WebMarker
Mark web pages for use with multimodal large language models
5 followers
Mark web pages for use with multimodal large language models
5 followers
WebMarker adds visual markings with labels to elements on a web page. This can be used for Set-of-Mark (SoM) prompting, which improves visual grounding abilities of vision-language models such as GPT-4o, Claude 3.5, and Google Gemini 1.5.
Free
Launch Team
Intercom — Startups get 90% off Intercom + 1 year of Fin AI Agent free
Startups get 90% off Intercom + 1 year of Fin AI Agent free
Promoted
Be the first to comment