Background
Since 2024, I am an Associate Professor at the University of Modena and Reggio Emilia, where I work on Deep Learning, Vision-and-Language integration, Large-Scale models and Multimedia. I teach in the courses of "Computer Vision and Cognitive Systems," Scalable AI, and Computer Architecture. My research interests span various areas, including Vision-and-Language integration, Multimodal Retrieval, Image and Video Captioning, Visual-Semantic alignment, Large-Scale model development, HPC and Embodied AI.
I have authored more than 140 publications in international journals and conferences. Currently, I serve as an Associate Editor for Computer Vision and Image Understanding and Pattern Recognition and act as an Area Chair for ICCV and major multimedia conferences. I am also a Scholar in the ELLIS society (European Laboratory for Learning and Intelligent Systems), where I coordinate the Modena ELLIS Unit.
Since 2021, I have held the position of deputy director at the Interdepartmental Center on Digital Humanities at the University of Modena and Reggio Emilia. Earlier in my career, in 2017, I worked at the Facebook AI Research laboratory in Paris under the supervision of Hervé Jégou. During that time, I worked on the development of a video-matching algorithm that was adopted in production on the social network to detect abusive content.
News
We have open research collaborator and post-doc positions within the MINERVA EU project, and the PRIN projects "MUCES - a Multimedia platform for Content Enrichment and Search in audiovisual archives" and "MUSMA: Multimedia Understanding meets Social Media Analysis". If you are interested, please get in touch!
Area Chair for ECCV 2026
Happy to share that I will serve as an Area Chair for ECCV 2026!
Québec-Emilia Romagna Dialogues
Happy to share that I will take part as moderator at the event “Intelligenza artificiale: prospettive etiche, socio-economiche e di governance”, held on 10 December 2025 at the Tecnopolo DAMA in Bologna. During the second session, I will introduce and guide a discussion featuring representatives from institutions, industry, and research on the societal and economic impact of AI.
This conference marks the first annual meeting within the collaboration between Québec and the Emilia-Romagna Region, dedicated to exploring key shared challenges in artificial intelligence.
Full Professor Habilitation
🎉 Happy to share that I've obtained the National Italian Habilitation (ASN - Abilitazione Scientifica Nazionale) as Full Professor (Fascia I) in Information Processing Systems (09/H1) 🎉
EuroHPC Extreme Scale grant
We are pleased to announce that our project "VISTA - Versatile Intelligent Systems for Tailored and Adaptive Next-Generation Multimodal AI" was accepted for the EuroHPC Extreme Scale grant, with an allocation of almost 1M GPU hours.
Paper accepted to NeurIPS 2025
Our paper, "vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models", has been accepted to NeurIPS 2025, Datasets and Benchmarks track!
Two papers accepted at BMVC 2025
Our papers "Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization" and "Verifier Matters: Enhancing Inference-Time Scaling for Video Diffusion Models" have been accepted to BMVC 2025!
Three papers accepted at ICCV 2025!
Our papers "MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models", "What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models" and "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation" have been accepted to ICCV 2025!
Area Chair for WACV 2026
Happy to share that I will serve as an Area Chair for WACV 2026!
Tutorial on AI and HPC at ICIAP 2025
We are glad to announce that we will organize, together with NVIDIA, a tutorial on AI and HPC at ICIAP 2025. The tutorial is organized as part of the MINERVA European Project.
Featured publications
vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
Leonardo Zini, Elia Frigieri, Sebastiano Aloscari, Lorenzo Baraldi
NeurIPS 2025, Datasets and Benchmarks track
What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models
Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara
ICCV 2025
Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
Luca Barsellotti, Lorenzo Bianchi, Nicola Messina, Fabio Carrara, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Rita Cucchiara
ICCV 2025
MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models
Vittorio Pipoli, Alessia Saporita, Federico Bolelli, Marcella Cornia, Lorenzo Baraldi, Costantino Grana, Rita Cucchiara, Elisa Ficarra
ICCV 2025
Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
Davide Caffagni, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
CVPR 2025
Hyperbolic Safety-Aware Vision-Language Models
Tobia Poppi, Tejaswi Kasarla, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara
CVPR 2025 Highlight
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
Federico Cocchi, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
CVPR 2025
Causal Graphical Models for Vision-Language Compositional Understanding
Fiorenzo Parascandolo, Nicholas Moratelli, Enver Sangineto, Lorenzo Baraldi, Rita Cucchiara
ICLR 2025
Courses
Scalable AI (2025/2026)
AI Engineering
Lorenzo Baraldi, Giuseppe Fiameni, Sara Sarto
Computer Vision and Cognitive Systems (2025/2026)
AI Engineering
Lorenzo Baraldi, Vittorio Cuculo
Architettura dei Calcolatori (2025/2026)
Course material
· Upcoming exams
Architettura dei Calcolatori
Rita Cucchiara, Lorenzo Baraldi