Embedded Files
Highlights
Highlights
G. Cicchetti, E. Grassucci, L. Sigillo, D. Comminiello, Gramian Multimodal Learning and Alignment, ICLR 2025. [Project page][Preprint]
E. Grassucci, C. Marinoni, A. Rodriguez, D. Comminiello, Diffusion models for audio semantic communication, IEEE ICASSP 2024. [Preprint][Paper on IEEEXplore][Project page][GitHub]
Preprint and under review papers
Preprint and under review papers
E. Grassucci, G. Cicchetti, A.Uncini, D. Comminiello, Semantic Compression via Multimodal Representation Learning, under review 2025. [Preprint]
E. Grassucci, G. Galadini, G. Cicchetti, F. Antonacci, A.Uncini, D. Comminiello, Training-Free Multimodal Guidance for Video to Audio Generation, under review 2025. [Preprint]
C. Marinoni, R. F. Gramaccioni, E. Grassucci, D. Comminiello, Controllable Audio-Visual Viewpoint Generation from 360° Spatial Information, under review 2025. [Preprint]
E. Grassucci, J. Choi, J. Park, R. F. Gramaccioni, G. Cicchetti, D. Comminiello, Rethinking Multi-User Semantic Communications with Deep Generative Models, under review. [Preprint]
E. Grassucci, J. Park, S. Barbarossa, S.-L. Kim, J. Choi, D. Comminiello, Generative AI Meets Semantic Communication: Evolution and Revolution of Communication Tasks, under review. [Preprint]
Journal papers
Journal papers
E. Grassucci, G. Grassucci, A. Uncini, D. Comminiello, Beyond Answers: How LLMs Can Pursue Strategic Thinking in Education, IEEE Signal Processing Magazine, 2025. [Preprint]
E. Grassucci, G. Pignata, G. Cicchetti, D. Comminiello, Lightweight Diffusion Models for Resource-Constrained Semantic Communication, IEEE Wireless Communication Letters, 2025. [Preprint]
J.D. Jiménez-López, R.M. Fernández-Alcalá, F. Gutiérrez-Trujillo, E. Grassucci, D. Comminiello, Optimal fusion β-quaternion filtering from delayed observations and packet losses with compensation strategy under properness, Systems Science & Control Engineering, 2025. [Paper]
P. Zhang, P. Shi, S. Cui, Z. Zhang, K. Niu, Y. Xiao, Z. Qin, J. Dai, S. Shao, D. Gündüz, E. Grassucci, Semantic communications: Theories, technologies and applications, in China Communications, vol. 21, no. 7, pp. iii-vii, July, 2024.
E. Lopez, F. Betello, F. Carmignani, E. Grassucci, D. Comminiello, Attention-map augmentation for hypercomplex breast cancer classification, May 2024, Pattern Recognition Letters. [Paper]
E. Grassucci, L. Sigillo, A. Uncini, and D. Comminiello, GROUSE: A Task and Model Agnostic Wavelet-Driven Framework for Medical Imaging, Oct. 2023, IEEE Signal Processing Letters. [IEEEXplore]
S. Barbarossa, D. Comminiello, E. Grassucci, F. Pezone, S. Sardellitti, P. Di Lorenzo, Semantic communications Based on Adaptive Generative Models and Information Bottleneck, IEEE Communications Magazine, vol. 61, n. 11, pp. 36-41, Nov 2023. [Paper]
L. Parisi, S. Mulargia, F. Comunello, V. Bernardini, A. Bussoletti, C. R. Nisi, L. Russo, I. Campagna, B. Lanfranchi, I. Croci, E. Grassucci, F. Gesualdo, The vaccine conversation on TikTok in Italy: beyond classic vaccine stances, BC Public Health, April 2022.
C. Brignone, G. Mancini, E. Grassucci, A. Uncini, D. Comminiello, Efficient sound event localization and detection in the quaternion domain, IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 5, pp. 2453-2457, May 2022. [Paper][Slides]
Awarded as Best Track Manuscript by the IEEE Circuits and Systems Society at IEEE ISCAS 2022!
Book chapters
Book chapters
E. Grassucci, E. Cicero and D. Comminiello, Quaternion Generative Adversarial Networks, in Generative Adversarial Learning: Architectures and Applications, R. Razavi-Far, A. Ruiz-Garcia, V. Palade, and J. Schmidhuber, Springer International Publishing, pp. 57–86, January 2022. [Paper] [Preprint] [GitHub]
E. Grassucci, S. Scardapane, D. Comminiello, and A. Uncini, Flexible Generative Adversarial Networks with Non-Parametric Activation Functions, in Progress in Artificial Intelligence and Neural Systems, (Anna Esposito, Marcos Faundez-Zanuy, Francesco Carlo Morabito, Eros Pasero, Eds.), vol. 184 of Smart Innovation, Systems and Technologies, Springer, 2021.
Conference papers
Conference papers
E. Grassucci, G. Cicchetti, D. Comminiello, Closing the Gap in Multimodal Medical Representation Alignment, IEEE MLSP 2025.
E. Grassucci, G. Cicchetti, D. Comminiello, Closing The Modality Gap Enables Novel Multimodal Learning Applications, ICLR 2025 Re-Align Workshop [Paper]
R. F. Gramaccioni, C. Marinoni, E. Grassucci, G. Cicchetti, A. Uncini, D. Comminiello, FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders, IJCNN 2025 [Preprint]
E. Grassucci, G. Cicchetti, D. Comminiello, Contrastive Learning Enables Low-Bandwidth Semantic Communication, AAAI Workshop on Artificial Intelligence for Wireless Communications and Networking (AI4WCN), 2025.
J. D. J. Lopez, R. M. Fernandez-Alcala, J. Navarro-Moreno, Ruiz-Molina, E. Grassucci, D. Comminiello, β-Quaternion Centralized Fusion Estimation Problem Under First-Order Properness Conditions, IEEE Forum on Research and Technologies for Society and Industry Innovation (RTSI), 2024.
G. Cicchetti, E. Grassucci, J. Park, S. Barbarossa, D. Comminiello, Language-Oriented Semantic Latent Representation for Image Transmission, IEEE International Workshop on Machine Learning for Signal Processin (MLSP), 2024, London, UK. [Preprint]
E. Lopez, E. Grassucci, D. Comminiello, Towards Explaining Hypercomplex Neural Networks, IEEE WCCI 2024.
E. Grassucci, C. Marinoni, A. Rodriguez, D. Comminiello, Diffusion models for audio semantic communication, IEEE ICASSP 2024. [Preprint][Paper on IEEEXplore][Project page][GitHub]
E. Grassucci, Y. Mitsufuji, P. Zhang, D. Comminiello, Enhancing Semantic Communication with Deep Generative Models: An Overview, IEEE ICASSP 2024. [Preprint][Paper on IEEEXplore]
M. Mancanelli, E. Grassucci, A. Uncini, and D. Comminiello, PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functions, IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2023), Sept. 2023. [Preprint]
Honorable Top 5% Mention!
L. Sigillo, A. Marzilli, D. Moretti, E. Grassucci, C. Greco, and D. Comminiello, Sailing the SeaFormer: A Transformer-Based Model for Vessel Route Forecasting, IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2023), Sept. 2023.
G. Vieira, M. E. Valle, E. Grassucci, and D. Comminiello, Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling, IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2023), Sept. 2023. [Preprint]
Honorable Top 10% Mention!
E. Lopez, E. Chiarantano, E. Grassucci, and D. Comminiello, Hypercomplex Multimodal Emotion Recognition from EEG and Peripheral Physiological Signals, IEEE ICASSP, June 2023.
L. Sigillo, E. Grassucci, and D. Comminiello, StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation, IEEE Int. Symposium on Circuits and Systems. (ISCAS), Monterey, CA, USA, May 2023.
Page updated
Report abuse