Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Paper • 2607.24027 • Published • 27
AI & ML interests
A Small GenAI Group in W2 Building@HKUST, Guangzhou.
Recent Activity
View all activity
Papers
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
Owen777
authored a
paper about 19 hours ago
Owen777
submitted a
paper to Daily Papers about 21 hours ago
Xsong123
updated a
model 2 months ago
Xsong123
published a
model 4 months ago
Xsong123
updated a
model 5 months ago
Remove library name and update license
1
#2 opened 10 months ago
by 
nielsr
Improve model card: Add pipeline tag, library name, license, paper and code links
#1 opened 10 months ago
by nielsr
Xsong123
published a
model 11 months ago
Owen777
updated a
model 11 months ago
Xsong123
updated a
model 11 months ago
Xsong123
published a
model 11 months ago
Owen777
authored a
paper about 1 year ago
Owen777
authored 6
papers over 1 year ago
Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
Paper • 2411.10781 • Published
CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
Paper • 2503.09662 • Published • 33
POSTA: A Go-to Framework for Customized Artistic Poster Generation
Paper • 2503.14908 • Published
An Empirical Study of GPT-4o Image Generation Capabilities
Paper • 2504.05979 • Published • 64
MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
Paper • 2503.05978 • Published • 36
Magic 1-For-1: Generating One Minute Video Clips within One Minute
Paper • 2502.07701 • Published • 37
Owen777
authored 2
papers almost 2 years ago