foundation-multimodal-models

AI & ML interests

Dedicated to contributing advanced and foundation multimodal models to the open source

Recent Activity

stormthunder  authored a paper 9 days ago

Benchmarking and Improving Detail Image Caption

stormthunder  authored a paper 9 days ago

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

stormthunder  authored a paper 9 days ago

World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

View all activity

Team members 7