Shiyu Zhao

9

Papers

16

Total Citations

Papers (9)

MLLM-as-a-Judge for Image Safety without Human Labeling

Taming Self-Training for Open-Vocabulary Object Detection

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

Generating Enhanced Negatives for Training Language-Based Object Detectors

Deep Animation Video Interpolation in the Wild

Global Matching With Overlapping Attention for Optical Flow Estimation

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction

Exploiting Unlabeled Data with Vision and Language Models for Object Detection