Tobia Poppi

prof_pic.png

Modena, Italy 41100

I’m a PhD candidate in the National PhD in Artificial Intelligence at the University of Pisa, specializing in AI Safety, Responsible AI, and Trustworthy AI.

My research focuses on advancing Generative AI and Multimodal architectures, aiming to bridge the gap between cutting-edge deep learning technologies and ethical alignment with human values.

Passionate about leveraging AI to solve complex societal challenges, I am dedicated to ensuring AI systems are safe, transparent, and aligned with responsible principles, driving innovation with a human-centric approach.

selected works and publications

  1. Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
    Samuele Poppi, Tobia Poppi, Federico Cocchi, Marcella Cornia, and 2 more authors
    In Proceedings of the European Conference on Computer Vision 2024
  2. Towards Trustworthy AI: LLM Aligning for Offensive Content Removal
    Tobia Poppi, Samuele Poppi, Lorenzo Baraldi, Rita Cucchiara, and 1 more author
    2023
  3. Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation
    Elena Govi, Davide Sapienza, Carmelo Scribano, Tobia Poppi, and 4 more authors
    2023
  4. Deep Learning for DeepFake Detection
    Tobia Poppi, Elena Govi, and Fabio Marinelli
    2022
  5. Il labelling: i migliori tool disponibili e la loro applicazione per il rilevamento di persone e cartelli stradali e per la pose estimation di oggetti 3D
    Tobia Poppi
    2021