Size Wu PRO

wusize's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 5 papers 4 months ago

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Paper • 2310.01403 • Published Oct 2, 2023 • 1

CLIM: Contrastive Language-Image Mosaic for Region Representation

Paper • 2312.11376 • Published Dec 18, 2023

OMG-Seg: Is One Model Good Enough For All Segmentation?

Paper • 2401.10229 • Published Jan 18, 2024 • 1

F-LMM: Grounding Frozen Large Multimodal Models

Paper • 2406.05821 • Published Jun 9, 2024

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

Paper • 2503.21979 • Published Mar 27 • 3