Yuzhong Zhao

5

Papers

3

Total Citations

Papers (5)

DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models

Generative Prompt Model for Weakly Supervised Object Localization

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models