AImageLab publications export - 5 publications; author=asaporita

Saporita, A., Pipoli, V., Bolelli, F., Baraldi, L., Acquaviva, A., & Ficarra, E. (2026). FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). https://iris.unimore.it/handle/11380/1390068

Pipoli, V., Saporita, A., Marchesini, K., Grana, C., Ficarra, E., & Bolelli, F. (2026). IM-Fuse: A Mamba-based Fusion Block for Brain Tumor Segmentation with Incomplete Modalities. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). https://doi.org/10.1007/978-3-032-04984-1_22

Saporita, A., Pipoli, V., Bolelli, F., Acquaviva, A., & Ficarra, E. (2026). PathoClass-BRCA: Reframing Pathology Report Generation as Guideline-Aligned Multi-Task Classification. The British Machine Vision Conference (BMVC). https://iris.unimore.it/handle/11380/1417328

Saporita, A., Pipoli, V., Bolelli, F., Baraldi, L., Acquaviva, A., & Ficarra, E. (2025). Tracing Information Flow in LLaMA Vision: A Step Toward Multimodal Understanding. International Conference in Computer Analysis of Images and Patterns Las Palmas de Gran. https://iris.unimore.it/handle/11380/1383028

Pipoli, V., Saporita, A., Bolelli, F., Cornia, M., Baraldi, L., Grana, C., Cucchiara, R., & Ficarra, E. (2025). MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models. IEEE/CVF International Conference on Computer Vision Honolulu, Hawaii. https://iris.unimore.it/handle/11380/1381191