[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).
We're currently in the final stages of cleaning up and organizing everything. We appreciate your interest in the SeeAct online tool. It will be released really soon.
Hi,
Thanks for sharing the exciting project! I am just curious about when the full code will be ready. Can not wait to try.
Regards,