Curriculum Vitae
👨🎓 Education
Ph.D. in Artificial Intelligence
University of Pisa, Nov 2022 – Nov 2025 (expected)
- Research in computer vision and generative models
- Publications in ECCV, ACL Findings, ACMMM
- Under review: ICCV, BMVC, IJCV
M.Sc. in Computer Science
University of Modena and Reggio Emilia, 2020 – 2022
B.Sc. in Computer Science
University of Modena and Reggio Emilia, 2017 – 2020
🧑🔬 Experience
Research Intern
Huawei European Research Center – Munich, Germany
Nov 2024 – May 2025
- Research on video generation and world models
Research Intern
AImageLab – University of Modena, Italy
Feb 2022 – Nov 2022
- Vision Transformer pre-training methods (published at CVIU)
📚 Selected Publications
Baraldi, Amoroso, Cornia, Baraldi, Pilzer, Cucchiara
Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training, CVIU, 2025
Caffagni, Cocchi, Barsellotti, Moratelli, Sarto, Baraldi, Baraldi, Cornia, Cucchiara
The (R)Evolution of Multimodal Large Language Models: A Survey, ACL Findings, 2024
Baraldi, Cocchi, Cornia, Baraldi, Cucchiara
Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities, ECCV, 2024
Betti, Baraldi, Viglianisi, Baraldi, Cucchiara, Sebe
Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection, ECCV Workshop, 2024
Cappelletti, Baraldi, Cocchi, Cornia, Baraldi, Cucchiara**
*Adapt to Scarcity: Few-Shot Deepfake Detection via Low-Rank Adaptation, **ICPR, 2024
See Publications for the full list.
🧠 Projects
ELSA: European Lighthouse on Secure and Safe AI
- Designed and managed an international benchmark on deepfake detection
- Try it here
3D Digital Twin Reconstruction
- Built a POC pipeline to reconstruct 3D models of damaged vehicles from monocular images
- In collaboration with Prometeia and DAT S.r.l.
🛠️ Skills
Technical
- Python (5+ years), PyTorch (4+ years), Slurm HPC (4+ years)
- Experience with LLMs, Diffusion Models, Vision Transformers
Soft
- Leadership, Mentoring, Problem Solving