Giordano Cicchetti

DIET Dept, Sapienza

University of Rome

Building B (RM032), Floor 1, Room 114

Via Eudossiana 18 - 00184 Rome, Italy

Hey there👋, I am Giordano, a Computer Science Engineer and Ph.D. student in Information and Communication Technologies (ICT) at Sapienza University of Rome.

I am a member👨‍🔬 of the ISPAMM Lab, supervised by professor Danilo Comminiello and my main research topic is Representation Learning.

I completed both the BSc and the MSc at Sapienza University Of Rome, both in Computer Science Engineering🎓.

My research is focused on the field of Representation Learning, with a particular emphasis on Multimodal Representation Learning. My aim is to explore the intricate alignment of latent representations across diverse modalities, unraveling how these can be unified within a shared latent space, guided by the underlying semantics of the input data

Selected publications

Closing the Modality Gap Aligns Group-Wise Semantics

Eleonora Grassucci, Giordano Cicchetti, Emanuele Frasca, Aurelio Uncini, and Danilo Comminiello

In The Fourteenth International Conference on Learning Representations, 2026

arXiv Bib

@inproceedings{grassucci2026closing,
  title = {Closing the Modality Gap Aligns Group-Wise Semantics},
  author = {Grassucci, Eleonora and Cicchetti, Giordano and Frasca, Emanuele and Uncini, Aurelio and Comminiello, Danilo},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=RHPqr2egJO},
  bibtex_show = true,
  altmetric = true,
  selected = true
}

A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity

Giordano Cicchetti, Eleonora Grassucci, and Danilo Comminiello

In Advances in Neural Information Processing Systems (NeurIPS), 2025

arXiv Bib HTML Code

@inproceedings{cicchetti2025neurips,
  title = {A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity},
  author = {Cicchetti, Giordano and Grassucci, Eleonora and Comminiello, Danilo},
  year = {2025},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  bibtex_show = true,
  altmetric = true,
  selected = true
}

Gramian Multimodal Representation Learning and Alignment

Giordano Cicchetti, Eleonora Grassucci, Luigi Sigillo, and Danilo Comminiello

In The Thirteenth International Conference on Learning Representations, 2025

arXiv Bib Code Website

@inproceedings{cicchetti2024gramianmultimodalrepresentationlearning,
  title = {Gramian Multimodal Representation Learning and Alignment},
  author = {Cicchetti, Giordano and Grassucci, Eleonora and Sigillo, Luigi and Comminiello, Danilo},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=ftGnpZrW7P},
  bibtex_show = true,
  altmetric = true,
  selected = true
}

Language-Oriented Semantic Latent Representation for Image Transmission

Giordano Cicchetti, Eleonora Grassucci, Jihong Park, Jinho Choi, Sergio Barbarossa, and 1 more author

In 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 2024

DOI arXiv Bib Code

@inproceedings{10734812,
  author = {Cicchetti, Giordano and Grassucci, Eleonora and Park, Jihong and Choi, Jinho and Barbarossa, Sergio and Comminiello, Danilo},
  booktitle = {2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)},
  title = {Language-Oriented Semantic Latent Representation for Image Transmission},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-6},
  bibtex_show = true,
  altmetric = true,
  keywords = {Visualization;Image coding;Image communication;Text to image;Receivers;Signal processing;Vectors;Noise measurement;Image reconstruction;Signal to noise ratio;Semantic Communication;Semantic Coding;Generative Models;Generative Semantic Communication},
  doi = {10.1109/MLSP58920.2024.10734812},
  selected = true
}