Scholar
Omar Khattab
Google Scholar ID: Lwr5ozgAAAAJ
MIT EECS & CSAIL
Citations & Impact
Citations
13,276
H-index
22
i10-index
27
Publications
20
Co-authors
29
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including 'Reasoning-Intensive Regression', 'GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning', 'WARP: An Efficient Engine for Multi-Vector Retrieval'. Won Best Paper Award at SIGIR 2025.
Research Experience
- Worked as a Research Scientist at Databricks. Research directions include: 1. Building Reliable AI Systems with Language Models; 2. Developing Effective & Efficient Retrieval Models. Developed influential open-source research systems such as DSPy framework and ColBERT retrieval model.
Education
- Ph.D. in Computer Science from Stanford, advised by Matei Zaharia and Christopher Potts, and part of Stanford NLP. During his Ph.D., he was supported by the Apple Scholars in AI/ML PhD Fellowship.
Background
- Assistant Professor at MIT EECS and a member of CSAIL. Research interests include Natural Language Processing (NLP) and AI systems, specifically how to program intelligent software systems that are partly specified in natural language, process natural language at scale, and optimize quality and cost using language models.
