DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 66 •
3
ZehongMa
zehongma
AI & ML interests
MLLMs, Image/Video Generation, Multi-modal Representation Learning
Recent Activity
upvoted an article 17 days ago
PRX Part 3 — Training a Text-to-Image Model in 24h! upvoted a paper about 1 month ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision EncodersOrganizations
None yet
commented a
paper 5 months ago