Skip to content

2025-2026 Seminar Series

Link to older Seminar Series

Upcoming Seminar

Speaker: Ani Majumdar (Princeton University)

Flyer

Title: Video World Models That Know When They Don't Know

Abstract: World models in the form of action-conditioned video generation models have the potential to serve as general-purpose simulators for robotics. Their ability to generate photorealistic observations, simulate complex physical interactions, and be improved with data make them an attractive alternative to traditional physics-based simulation for policy evaluation, data generation, and inference-time planning. In this talk, I will highlight our recent work from Google DeepMind on using video models as "simulators" for evaluating generalist robot policies for performance, generalization, and safety. I will then describe how the data-driven nature of video world models also leads to outputs that are not always trustworthy. Indeed, current models exhibit a variety of hallucinations: objects can appear or disappear, deform in unrealistic ways, or move in a manner that defies physics. I will argue that knowing when and where to trust the generations of world models is critical in robotics applications. I will describe recent work from my group at Princeton on training world models that output dense confidence estimates at the subpatch (channel) level, precisely localizing the uncertainty in each generated video frame. Through extensive experiments on large-scale robotics datasets (DROID and Bridge), we demonstrate how our method allows us to identify uncertainty in a calibrated manner, while also enabling out-of-distribution detection in unseen domains. To our knowledge, this is the first work on calibrated uncertainty quantification for action-conditioned video models.

Date: Thursday, January 15th, 2026

Time: 09:00-10:00 AM EST

Link: https://dartmouth.zoom.us/j/94765993258?pwd=aErnkjFBqQaOTEgonxZkeNTbojHRbp.1

Date Speaker Title YouTube
Dec. 11, 2025 Heng Yang Semidefinite Relaxations for Robot Perception and Control: From Theory to Practice and Back (link)
Jan. 15, 2026 Anirudha Majumdar Video World Models That Know When They Don't Know
Jan. 26, 2026 Thomas Lew Topic coming soon
March 12, 2026 Yan Gu Topic coming soon
April 9, 2026 Somil Bansal Topic coming soon