4 papers
Prompt Group-Aware Training for Robust Text-Guided Nuclei Segmentation
Yonghuang Wu, Zhenyang Liang, Wenwen Zeng +2
Foundation models such as Segment Anything Model 3 (SAM3) enable flexible text-guided medical image segmentation, yet their predictions remain highly sensitive to prompt formulatio…
MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding
Wenwen Zeng, Yonghuang Wu, Yifan Chen +5
Reconstructing dynamic videos from fMRI is important for understanding visual cognition and enabling vivid brain-computer interfaces. However, current methods are critically limite…
SAMPO-Path: Segmentation Intent-Aligned Preference Optimization for Pathology Foundation Model Segmentation
Yonghuang Wu, Wenwen Zeng, Xuan Xie +3
Foundation models have shown strong performance in multi-object segmentation with visual prompts, yet histopathology images remain challenging due to high cellular density, heterog…
Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Image
Yonghuang Wu, Xuan Xie, Xinyuan Niu +2
Pathology computing has dramatically improved pathologists' workflow and diagnostic decision-making processes. Although computer-aided diagnostic systems have shown considerable va…