liugddx

liugddx's activity

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

upvoted a paper about 1 month ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Paper • 2602.07026 • Published Feb 2 • 138

upvoted a paper 8 months ago

FastVLM: Efficient Vision Encoding for Vision Language Models

Paper • 2412.13303 • Published Dec 17, 2024 • 75

upvoted an article about 1 year ago

view article

Article

Finally, a Replacement for BERT: Introducing ModernBERT

• 
• 
• +13

Dec 19, 2024

•

734

upvoted a collection almost 2 years ago

Text-to-Image Base Models

Collection

All text-to-image open source base models, with their respective license • 28 items • Updated May 10, 2024 • 28