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).
1 best points · 0 comments · 1 Hacker News post · 853 GitHub stars · View on GitHub
Hacker News discussions
- SeeAct GPT-4V(ision) Is a Generalist Web Agent, If Grounded (1 points, 0 comments, by r_singh, 2024-01-18)