Fifteen older adults used a wearable camera paired with a multimodal LLM in their own homes. It kept a running text diary of what happened around them and answered spoken questions like “where did I leave my glasses?” Participants located objects more successfully with the assistant than without it, and rated the experience positively.
Maniar, N., Chan, S. W. T., Zulfikar, W., Ren, S., Xu, C., & Maes, P. (2025). Proceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25).
Read the paper