SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Paper • 2512.11749 • Published • 39
Shi Minglei
MingleiShi
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
SkillOS: Learning Skill Curation for Self-Evolving Agents upvoted a paper about 1 month ago
Seedance 2.0: Advancing Video Generation for World Complexity upvoted a paper about 1 month ago
ELT: Elastic Looped Transformers for Visual GenerationOrganizations
authored 2
papers 5 months ago
authored a
paper about 1 year ago