SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Paper • 2512.11749 • Published • 39 •
3
Shi Minglei
MingleiShi
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Seedance 2.0: Advancing Video Generation for World Complexity upvoted a paper 4 days ago
ELT: Elastic Looped Transformers for Visual Generation upvoted a paper 10 days ago
OpenWorldLib: A Unified Codebase and Definition of Advanced World ModelsOrganizations
commented a
paper 4 months ago
commented a
paper 6 months ago
commented 4
papers about 1 year ago
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 •
5
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 •
5
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 •
5
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 •
5