Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining.…
cs.CV2025
MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expression
Hai Dang Nguyen, Nguyen Dang Huy Pham, The Minh Duc Nguyen +3
Spatial Transcriptomics (ST) enables the measurement of gene expression while preserving spatial information, offering critical insights into tissue architecture and disease pathol…