Massimiliano Mancini

University of Trento

massi.jpg

Assistant Professor,

University of Trento

Trento, Italy

Hello! I am Massimiliano (Massi) a tenure-track Assistant Professor (RTD-b) at the Department of Information Engineering and Computer Science of University of Trento. The goal of my work is developing algorithms for increasing the generalization capabilities of deep architectures to new visual domains and semantic concepts, focusing on problems such as transfer learning, trustworthiness, and compositionality in computer vision. I am a member of ELLIS.

If you come to Italy, visit my wonderful medieval hometown Monte Santa Maria Tiberina!

news

May 15, 2025 I started my new position as a tenure-track assistant professor (RTDb) here at the Department of Information Engineering and Computer Science (DISI) of the University of Trento. Thanks to all who supported me during this journey! I am excited about the next steps and, if you are interested in joining this new journey, just drop me an email!
Apr 10, 2025 I will co-organize the ItalNet workshop at ICIAP 2025! Check our website for updates on the program and, if you are an early career researcher based in Italy, consider contributing (form)!
Mar 28, 2025 I will serve as Area Chair for NeurIPS 2025, in the Datasets and Benchmarks Track.
Feb 27, 2025 We came back stronger: 5/7 papers accepted at CVPR 2025! 😁 Congrats to Davide, Luca, Marco, Matteo, and Quentin! A pity for the two rejected ones, but ICCV is just around the corner…
Dec 20, 2024 Happy to be among the outstanding reviewers at WACV 2025!

selected publications

  1. notonlytext.png
    Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
    Davide Berasi , Matteo Farina , Massimiliano Mancini, and 2 more authors
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  2. comca.png
    Compositional Caching for Training-free Open-vocabulary Attribute Detection
    Marco Garosi , Alessandro Conti , Gaowen Liu , and 2 more authors
    In , 2025
  3. c2b.png
    Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers
    Quentin Guimard , Moreno D’Incà , Elia Peruzzo , and 2 more authors
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  4. 2sfs.png
    Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
    Matteo Farina , Massimiliano Mancini, Giovanni Iacca , and 1 more author
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  5. synvita.png
    Can Text-to-Video Generation help Video-Language Alignment?
    Luca Zanella , Massimiliano Mancini, Willi Menapace , and 3 more authors
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
  6. zero2024.png
    Frustratingly Easy Test-Time Adaptation of Vision-Language Models
    Matteo Farina , Gianni Franchi , Giovanni Iacca , and 2 more authors
    Advances in Neural Information Processing Systems (NeurIPS), Dec 2024
  7. openbias.png
    OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
    Moreno D’Incà , Elia Peruzzo , Massimiliano Mancini, and 6 more authors
    IEEE/CVF Conference on Computer Vision and Pattern Recognition, Dec 2024
  8. lavad.png
    Harnessing Large Language Models for Training-free Video Anomaly Detection
    Luca Zanella , Willi Menapace , Massimiliano Mancini, and 2 more authors
    IEEE/CVF Conference on Computer Vision and Pattern Recognition, Dec 2024
  9. iclr2024.png
    Vision-by-Language for Training-Free Compositional Image Retrieval
    Shyamgopal Karthik , Karsten Roth , Massimiliano Mancini, and 1 more author
    In International Conference on Learning Representations (ICLR) , Dec 2024
  10. vic.png
    Vocabulary-free Image Classification
    Alessandro Conti , Enrico Fini , Massimiliano Mancini, and 3 more authors
    Advances in Neural Information Processing Systems (NeurIPS), Dec 2023