Moreno D'Incà

prof_pic.jpg

via Sommarive, 9, Povo Trento, Italy

Hi there! I am Moreno D’Incà a Ph.D. student at the Multimedia and Human Understanding Group - University of Trento (Italy), under the supervision of Prof. Nicu Sebe. My research focuses on safety and fairness for Multimodal LLMs and Generative AI.

In summer 2025, I have joined Amazon AGI in Los Angeles for a six-months internship working on local search tasks within the Amazon Alexa team.

Previously, I earned my Master’s degree in Artificial Intelligence from the University of Trento (Italy) after completing my Master’s thesis at the Queen Mary University of London, an opportunity provided by the AI4Media Junior Fellows Exchange Program.

news

Sep 24, 2026 MARS is accepted to NeurIPS 2026!
Oct 20, 2025 UWM is accepted to WACV 2026!
Jul 20, 2025 GradBias is accepted to TPAMI
Jun 16, 2025 I have joined Amazon AGI in Los Angeles as Applied Scientist Intern 🚀
Feb 27, 2024 OpenBias is accepted as Highlight paper (top 11.9%) at CVPR 2024! 🚀

selected publications

  1. NeurIPS
    Harnessing Textual Refusal Directions for Multimodal Safety
    Moreno D’Incà , Nicu Sebe , and Massimiliano Mancini
    In Advances in Neural Information Processing Systems , 2026
    PDF Code
  2. EMNLP
    ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
    Shaghayegh Kolli , Sina Emami , Moreno D’Incà , and 4 more authors
    In Conference on Empirical Methods in Natural Language Processing , 2026
    PDF Code
  3. WACV
    Safe Vision-Language Models via Unsafe Weights Manipulation
    Moreno D’incà , Elia Peruzzo , Xingqian Xu , and 3 more authors
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , 2026
    PDF Code
  4. TPAMI
    GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
    Moreno D’Incà , Elia Peruzzo , Massimiliano Mancini , and 3 more authors
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
    PDF Code
  5. CVPR
    Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers
    Quentin Guimard , Moreno D’Incà , Massimiliano Mancini , and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2025
    PDF Code
  6. CVPR
    OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
    Moreno D’Incà , Elia Peruzzo , Massimiliano Mancini , and 6 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    PDF Code
  7. WACV
    Improving Fairness Using Vision-Language Driven Image Augmentation
    Moreno D’Incà , Christos Tzelepis , Ioannis Patras , and 1 more author
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , 2024
    PDF Code
  8. IEE Access
    Unleashing the Transferability Power of Unsupervised Pre-Training for Emotion Recognition in Masked and Unmasked Facial Images
    Moreno D’incà , Cigdem Beyan , Radoslaw Niewiadomski , and 2 more authors
    IEEE Access, 2023
    PDF