Physics-Informed Diffusion Modelling for Medical Imaging Physics-guided, efficient diffusion models for high-fidelity medical image reconstruction. Efficient Face Presentation Attack Detection Spatio-temporal deep learning for robust, lightweight face anti-spoofing. Provoking LLMs by LLMs: Red Teaming for Harmful Content Detection A red team framework for proactively detecting harmful content generated by large language models. Non-Visual Information Transmission for the Blind and Visually Impaired Tactile and multi-modal AI interfaces that make visual information (color, art, text) accessible. Robust Indoor Location Estimation Sensor fusion and deep learning for precise, infrastructure-light indoor positioning and navigation.
