Please note: This PhD defence will take place in M3 4001 and online.

Xueguang Ma, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Jimmy Lin

Information seeking has been fundamental to human advancement, enabling knowledge acquisition, decision-making, and innovation across disciplines. However, traditional information retrieval systems often rely on specialized pipelines optimized for specific retrieval tasks, causing information silos that hinder unified information seeking.

In this talk, I will present our work in building unified document retrieval systems that break these information silos across three dimensions:

1. domain and language silos, where I demonstrate how LLM-based dense retrievers achieve strong generalizability across retrieval tasks and present frameworks for training small, generalizable retrievers through diverse LLM augmentation
2. modality silos, where I introduce a paradigm shift from text-based retrieval that relies on content extraction to directly encoding document screenshots, preserving all information including text, images, and layout in unified dense representations
3. space silos, where we show the importance of LLM-powered search agents in seeking and gathering information across disparate sources, and present fair and transparent evaluation benchmarks for assessing deep-search systems. 

To attend this PhD defence in person, please go to M3 4001. You can also attend virtually on Zoom.