Valentino Maiorca

Ph.D. Student at Sapienza, University of Rome. GLADIA research group.

prof_pic.jpg

My biography?

It's right there!

Towards a more general understanding of the latent shape of information I research how similar latent representations emerge in different neural networks, both artificial and biological, and how we can leverage this understanding for various applications.

I focus on intrinsic factors from input data (its semantics) revealing how networks process similar concepts, and extrinsic factors, like random initialization or data modality, which alter the space where these representations exist rathern than their structure.

My work involves formalizing “latent communication” to align different neural networks’ latent spaces. This has practical applications in deep learning model stitching, single-cell alignment in biology, and brain decoding in neuroscience.

By understanding the universal principles of data processing and the geometry of latent spaces, my work aims to drive advancements across multiple fields and positively impact both academic research and real-world applications.


Full CV available here.

Selected Publications

  1. COSYNE
    Multi-subject neural decoding via relative representations
    Valentino Maiorca, Simone Azeglio, Marco Fumero, Clémentine Dominé, Emanuele Rodolà, and Francesco Locatello
    In Cosyne Abstracts, 2024
  2. Relative representations enable zero-shot latent space communication
    Luca MoschellaValentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, and Emanuele Rodolà
    In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023, 2023
  3. ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training
    Antonio Norelli, Marco Fumero, Valentino MaiorcaLuca MoschellaEmanuele Rodolà, and Francesco Locatello
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
  4. Accelerating Transformer Inference for Translation via Parallel Decoding
    Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, and Emanuele Rodolà
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023
  5. Latent Space Translation via Semantic Alignment
    Valentino MaiorcaLuca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, and Emanuele Rodolà
    In Thirty-seventh Conference on Neural Information Processing Systems, Jul 2023
  6. From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
    Irene CannistraciLuca Moschella, Marco Fumero, Valentino Maiorca, and Emanuele Rodolà
    In The Twelfth International Conference on Learning Representations, Jul 2024