Category: News

Paper accepted to NeurIPS 2025 Workshop on Learning from Time Series for Health (TS4H)

Happy to share that the paper RAxSS: Retrieval-Augmented Sparse Sampling for Explainable Variable-Length Medical Time Series Classification has been accepted to the Learning from Time Series for Health (TS4H) workshop at NeurIPS 2025 as a joint effort by Aydin Javadov and co-authors. They introduce a lightweight, retrieval-augmented convex aggregation approach for clinical time series. Evaluated…
Read more

Google PhD Summit 2025 in Warsaw

Our PhD student Aydin attended the Google PhD Summit 2025 in Warsaw, which was an exclusive event bringing together talented PhD researchers from across Europe and Google’s leading scientists and engineers! It was a great opportunity for valuable networking with Googlers and fellow PhD students, and for gaining insights into the latest developments in AI…
Read more

Swiss {ai} Weeks with CTRL+ALT+RELAX Exhibition

How is AI shaping the way we work? During Swiss {ai} Weeks, the exhibition CTRL+ALT+RELAX invites you to explore how new technologies influence your daily work life. – Join a guided tour– Try out interactive applications, for example, how conscious breathing impacts your brain activity and heart rate– Participate in a workshop with your team…
Read more

VRxBioRelax Showcased at IEEE Telepresence 2025

At this year’s IEEE Telepresence conference in Leiden, the Mobiliar Lab for Analytics at ETH Zurich and Delsys Europe joined forces to showcase VRxBioRelax — an open-source application that combines immersive virtual reality with real-time EMG biofeedback using Delsys Trigno Avanti sensors and the Delsys Python API. The project explores how physiological signals can make…
Read more

Transparent Explanations and the Personalisation–Privacy Paradox in Digital Health

Would you want transparent explanations about how your data is used in personalised healthcare services? Most people say yes, but in practice, these explanations only increase privacy concerns — a phenomenon termed the Personalisation–Privacy paradox. In our new paper, authored by Dr. Joseph Ollier in collaboration with Dr. Marcia Nißen and Dr. Prof. Florian von…
Read more

Emotion, Cognition, and Immersive Technologies: Towards Adaptive Interventions for Mental Wellness

Last week, Rayna Ney from Mobiliar Lab for Analytics at ETH Zurich (ETH Zürich) gave a talk at the Media Informatics Group (LMU). Titled “Emotion, Cognition, and Immersive Technologies: Towards Adaptive Interventions for Mental Wellness,” her talk explored how we can support user mental wellbeing in contexts such as VR and how this can translate…
Read more

Can EMG coupled with a VR experience act as a therapeutic aid to modulate stress?

Our PhD candidate and researcher Melanie Baumgartner joined XR4Rehab alongside Delsys to demo VRxBioRelax —a real-time EMG biofeedback experience that brings embodiment and cognition into sharp focus. By streaming trapezius signals from Delsys Trigno® Avanti sensors into a VR landscape, participants can literally see and steer the interplay of muscle tension and progressive relaxation, stress,…
Read more

Generative AI for Wellness Applications via User Generated Immersive Virtual Environments

How can Generative AI empower users to actively shape immersive environments tailored for personal wellness? We’re excited to announce that Rayna Ney presented her work “Generative AI for Wellness Applications via User Generated Immersive Virtual Environments” at the CHI 2025 workshop on Generative AI and Human-Computer Interaction (GenAICHI 2025). In her paper, Rayna explores how…
Read more

Are Machines Becoming Emotionally Aware? Our Design Explores How Robots Could Adapt to Human States

We were thrilled to present our research, BioSyncHRI, a real-time adaptive system that integrates biosignals like EEG, sEMG, and HRV into VR surgical simulators at at CHI 2025 in Yokohama as part of the Workshop on Envisioning the Future of Interactive Health. In this research, we examine how robots can adjust to the emotional and cognitive states of human operators—improving…
Read more

Adaptive Confidence-Weighted LLM Infusion for Financial Reinforcement Learning

How can we make financial AI models more trustworthy, cautious, and accurate in their market valuations? We’re happy to share that Aydin Javadov, PhD student at Mobiliar Lab for Analytics at ETH Zurich, coauthored a paper presented at the 2025 IEEE International Conference on Intelligent Data and Security (IDS), in the special track on Financial Reinforcement Learning…
Read more