ZehongMa's picture

ZehongMa

zehongma

·

https://zehong-ma.github.io/

zehong-ma

AI & ML interests

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

Recent Activity

upvoted a paper 2 days ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

upvoted a paper about 1 month ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

submitted a paper about 1 month ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

View all activity

Organizations

None yet

submitted a paper to Daily Papers about 1 month ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published Feb 2 • 44

authored a paper 4 months ago

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

Paper • 2511.19365 • Published Nov 24, 2025 • 64

authored a paper 8 months ago

MagCache: Fast Video Generation with Magnitude-Aware Cache

Paper • 2506.09045 • Published Jun 10, 2025 • 1