activity
20222026
most citedExploring Vanilla U-Net for Lesion Segmentation from Whole-body FDG-PET/CT Scans

10 citations · 15 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models

Yuncheng Yang, Feiyang Ye, Shixian Luo +7

Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…