1 citations · 1 across the 5 of their papers we have counts for
5 papers
Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention
Giorgio Roffo, Hazem Abdelkawy, Nilli Lavie +1
The quadratic cost of softmax attention limits Transformer scalability in high-resolution vision. We introduce Infinite Self-Attention (InfSA), a spectral reformulation that treats…
The Origin of Self-Attention: Pairwise Affinity Matrices in Feature Selection and the Emergence of Self-Attention
Giorgio Roffo
The self-attention mechanism, now central to deep learning architectures such as Transformers, is a modern instance of a more general computational principle: learning and using pa…
A Temporal Convolutional Network-Based Approach and a Benchmark Dataset for Colonoscopy Video Temporal Segmentation
Carlo Biffi, Giorgio Roffo, Pietro Salvagnini +1
Following recent advancements in computer-aided detection and diagnosis systems for colonoscopy, the automated reporting of colonoscopy procedures is set to further revolutionize c…
Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing
Giorgio Roffo, Carlo Biffi, Pietro Salvagnini +1
To address overfitting and enhance model generalization in gastroenterological polyp size assessment, our study introduces Feature-Selection Gates (FSG) or Hard-Attention Gates (HA…
Exploring Advanced Large Language Models with LLMsuite
Giorgio Roffo
This tutorial explores the advancements and challenges in the development of Large Language Models (LLMs) such as ChatGPT and Gemini. It addresses inherent limitations like tempora…