Shi Minglei's picture

Shi Minglei

MingleiShi

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

updated a model 3 months ago

KlingTeam/SVG-T2I

upvoted a paper 3 months ago

Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

View all activity

Organizations

authored 2 papers 3 months ago

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder

Paper • 2512.11749 • Published Dec 12, 2025 • 39

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17, 2025 • 49

authored a paper 12 months ago

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Paper • 2503.14487 • Published Mar 18, 2025 • 28