Zimu Zhang

VCDP transforms semi-supervised medical image segmentation by aligning voxel embeddings with both global organ identities and local anatomical variations, leading to superior performance on challenging segmentation tasks.

HPR-SAM outperforms existing methods by effectively capturing complex anatomical representations, achieving state-of-the-art results in medical image segmentation without the need for prompts.

SHTA achieves significant improvements in segmentation accuracy by ensuring semantic consistency in challenging regions, all without increasing inference costs.

LLMs can scalably annotate motion capture data to produce semantically rich descriptions of bimanual interactions, enabling higher-quality generation of dexterous hand motions.