Artemis Llabrés

PhD student · Computer Vision Center (CVC), Universitat Autònoma de Barcelona

I am part of the Vision, Language, and Reading Group, where I research multimodal models for document understanding.

My work focuses on large-scale training of vision-language models (VLMs), agentic AI systems that can reason and act over complex documents, and efficient VLMs for long-context document understanding, making it possible to process multi-page documents and large collections without prohibitive compute costs.

ICDAR 2026 Competition on Multimodal Reasoning over Documents in Multiple Domains Artemis Llabrés, Marc Serra Ortega, Tomás Ockier, Samuel Ortega Cuadra, Amritpal Singh, Christos Georgakilas, Andrey Barsky, Ernest Valveny, Dimosthenis Karatzas International Conference on Document Analysis and Recognition (ICDAR), 2026 Oral [Paper] [arXiv]
AdaNav: Query-Adaptive Multi-granularity Navigation for Long Document Understanding Yiming Xu, Eric López, Artemis Llabrés, Maximiliano Hormazábal, Ernest Valveny, Dimosthenis Karatzas International Conference on Document Analysis and Recognition (ICDAR), 2026 Oral [Paper]
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections Łukasz Borchmann, Jordy Van Landeghem, Michał Turski, Shreyansh Padarha, Ryan Othniel Kearns, Adam Mahdi, Niels Rogge, Clémentine Fourrier, Siwei Han, Huaxiu Yao, Artemis Llabrés, Yiming Xu, Dimosthenis Karatzas, Hao Zhang, Anupam Datta International Conference on Machine Learning (ICML), 2026 Oral [ICML] [arXiv]
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books Marc Serra Ortega, Emanuele Vivoli, Artemis Llabrés, Dimosthenis Karatzas IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025 [Paper] [arXiv]
Enhancing Document VQA Models via Retrieval-Augmented Generation Eric López, Artemis Llabrés, Ernest Valveny International Conference on Document Analysis and Recognition (ICDAR), 2025 [Paper] [arXiv]
ComicsPAP: Understanding Comic Strips by Picking the Correct Panel Emanuele Vivoli*, Artemis Llabrés*, Mohamed Ali Souibgui, Marco Bertini, Ernest Valveny, Dimosthenis Karatzas (*contributed equally) International Conference on Document Analysis and Recognition (ICDAR), 2025 Oral [Paper] [arXiv]
One Missing Piece in Vision and Language: A Survey on Comics Understanding Emanuele Vivoli, Mohamed Ali Souibgui, Andrey Barsky, Artemis Llabrés, Marco Bertini, Dimosthenis Karatzas arXiv preprint, 2024 [arXiv]
Image-Text Matching for Large-Scale Book Collections Artemis Llabrés, Arka Ujjal Dey, Dimosthenis Karatzas, Ernest Valveny International Workshop on Document Analysis Systems (DAS), 2024 Best Student Paper [Paper] [arXiv]
Retrieval Augmented Verification for Zero-Shot Detection of Multimodal Disinformation Arka Ujjal Dey, Artemis Llabrés, Ernest Valveny, Dimosthenis Karatzas arXiv preprint, 2024 [arXiv]