Zhibin Lan

zhibinlan's activity

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

upvoted a paper 7 days ago

LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning

Paper • 2503.04812 • Published 14 days ago • 12

upvoted a collection 8 days ago

LLaVE

Collection

LLaVE is a series of large language and vision embedding models trained on a variety of multimodal embedding datasets • 4 items • Updated 8 days ago • 8