BioCAS 2024 was all about tiny-yet-capable brain–machine interfaces. I presented VowelNet, our lightweight neural network for wearable speech imagery, on the main stage, and then walked the poster floor with Train-on-Request (ToR)—our on-device continual learning workflow for adaptive BMIs. Both pieces highlight how ultra-low-power embedded platforms can deliver rich human–machine interaction.
Xi’an International Conference Center, Xi’an, China
8 East Minguang Road, Xi'an, Shaanxi 710018
Conference snapshot
Oral spotlight:VowelNet: Enhancing Communication with Wearable EEG-Based Vowel Imagery (joint work with Victor Javier Kartsch Morinigo, Andrea Cossettini, Xiaying Wang, Luca Benini).
Poster tour:Train-On-Request (ToR): An On-Device Continual Learning Workflow for Adaptive Real-World Brain–Machine Interfaces with Cristian Cioflan and Lan Mei.
Theme: Making wearable BMIs responsive, robust, and comfortable enough for everyday use.
Making AI run on microwatts: I build foundation models for EEG, ECG, and other biosignals, and compress them until they run in real time on wearable devices, not in the cloud.