Omar Khattab

Google Scholar


I’m a first-year CS Ph.D. student at Stanford, interested in scalable machine learning systems that tackle data-intensive Natural Language Understanding (NLU) tasks. I’m very fortunate to be advised by Matei Zaharia and Christopher Potts, with whom I’m currently exploring efficient and effective NLU models for Information Retrieval and Open-Domain Question Answering over massive document collections.

Before coming to Stanford, I got my B.S. in CS in May 2019 from CMU-Qatar, where I was very lucky to be supervised by Mohammad Hammoud.


ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
O. Khattab and M. Zaharia
SIGIR 2020 (to appear) | preprint | code

Finding the Best of Both Worlds: Faster and More Robust Top-k Document Retrieval
O. Khattab, M. Hammoud, and T. Elsayed
SIGIR 2020 (to appear)

PolyHJ: A Polymorphic Main-Memory Hash Join Paradigm for Multi-Core Machines
O. Khattab, M. Hammoud, and O. Shekfeh
CIKM 2018 | paper | code

LA3: A Scalable Link- and Locality-Aware Linear Algebra-Based Graph Analytics System
Y. Ahmad, O. Khattab, A. Malik, A. Musleh, M. Hammoud, M. Kutlu, M. Shehata, T. Elsayed
VLDB 2018 | paper | code