4 papers
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.…
Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps
Do Tien Hai, Trung Nguyen Mai, TrungTin Nguyen +3
We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model sele…
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen +10
State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by auto…
MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification
Anh-Tien Nguyen, Duy Minh Ho Nguyen, Nghiem Tuong Diep +7
Whole slide pathology image classification presents challenges due to gigapixel image sizes and limited annotation labels, hindering model generalization. This paper introduces a p…