Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lava_pidgeon
53 days ago
|
parent
|
context
|
favorite
| on:
Vision Language Models Are Biased
At all, the models are just overfitting?
vokhanhan25
53 days ago
[–]
Not really. Rather, the model is still overconfident in what it has learned, the question is if it is trained only to do counting without relying on knowledge, can it do this?
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
