arxiv:2511.19365
ZehongMa
zehongma
AI & ML interests
MLLMs, Image/Video Generation, Multi-modal Representation Learning
Recent Activity
upvoted
a
paper
2 days ago
BabyVision: Visual Reasoning Beyond Language
upvoted
a
paper
about 1 month ago
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
upvoted
a
paper
about 1 month ago
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
Organizations
None yet
