Groups

Bayesian inference and learning applied to audio, speech and language.

The Computational Learning and Computational Linguistics group develops techniques to improve our understanding of how linguistic structural and meaning properties are represented in current machine learning models, across many languages.

The Energy Informatics Group focuses on advancing the modeling and simulation of energy transition pathways, with a particular emphasis on the dynamic evolution of buildings energy systems and urban comfort.

We develop and apply artificial intelligence approaches to advance health, spanning the molecular, individual and societal scales.

The Human-centered Robotics and AI’s research lies at the intersection of robotics, human-robot interaction, machine learning, and participatory design, with the goal of creating robots that are physically useful and socially acceptable.

Trustworthy identity in the age of AI

The Machine Learning group develops and analyzes algorithms to train, use, and evaluate AI models. Its goal is to improve these models while deepening the scientific understanding of their fundamental principles.

The Media & Information Interaction Group develops AI systems for media and information interaction grounded in language, human interpretation, and information practices.

The Medical AI group develops clinically grounded, trustworthy AI for medical imaging, physiological signals, and health data.

The Natural Language Understanding group works at the intersection of machine learning and natural language processing, with an emphasis on representation learning for the meaning of language, attention-based deep learning models, and structured prediction.

The Neuro-symbolic AI Group develops models which are capable of complex, controlled, transparent, data-efficient and safe reasoning.

We develop scene understanding and behavioral foundation models to decode human activities and behaviors from real-world sensors, spanning computer vision, deep learning, multimodal signal processing, and the social sciences. Our research focuses on recognizing and interpreting non-verbal behaviors, from gaze and attention to gestures and social dynamics, with applications in health, robotics, and industrial systems.

The Robot Learning & Interaction group focuses on human-centered robotics applications in which the robots can acquire new skills from only few demonstrations and interactions.

The Signal Processing for Communication group focuses on establishing digital algorithms tackling a wide range of challenges arising in human communication.

The Social Computing research group operates at the intersection of computing and the social sciences to develop computational methods for sensing, analyzing, and interpreting human behavior in real-world contexts.

Speech and audio processing, spoken language understanding