From the 1 of 12 linked papers with an AI index.
12 papers
Gated Spatial Redundancy Projection for Pathology Transformer Attentions
Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh +1
Transformer models are increasingly used for whole-slide image analysis in computational pathology. Yet, WSIs differ fundamentally from natural images: neighbouring patches often c…
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders
Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. Hosseini
The paper proposes two sparsity regularizers that work with Top‑k sparse autoencoders to improve the interpretability of latent features without hurting reconstruction quality.
MOOZY: A Patient-First Foundation Model for Computational Pathology
Yousef Kotp, Vincent Quoc-Huy Trinh, Christopher Pal +1
Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain largely slide-centric, often depe…
Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
Ghodsiyeh Rostami, Po-Han Chen, Mahdi S. Hosseini
Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed archite…
Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation
Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh +1
Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the c…
SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini
Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated…