GUI Agents Papers
Star · 821

WebVLN: Vision-and-Language Navigation on Websites

Qi Chen , Dileepa Pitawela , Chongyang Zhao , Gengze Zhou , Hsiang-Ting Chen , Qi Wu

🏛 Institutions
Australian Institute for Machine Learning , University of Adelaide
📅 Date
December 25, 2023
📑 Publisher
AAAI 2024
💻 Env
Web
🔑 Keywords
TLDR

WebVLN extends vision-and-language navigation to websites by framing browsing as question-driven navigation over rendered pages plus underlying HTML. The paper introduces the WebVLN-v1 dataset and a Website-aware VLN Network that outperforms prior VLN and web-navigation baselines.

Open paper Report issue
Related papers (24)