in LLMs (github.com/jeffreywong20)
1 point by thw20 11 hours ago | past | 1 comment
2.The Existence and Behavior of Secondary Attention Sinks (arxiv.org)
1 point by thw20 22 days ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: