Tobia Poppi

I'm a PhD candidate in the National PhD in Artificial Intelligence at the University of Pisa, conducting my research at AImageLab, the research laboratory of the Department of Engineering "Enzo Ferrari" at the University of Modena and Reggio Emilia. I recently participated in an internship at Amazon Prime Video in Seattle. My specialization areas include AI Safety, Responsible AI, and Trustworthy AI.

Email / CV / Scholar / Github

Research

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. Some papers are highlighted.

	CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers arXiv, 2026 arXiv CounterVid introduces a framework leveraging diffusion models for image editing and video generation combined with the reasoning capabilities of video-language models to generate counterfactual videos that mitigate hallucinations, developed during an internship at Amazon Prime Video.
	Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Prefilling Attack Silvia Cappelletti, Tobia Poppi, Samuele Poppi, Zheng-Xin Yong, Diego Garcia-Olano, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara arXiv, 2025 arXiv We propose the prefilling attack, a structured natural-language prefix prepended to the model output, to steer the model to respond with a clean, valid option in multiple-choice question answering tasks, significantly improving accuracy and calibration.
	Hyperbolic Safety-Aware Vision-Language Models Tobia Poppi, Tejaswi Kasarla, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara CVPR, 2025 (Highlight) project page / arXiv / code / model HySAC, Hyperbolic Safety-Aware CLIP, models hierarchical safety relations to enable effective retrieval of unsafe content, dynamically redirecting it to safer alternatives for enhanced content moderation.
	Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models Samuele Poppi, Tobia Poppi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara ECCV, 2024 project page / bibtex / arXiv / code / models Vision-and-language model designed to mitigate the risks associated with NSFW content in AI applications. Safe-CLIP is fine-tuned to serve the association between linguistic and visual concepts, ensuring safer outputs in text-to-image and image-to-text retrieval and generation tasks.
	Towards Trustworthy AI: LLM Aligning for Offensive Content Removal Tobia Poppi, Samuele Poppi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara 2023 morethesis A study on aligning Large Language Models (LLMs) for offensive content removal, introducing the CAiA dataset and Safe-CLIP to ensure ethical and responsible AI-driven content moderation.
	Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation Elena Govi, Davide Sapienza, Carmelo Scribano, Tobia Poppi, Giorgia Franchini, Paola Ardòn, Micaela Verucchi, Marko Bertogna 2023 arXiv An investigation into background-induced bias in 6-DoF object pose estimation, revealing how ArUco markers in datasets like Linemod influence model predictions and proposing mitigation strategies using dataset augmentation and saliency map analysis.
	Deep Learning for DeepFake Detection Tobia Poppi, Elena Govi, Fabio Marinelli 2022 pdf A deep learning pipeline for DeepFake detection, leveraging custom datasets and an optimized Xception-based CNN to identify manipulated facial images with high accuracy."
	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 arXiv A comprehensive study of data labeling tools and techniques, evaluating their efficiency in person and traffic sign detection, as well as 3D pose estimation for robotic applications.

Participation to National and European Projects

	ELIAS - European Lighthouse of AI for Sustainability ELIAS aims at establishing Europe as a leader in Artificial Intelligence (AI) research that drives sustainable innovation and economic development.
	FAIR - Future Artificial Intelligence Research The FAIR project is a national scale, multidisciplinary initiative aimed at reimagining and developing large-scale foundational models. It explores research questions, methodologies, models, technologies, as well as ethical and legal frameworks for creating Artificial Intelligence systems capable of interacting and collaborating with humans.
	ELSA - European Lighthouse on Secure and Safe AI ELSA is a virtual center of excellence that will spearhead efforts in foundational safe and secure artificial intelligence (AI) methodology research.

Selected Activities as Reviewer

IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2025
Computer Vision and Image Understanding - Journal (CVIU) 2024
Pattern Recognition (PR) - Journal 2024
European Conference on Computer Vision (ECCV) 2024
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2024

Website created by Tobia | HTML template forked from Jon Barron