Oregon State University · EECS

Karthika Mohan

Assistant Professor · Computer Science · Director, Causal Intelligence and Reasoning Laboratory

I work at the intersection of Artificial Intelligence and Causal Inference, driven by the conviction that machines will not truly reason until they can think causally. Before joining Oregon State, I was a postdoctoral scholar at UC Berkeley with Stuart Russell. My PhD is from UCLA, where I had the privilege of being advised by Judea Pearl, who gave causality its mathematical language, and I continue to build on that foundation.

Publications Meet the Lab
Karthika Mohan
karthika.mohan@oregonstate.edu
2109 Kelley Engineering Center
Oregon State University

Selected Publications

Planning under Distribution Shifts with Causal POMDPs

with Matteo Ceriscioli, ICAPS 2026

Do Finetti: On Causal Effects for Exchangeable Data

with Siyuan Guo, Chi Zhang, Ferenc Huszár, Bernhard Schölkopf, NeurIPS 2024

Graphical Models for Processing Missing Data

with Judea Pearl, Journal of the American Statistical Association (JASA), 2021

Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation

with Matteo Ceriscioli, NeurIPS 2025

Causal Inference with Non-IID Data under Model Uncertainty

with Chi Zhang, Judea Pearl, CLeaR 2023

Causal Inference with Non-IID Data using Linear Graphical Models

with Chi Zhang, Judea Pearl, NeurIPS 2022

Causal Graphs for Missing Data: A Gentle Introduction

Solo author · Invited chapter, ACM Books — Probabilistic and Causal Inference: The Works of Judea Pearl

Causal Discovery in the Presence of Missing Data

with Ruibo Tu, Cheng Zhang, Paul Ackermann, Hedvig Kjellström, Kun Zhang, AISTATS 2019

Estimation with Incomplete Data: The Linear Case

with Felix Thoemmes and Judea Pearl, IJCAI 2018

Missing Data as a Causal and Probabilistic Problem

with Ilya Shpitser and Judea Pearl · Featured in "What's Hot in UAI" at AAAI 2016, UAI 2015

Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data

with Guy Van den Broeck, Arthur Choi, Adnan Darwiche, and Judea Pearl, UAI 2015

Graphical Representation of Missing Data Problems

with Felix Thoemmes, Structural Equation Modeling: A Multidisciplinary Journal, 2015

Graphical Models for Recovering Probabilistic and Causal Queries from Missing Data

with Judea Pearl, NeurIPS 2014

On the Testability of Models with Missing Data

with Judea Pearl, AISTATS 2014

Graphical Models for Inference with Missing Data

with Judea Pearl and Jin Tian · Oral Spotlight, NeurIPS 2013

Teaching

AI-532 Causal Inference for Artificial Intelligence
AI-536 Probabilistic Graphical Models
CS-499 Introduction to Probabilistic and Causal Inference
CS-391 Social & Ethical Issues in Computer Science

Service

I serve as Associate Editor for the Journal of Causal Inference. I have been a Sponsorship Co-Chair for UAI 2022, and have served on program committees at NeurIPS, UAI, AAAI, IJCAI, ICML, and AISTATS over the years. At Oregon State University, I have contributed to a range of institutional service activities, including faculty hiring committees for the School of Electrical Engineering and Computer Science (AI searches) and the College of Earth, Ocean, and Atmospheric Sciences, among others. I review regularly for journals spanning machine learning, statistics, AI, epidemiology, psychology, political science, and sociology, including the Journal of Machine Learning Research (JMLR), Journal of the Royal Statistical Society (JRSS), Journal of the American Statistical Association (JASA), IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), and the Journal of Artificial Intelligence Research (JAIR), and have reviewed grant proposals for NSF, the Swiss National Science Foundation, and the Alfred P. Sloan Foundation.