9 papers
Losses that Cook: Topological Optimal Transport for Structured Recipe Generation
Mattia Ottoborgo, Daniele Rege Cambrin, Paolo Garza
Cooking recipes are complex procedures that require not only a fluent and factual text, but also accurate timing, temperature, and procedural coherence, as well as the correct comp…
HydroChronos: Forecasting Decades of Surface Water Change
Daniele Rege Cambrin, Eleonora Poeta, Eliana Pastor +4
Forecasting surface water dynamics is crucial for water resource management and climate change adaptation. However, the field lacks comprehensive datasets and standardized benchmar…
Magnifier: A Multi-grained Neural Network-based Architecture for Burned Area Delineation
Daniele Rege Cambrin, Luca Colomba, Paolo Garza
In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural netw…
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto +2
Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive…
Level Up Your Tutorials: VLMs for Game Tutorials Quality Assessment
Daniele Rege Cambrin, Gabriele Scaffidi Militone, Luca Colomba +3
Designing effective game tutorials is crucial for a smooth learning curve for new players, especially in games with many rules and complex core mechanics. Evaluating the effectiven…
KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
Daniele Rege Cambrin, Eleonora Poeta, Eliana Pastor +3
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this…