Yu-Han Zhang

MVLGeo, an efficient framework designed to unify multiple viewpoints and reduce model redundancy, achieves state-of-the-art performance, demonstrating robustness to input degradation and generalization across viewpoints.

CamoShift is the first to target both visual stealthiness and attack success in visible-infrared object detection, and is the first to target both visual stealthiness and attack success in visible-infrared object detection.

AnomExpert achieves 86.9% accuracy in prenatal ultrasound anomaly diagnosis by intelligently selecting relevant anatomical planes without requiring detailed annotations.

FrameONE revolutionizes echocardiographic keyframe detection by achieving state-of-the-art accuracy through a unified multi-view approach that overcomes traditional limitations.

Training-free anomaly classification in prenatal ultrasound can now be achieved with just a few reference images, revolutionizing diagnostic accessibility.

Mandol achieves a 5.4x speedup in retrieval and a 4.8x speedup in insertion, revolutionizing long-term conversational memory management.

Query-aware segment folding boosts long-video understanding performance by up to 9.1 percentage points without additional computational cost.