Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Scalable Pre-Training of Large Autoregressive Image Models (Aim by Apple)
(
github.com/apple
)
12 points
by
rampantraccoon
11 months ago
|
hide
|
past
|
favorite
|
1 comment
rampantraccoon
11 months ago
[–]
"Interestingly, even at this scale, we observe no sign of saturation in performance, suggesting that AIM potentially represents a new frontier for training large-scale vision models."
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
