Five papers accepted at SIGIR 2025; leading the TREC 2024 Retrieval-Augmented Generation Track; introduced RankZephyr and RankVicuna projects; presented work on 'How Does Generative Retrieval Scale to Millions of Passages?' at EMNLP 2023.
Research Experience
Worked on LLMs at Yupp AI; interned at Google and Apple during his PhD; interned at Quebec Artificial Intelligence Institute (Mila), ContextLogic, and RBC Research during his undergraduate studies.
Education
PhD: David R. Cheriton School of Computer Science at the University of Waterloo, advised by Jimmy Lin; Undergraduate: University of Waterloo, majoring in Computer Science and Combinatorics and Optimization.
Background
Research interests lie at the intersection of Information Retrieval and Natural Language Processing, specifically in tasks such as Open Domain Question Answering, Fact Verification, and Document Ranking. Recently, he has been investigating the memory component of Large Language Models and the interplay between the inherent reasoning and memory modules.