activity
20242026
collaborators

7 papers

cs.LG2026

Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation

Lorenzo Brigato, Stavroula Mougiakakou

We introduce Tune without Validation (Twin), a simple and effective pipeline for tuning learning rate and weight decay of homogeneous classifiers without validation sets, eliminati…

cs.LG2026

There are no Champions in Supervised Long-Term Time Series Forecasting

Lorenzo Brigato, Rafael Morand, Knut Strømmen +3

Recent advances in long-term time series forecasting have introduced numerous complex supervised prediction models that consistently outperform previously published architectures.…

eess.IV2025

Unmasking Interstitial Lung Diseases: Leveraging Masked Autoencoders for Diagnosis

Ethan Dack, Lorenzo Brigato, Vasilis Dedousis +9

Masked autoencoders (MAEs) have emerged as a powerful approach for pre-training on unlabelled data, capable of learning robust and informative feature representations. This is part…

cs.LG2025

Personalised Insulin Adjustment with Reinforcement Learning: An In-Silico Validation for People with Diabetes on Intensive Insulin Treatment

Maria Panagiotou, Lorenzo Brigato, Vivien Streit +13

Despite recent advances in insulin preparations and technology, adjusting insulin remains an ongoing challenge for the majority of people with type 1 diabetes (T1D) and longstandin…

cs.AI2025

The Role of Artificial Intelligence in Enhancing Insulin Recommendations and Therapy Outcomes

Maria Panagiotou, Knut Stroemmen, Lorenzo Brigato +2

The growing worldwide incidence of diabetes requires more effective approaches for managing blood glucose levels. Insulin delivery systems have advanced significantly, with artific…

cs.CV2025

Benchmarking Post-Hoc Unknown-Category Detection in Food Recognition

Lubnaa Abdur Rahman, Ioannis Papathanail, Lorenzo Brigato +1

Food recognition models often struggle to distinguish between seen and unseen samples, frequently misclassifying samples from unseen categories by assigning them an in-distribution…