Alberto Baldrati

Research Scientist at Samsung AI Cambridge

google_scholar_image.jpg

I am Alberto Baldrati, a Research Scientist at the Samsung AI Center in Cambridge, UK, focusing on computer vision and machine learning research.

Previously, I successfully defended my PhD thesis in February 2025 as part of the AI Italian National Doctorate program at the University of Pisa. During my PhD, I was hosted by the University of Florence and worked at the Media Integration and Communication Center (MICC) under the supervision of Prof. Marco Bertini and Andrew David Bagdanov.

During my PhD, my research interests revolved around vision and language, with a particular focus on prompt learning and composed image retrieval, and fashion image generation, focusing on multimodal fashion image editing and virtual try-on. As part of my PhD journey, I also had the opportunity to intern as a Computer Vision Research Scientist at Huawei Finland Research Center from March to September 2024, where I worked on video generation.

If you wish to learn more about my research or explore potential collaborations, please feel free to reach out via email!

News

Mar 3, 2025 Joined Samsung AI Center in Cambridge as a Research Scientist.
Feb 19, 2025 Successfully defended my PhD thesis at University of Pisa.
Jan 21, 2025 One paper about CLIP representations accepted at ICLR 2025.
Jul 9, 2024 One paper about prompt learning accepted at ECCV 2024.
May 5, 2024 We released the extended version of our ICCV2023 paper on composed image retrieval.

Selected Publications

2025

  1. ICLR
    Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
    M. Mistretta*A. Baldrati*, L. Agnolucci*, M. Bertini, and A. Bagdanov
    In The Thirteenth International Conference on Learning Representations, 2025

2024

  1. ECCV
    Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation
    M. Mistretta*A. Baldrati*, M. Bertini, and A. Bagdanov
    In European Conference on Computer Vision, 2024

2023

  1. ICCV
    Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing
    A. Baldrati*, D. Morelli*, G. Cartella, M. Cornia, M. Bertini, and R. Cucchiara
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
  2. ICCV
    Zero-Shot Composed Image Retrieval with Textual Inversion
    A. Baldrati*, L. Agnolucci*, M. Bertini, and A. Del Bimbo
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023