The Horizon Europe-funded project MAMMOth (Multi-Attribute, Multimodal Bias Mitigation in AI Systems) officially concluded on 31 October 2025 after three years of pioneering work to make Artificial …
The Artificial Intelligence and Machine Learning (AIML) group, led by Prof. Dr. Eirini Ntoutsi, researches and develops robust and responsible Artificial Intelligence for real-world settings.
Our main research focuses are:
-
Robust AI, i.e., reliability under data biases, distribution shifts, adversarial manipulation, and other real-world challenges.
-
Responsible AI, including fairness-aware learning and explainable AI (XAI), with a focus on lifecycle-wide analyses and explicitly modeling objectives beyond pure downstream task performance.
-
Generative AI for improving data quality, addressing data scarcity, and supporting robust learning.
We apply our methods across a wide range of domains, including education, social networks, banking, agriculture, manufacturing, and engineering.
Our group is part of the research institute CODE for Cybersecurity and Smart Data and the Department of Computer Science at UniBw Munich. Previously, the group was based at the Freie Universität Berlin and Leibniz Universität Hannover/ L3S Research Center.
