Natural Language Processing
Our research group explores how intelligent agents understand and use language, with a growing focus on the integration of vision and language in large-scale models. At the intersection of cognitive science and artificial intelligence, we aim to advance machine understanding of human communication—spanning both purely linguistic and rich multimodal contexts.
We ask how language emerges, evolves, and operates as a system for conveying structured, grounded meaning. We investigate how computational systems can acquire, represent, and use this system in ways that mirror the versatility and flexibility of human cognition.
New Publications
Julius Mayer, Mohamad Ballout, Serwan Jassim, Farbod Nosrat Nezami, and Elia Bruni: iVISPAR – An Interactive Visual-Spatial Reasoning Benchmark for VLMs. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025).
Preprint available: https://arxiv.org/abs/2502.03214
Mohamad Ballout, Okajevo Wilfred, Seyedalireza Yaghoubi, Nohayr Muhammad Abdelmoneim, Julius Mayer, and Elia Bruni: Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMs. In Findings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Preprint available: https://arxiv.org/abs/2509.24640