[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 brilliant work. I want to do some analysis on the trajectories of different methods in your paper (e.g. FLAN-T5, GPT-4, SeeAct with different grounding methods). Is it possible to release any of the trajectories? That would be meaningful for much future work!
Dear Authors,
Thank you for this brilliant work. I want to do some analysis on the trajectories of different methods in your paper (e.g. FLAN-T5, GPT-4, SeeAct with different grounding methods). Is it possible to release any of the trajectories? That would be meaningful for much future work!
Thanks in advance!