Wangbo Zhao

10

Papers

11

Total Citations

Papers (10)

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning

Unsupervised Learning for Class Distribution Mismatch

Weakly Supervised Video Salient Object Detection

Modeling Motion With Multi-Modal Features for Text-Based Video Segmentation

Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative Guidance

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation

EA-Vit: Efficient Adaptation for Elastic Vision Transformer