Research focus
About the research
When can a generative model that produces convincing video be trusted to answer what if questions?
Read the full research overview
Ramin Zabih is a Professor of Computer Science at Cornell University and Cornell Tech. His research interests have always been in computer vision, and his main focus now is bringing techniques from causal inference into it. The group studies counterfactual world models, generative models asked what would happen under a different action instead of what usually happens next. Three questions organize the work: diagnosing which action-situation pairs the model is hallucinating, fixing them by reweighting training, and certifying the result.
Selected publications
3 listedMambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
arXiv (Cornell University)
DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization
Europe PMC (PubMed Central)
A Stable and Efficient Covariate-Balancing Estimator for Causal Survival Effects
arXiv (Cornell University)
People & alumni
Team details haven’t been added. See the lab’s website for its current members.
Alumni details haven’t been added. Check the lab’s official website.
Sources & listing information
Find Research Labs maintains this page using public sources. The faculty member, lab, and university have not claimed or approved this listing. Listing a lab does not indicate endorsement, partnership, or a recruiting opportunity.
Request a correction or removal ↗ · About directory listings