David Leon

DavidLeon's activity

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

authored a paper about 12 hours ago

Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection

Paper • 2502.16223 • Published Feb 22

liked a model about 13 hours ago

qihoo360/fg-clip-base

Zero-Shot Image Classification • 0.2B • Updated Jun 5 • 6.37k • 6

upvoted a collection about 13 hours ago

FG-CLIP

Collection

6 items • Updated 21 days ago • 4

commented a paper 3 months ago

FG-CLIP: Fine-Grained Visual and Textual Alignment

Paper • 2505.05071 • Published May 8 • 18 •

3

upvoted a paper 3 months ago

FG-CLIP: Fine-Grained Visual and Textual Alignment

Paper • 2505.05071 • Published May 8 • 18

authored a paper 4 months ago

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers

Paper • 2502.14377 • Published Feb 20 • 12

authored 3 papers 9 months ago

Bridge Diffusion Model: bridge non-English language-native text-to-image diffusion model with English communities

Paper • 2309.00952 • Published Sep 2, 2023

FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance

Paper • 2408.08189 • Published Aug 15, 2024 • 17

Qihoo-T2X: An Efficiency-Focused Diffusion Transformer via Proxy Tokens for Text-to-Any-Task

Paper • 2409.04005 • Published Sep 6, 2024 • 19

upvoted a paper 11 months ago

Qihoo-T2X: An Efficiency-Focused Diffusion Transformer via Proxy Tokens for Text-to-Any-Task

Paper • 2409.04005 • Published Sep 6, 2024 • 19

replied to HugoLaurencon's post about 1 year ago

view reply

Would you share the total training cost info? as traing of IDEFICS2-8B used "approximately 1.5 billion images and 225 billion text tokens" which is quite huge for a 8B sized LMM model