Project

Memoro: Wearable Personal Memory Assistant

Wazeer Zulfikar

Project Contact:

Groups

Memoro is a wearable memory assistant powered by an always-on AI agent. It continuously listens to users and their surroundings, enabling queryless recall, proactive reminders, and daily summaries.

Older adults, projected to make up 17% of the population by 2050, are a key group facing memory challenges. Using a codesign approach, we refined Memoro for their needs and conducted a 10-day field study. Ten adults aged 60–86 integrated Memoro into daily life, managing appointments, tasks, and routines, while revealing new opportunities for reflection and social connection in everyday life.

Paper Link

Honorable Mention at Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 450, 1–18. https://doi.org/10.1145/3613904.3642450

Honorable Mention in Student Category by FastCompany World Changing Ideas '24

Our study of (N=20) participants engaged in a real-time conversation, demonstrated that using Memoro reduced device interaction time and increased recall confidence while preserving conversational quality.

Overall, Memoro is a step towards a personal memory assistant for everyone.

Publication Research

Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation

Wazeer Deen Zulfikar, Samantha Chan, and Pattie Maes. 2024. Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 450, 1–18. https://doi.org/10.1145/3613904.3642450

Research Topics

#human-computer interaction #artificial intelligence #health #wearable computing