CS Events

Qualifying Exam Multi-Modal Memory Management System for Building Personalized LLM Agents
Export Event Save iCal Send to Google Calendar Send to Yahoo Calendar Send to Outlook Live Send to Microsoft Outlook Save iCal Preserve formatting in description (only supported in some calendar applications) Close Tuesday, December 16, 2025, 09:30am - 10:15am

Speaker: Zihe Ye

Bio

Location : CoRE 305

Committee: 

Prof. Lesia Semenova

Prof. Ruixiang Tang

Prof. Desheng Zhang

Prof. Yongfeng Zhang

Event Type: Qualifying Exam

Abstract: Long-term conversational agents struggle to maintain deep context and personal consistency using single-axis memory systems. This research addresses this by developing LocalMem, a novel memory system that integrates multi-modal personalized history with a robust hierarchical architecture. Built on the principles of utilizing multi-modality in memory management, LocalMem organizes data not only across temporal and semantic dimensions but also incorporates information from diverse user activity streams, including text, visual, and computer-usage logs. This rich, multi-dimensional data is curated and stored in a scalable memory structure, enabling the system to provide LLMs (like Gemini or ChatGPT) with deep, localized, and contextually complete recollections of the user's past activities. By leveraging hybrid management strategies against this multimodal memory, LocalMem achieves superior long-term personalization, validating a crucial path toward building truly stateful and human-like agents.

Organization: 

Contact  Professor Lesia Semenova

Zoom Link: https://rutgers.zoom.us/j/4452239702?pwd=VU5lTkpUeFM5YVBwTVFmR2xWNmh5dz09&omn=95781102232