liqiang niu

lqniu's activity

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

upvoted a paper 12 days ago

WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

Paper • 2603.11593 • Published 13 days ago • 25

upvoted a collection 5 months ago

UME-R1

Collection

UME-R1 is a framework designed to endow multimodal embedding models with the flexibility to switch between discriminative and generative embeddings • 5 items • Updated 2 days ago • 9

upvoted a paper about 1 year ago

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

Paper • 2503.04812 • Published Mar 4, 2025 • 17

upvoted a collection about 1 year 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 Mar 10, 2025 • 8