search

OSU-NLP-Group / SeeAct

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
https://osu-nlp-group.github.io/SeeAct/
Other
571 stars 69 forks source link

Setup and experiment guide on readme file #4

Closed asuzukosi closed 7 months ago

asuzukosi commented 7 months ago

I was thinking of adding a setup guide on the readme file, wanted to know if that was something that would be beneficial or if the project is best left as is

boyugou commented 7 months ago

Hi Kosi,

Thank you very much for being willing to help us organize the code and readme. Of course, a clearer and more instructive readme would be better.

We will organize the code and readme again when we release the online code (around this Friday). You can consider this at that time, hoping it can save some of your time and efforts.

I assume people will be more curious about the online tool, and the running of that tool will be super easy.