| 08:30 – 09:00 |
Registration and Welcome |
| 09:00 – 09:45 |
Keynote Talk 1: Thomas Ploetz, Georgia Institute of Technology, United States |
| 09:45 – 09:55 |
Tiny but Mighty: When Smart Rings Meet Large Language Models |
| 09:55 – 10:05 |
Optical Token Transmission for Secure IoT Device Discovery and Control in Ubiquitous Environments |
| 10:05 – 10:15 |
MemMod4CVQA: Using Memory Models to Infer Causal Relationships for Visual Question Answering on Life-Log Data |
| 10:15 – 10:45 |
Coffee Break |
| 10:45 – 11:30 |
Keynote Talk 2: Chiara Boldrini, Institute for Informatics and Telematics, CNR, Italy |
| 11:30 – 11:40 |
Can Large Language Models Identify Materials from Radar Signals? |
| 11:40 – 11:50 |
XR Exhibit+: An AI-enhanced XR Museum Guide based on Constructivism and Connectivism Theories |
| 11:50 – 12:00 |
Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homes |
| 12:00 – 12:10 |
Towards a Privacy-Preserving Approach for Seated Posture Monitoring Using CNN-Based mmWave Radar Sensing |
| 12:10 – 12:20 |
SugarScope: Estimating Sugar Concentration via Smartphone LiDAR Speckle Dynamics |
| 12:20 – 14:15 |
Lunch Break |
| 14:15 – 15:00 |
Keynote Talk 3: TBC |
| 15:00 – 15:10 |
Online Continual Learning for Building Automation on IoT Devices via Coreset Selection |
| 15:10 – 15:20 |
Imputation Matters: Evaluating the Impact of Missing Data Strategies on Interpretability in Clinical Time Series Models |
| 15:20 – 15:30 |
FuseLID: Vision-Language Model-Based Camera-Radar Fusion for Liquid Identification |
| 15:30 – 15:40 |
A Visual Context Aware Solution for Protecting Mobile Users from Visual Privacy Attacks |
| 15:40 – 15:50 |
Using LLMs to Generate Position Descriptions in Natural Language from Ultra-Wide Band Rangings Data |
| 15:50 – 16:15 |
Coffee Break |
| 16:15 – 16:25 |
iVAS: An Intelligent Visual Development Assessment System for Infants and Toddlers |
| 16:25 – 16:35 |
Bridging the Digital Gap in Healthcare Access: A Dual-Path Interface with AI Support for Elderly Users |
| 16:35 – 16:45 |
Design of a Multimodal Emotional Cognition AR System for Children with Autism Based on Generative AI |
| 16:45 – 17:00 |
Award Ceremony & Closing Remarks |