Omar Khattab

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Natural Language Processing (2)Interpretability & Mechanistic Interp (1)Recommendation & Information Retrieval (1)RLHF & Preference Learning (1)

Frequent co-authors

Matthew Russo (1)Tianyu Li (1)Zhuohan Gu (1)Michael Cafarella (1)

Papers (2)

Aug 10, 2026

Matthew Russo +62w ago·also Fudan, Shanghai Innovation

Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries

Users can now interactively critique and optimize their AI-driven data queries, transforming opaque analytics into a transparent, controllable process.

Matthew Russo, Tianyu Li, Zhuohan Gu +4

Interpretability & Mechanistic Interp Natural Language Processing Recommendation & Information Retrieval

May 21, 2026

MIT CSAILMay 21, 2026·also Affiliation:, Improbable AI Lab, KU

Vector Policy Optimization: Training for Diversity Improves Test-Time Search

LLMs trained with Vector Policy Optimization (VPO) learn to produce diverse solutions that unlock previously unsolvable problems in evolutionary search, outperforming models optimized for single scalar rewards.

Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld +6

Natural Language Processing RLHF & Preference Learning Tool Use & Agents