zzxslp

joined 2 years ago

[R] GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation in c/machinelearning@academy.garden

[–] zzxslp@alien.top 1 points 2 years ago

I guess the potential is not only for helping visually-impaired users (definitely important here) but also free everyone from daily tasks on our phone. A better Siri

permalink
fedilink
source
context

[R] GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation in c/machinelearning@academy.garden

[–] zzxslp@alien.top 1 points 2 years ago (1 children)

Hey all, I am the first author of this paper, feel free to connect with us if you got some ideas for pushing it into a cool product.

permalink
fedilink
source