Hugging Face's logo
ZehongMa's picture
1 8 2

ZehongMa

zehongma
wangsssssss's profile picture
·
https://zehong-ma.github.io/

AI & ML interests

MLLMs, Image/Video Generation, Multi-modal Representation Learning

Recent Activity

upvoted a paper 16 days ago
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
upvoted a paper 22 days ago
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
authored a paper about 1 month ago
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
View all activity

Organizations

None yet