foundation-multimodal-models

AI & ML interests

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

Recent Activity

melony  authored a paper 2 months ago

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

melony  authored a paper 5 months ago

Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation

melony  authored a paper 5 months ago

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

View all activity

Team members 7