[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).
Thank you for this inspiring work and for releasing the code!
Are you also planning to release the model predictions? More specifically, are you planning to release oracle action grounding done by human annotators (i.e., the description a˜ and the grounded triplet (e,o,v) that was chosen by the annotators)?
Thx again and sorry if it was already released and I missed it :)
Thank you for this inspiring work and for releasing the code!
Are you also planning to release the model predictions? More specifically, are you planning to release oracle action grounding done by human annotators (i.e., the description a˜ and the grounded triplet (e,o,v) that was chosen by the annotators)?
Thx again and sorry if it was already released and I missed it :)
Ori