影响力指数

-/100

发表论文4 篇

平均评分4.3

年均产出1.3 篇/年

Sizhuo Ma

Researcher@Snap Inc.·美国·OpenReview

研究方向

computational imaging · computational photography · computer vision

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

ICLR 2026Withdrawn

Posterior-Guided Visual Token Pruning in Vision–Language Models

ICLR 2026Withdrawn

DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior

ICLR 2025Withdrawn

合作者 (19)