Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Technotroll
11 months ago
|
parent
|
context
|
favorite
| on:
PaLI-3 Vision Language Models
Does the vision-language-model process raw image data, or does it process OCR character output?
bigfudge
11 months ago
[–]
Gpt4v seems to be doing the former, at least in my experiments with it. It interprets plots and categorises images.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: