GPT-4V(ision) is a Generalist Web Agent, if Grounded
Research paper by Boyuan Zheng and collaborators. Published 2024-01-03. Topics: GPT-4V, multimodal models, SEEACT, MIND2WEB benchmark, web agents.
Resource information
- Authors
- Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su
- Research topics
- GPT-4V, multimodal models, SEEACT, MIND2WEB benchmark, web agents, visual understanding, GPT-4, FLAN-T5, BLIP-2, set-of-mark prompting, oracle grounding
- Publication date
- 2024-01-03
- Publication
- arXiv
- Last record update
- Nov 3, 2026