Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
johntb86
on May 11, 2024
|
parent
|
context
|
favorite
| on:
Vision Transformers Need Registers
For these tokens you first need to unembed the result of the final layer, the re-embed the resulting token on the next pass. Has anyone investigated passing the raw output of one pass to the input of the next?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: