Brain-Artificial Intelligence Interfaces (BAIs)
The introduction of machine learning methods into the field of brain-computer interfacing (BCIs), which began almost two decades ago, has enabled unprecedented performance gains. Today, machine learning algorithms have become an indispensable component of BCIs. However, the field of machine learning has undergone a radical transformation in the past decade, giving rise to artificial intelligence (AI) systems that surpass human performance in many real-world tasks. In this talk, I argue that it is time for the BCI community to embrace these developments and build Brain-AI Interfaces (BAIs), i.e., systems that leverage the power of modern AI technologies to enable natural human-computer interaction. In particular, I suggest that to realize BAIs, we need to move beyond using AIs merely to decode neuronal signals and instead integrate AI agents into the neuroadaptive feedback loop. I will showcase a prototype of a conversational BAI and outline future directions and challenges in realizing the full potential of BAIs.

He earned his Dipl.-Ing. in Electrical and Information Engineering (2004) and his Dr.-Ing. (2008) from the Technical University of Munich.
His career includes postdoctoral research at the Max Planck Institute for Biological Cybernetics (2008–2013), leading a research group at the Max Planck Institute for Intelligent Systems (2013–2017), and serving as a Professor of Data Science at the Ludwig-Maximilians-Universität München (2017–2019).
At NAT’25, Prof. Grosse-Wentrup will deliver a keynote titled “Brain–Artificial Intelligence Interfaces (BAIs),” discussing the integration of modern AI technologies into BCIs to enable natural human–computer interaction.