AI for Good
AIGO utilizes state-of-the-art multimodal models, with a special attention to vision, and Foundation Models to interpret complex signals from various modalities, including video, audio, and language. The team aims at developing efficient and scalable AI solutions for high-impact sectors such as healthcare, assisted living, and industrial applications.
5
Active Projects
25
Team Members
14
Publications
Our Team
Relevant Papers
2027
Olivato F., Beyan C., Murino V.
Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation Under Image Corruptions
Lecture Notes in Computer Science, vol. 16819 LNCS, pp. 1-16
2027
Morelli V., Berardini D., Letti G., Curreli S., Mancini A., Fellin T., Murino V.
Freq2Clean: Enhancing Calcium Imaging Denoising via Frequency-Domain Fusion
Lecture Notes in Computer Science, vol. 16823 LNCS, pp. 657-671
2027
Dibitonto F., Beyan C., Murino V.
HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA
Lecture Notes in Computer Science, vol. 16814 LNCS, pp. 552-567
2027
Dahaghin M., Padalkar M.G., Toso M., Del Bue A., Murino V.
SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
Lecture Notes in Computer Science, vol. 16827 LNCS, pp. 19-33
2026
Altufayli I., Ciranni M., Barbano C.A., Murino V., Pastore V.P.
A Pair-Weighing Strategy for Enhancing Clip Zero-Shot Classification for Chest X-Rays
Proceedings - International Symposium on Biomedical Imaging, vol. 2026-April
2026
Ciranni M., Shcharbitski A., Murino V., Pastore V.P.
Confidently Biased (ConB): A Per-sample Confidence Approach for Unsupervised Model Debiasing
Lecture Notes in Computer Science, vol. 16167 LNCS, pp. 79-90