82 citations · 380 across the 53 of their papers we have counts for
17 papers · 1 filter
Source Anchoring for Physical Consistency in Flow Matching Models
Giulia Romoli, Filippo Ruffini, Paolo Soda
Deep generative models are used to solve partial differential equations and model distributions of physical system states, but ensuring that the generated samples satisfy the gover…
Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
Omar Coser, Antonio Orvieto, Paolo Soda +1
Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether similar gains extend to multimodal…
VegSim: A Geospatial World Model for Scenario-Conditioned Vegetation Simulation
Irene Iele, Elena Mulero Ayllón, Paolo Soda +1
Vegetation monitoring under climate stress requires answering not only how it will evolve given the expected weather, but how it would respond to alternative meteorological conditi…
Resilient Vision-Tabular Multimodal Learning under Modality Missingness
Camillo Maria Caruso, Valerio Guarrasi, Paolo Soda
Multimodal deep learning has shown strong potential in medical applications by integrating heterogeneous data sources such as medical images and structured clinical variables. Howe…
Hybrid Quantum Neural Network for Multivariate Clinical Time Series Forecasting
Irene Iele, Floriano Caprio, Paolo Soda +1
Forecasting physiological signals can support proactive monitoring and timely clinical intervention by anticipating critical changes in patient status. In this work, we address mul…
Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates
Irene Iele, Giulia Romoli, Daniele Molino +4
Short-term forecasting of vegetation dynamics is a key enabler for data-driven decision support in precision agriculture. Normalized Difference Vegetation Index (NDVI) forecasting…
Cross-dataset Multivariate Time-series Model for Parkinson's Diagnosis via Keyboard Dynamics
Arianna Francesconi, Donato Cappetta, Fabio Rebecchi +3
Parkinson's disease (PD) presents a growing global challenge, affecting over 10 million individuals, with prevalence expected to double by 2040. Early diagnosis remains difficult d…
Beyond the Generative Learning Trilemma: Generative Model Assessment in Data Scarcity Domains
Marco Salmè, Lorenzo Tronchin, Rosa Sicilia +2
Data scarcity remains a critical bottleneck impeding technological advancements across various domains, including but not limited to medicine and precision agriculture. To address…
Doctor-in-the-Loop: An Explainable, Multi-View Deep Learning Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer
Alice Natalina Caragliano, Filippo Ruffini, Carlo Greco +8
Non-small cell lung cancer (NSCLC) remains a major global health challenge, with high post-surgical recurrence rates underscoring the need for accurate pathological response predic…
MARIA: a Multimodal Transformer Model for Incomplete Healthcare Data
Camillo Maria Caruso, Paolo Soda, Valerio Guarrasi
In healthcare, the integration of multimodal data is pivotal for developing comprehensive diagnostic and predictive models. However, managing missing data remains a significant cha…
A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical Applications
Valerio Guarrasi, Fatih Aksu, Camillo Maria Caruso +4
Deep learning has revolutionized biomedical research by providing sophisticated methods to handle complex, high-dimensional data. Multimodal deep learning (MDL) further enhances th…
A Systematic Review on Long-Tailed Learning
Chongsheng Zhang, George Almpanidis, Gaojuan Fan +6
Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed lea…
Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasets
Camillo Maria Caruso, Paolo Soda, Valerio Guarrasi
Handling missing values in tabular datasets presents a significant challenge in training and testing artificial intelligence models, an issue usually addressed using imputation tec…
A Deep Learning Approach for Overall Survival Prediction in Lung Cancer with Missing Values
Camillo Maria Caruso, Valerio Guarrasi, Sara Ramella +1
In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevale…
MATNet: Multi-Level Fusion Transformer-Based Model for Day-Ahead PV Generation Forecasting
Matteo Tortora, Francesco Conte, Gianluca Natrella +1
Accurate forecasting of renewable generation is crucial to facilitate the integration of Renewable Energy Sources into the power system. Focusing on photovoltaic (PV) units, foreca…
RadioPathomics: Multimodal Learning in Non-Small Cell Lung Cancer for Adaptive Radiotherapy
Matteo Tortora, Ermanno Cordelli, Rosa Sicilia +5
The current cancer treatment practice collects multimodal data, such as radiology images, histopathology slides, genomics and clinical data. The importance of these data sources ta…
An Empirical Study on the Joint Impact of Feature Selection and Data Re-sampling on Imbalance Classification
Chongsheng Zhang, Paolo Soda, Jingjun Bi +3
In predictive tasks, real-world datasets often present different degrees of imbalanced (i.e., long-tailed or skewed) distributions. While the majority (the head) classes have suffi…