Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
The Bayesian Geometry of Transformer Attention
(
arxiv.org
)
2 points
by
samwillis
1 day ago
|
hide
|
past
|
favorite
|
1 comment
samwillis
1 day ago
[–]
Higher level overview and links to the other related papers:
https://medium.com/@vishalmisra/attention-is-bayesian-infere...
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
reply