5 papers
Simplifying Flow Matching Transformations with Low-Rank Mixture Models
Liam A. Kruse, Houjun Liu, Alexandros E. Tzikas +2
Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal de…
Foundational World Models Accurately Detect Bimanual Manipulator Failures
Isaac R. Ward, Michelle Ho, Houjun Liu +7
Deploying visuomotor robots at scale is challenging due to the potential for anomalous failures to degrade performance, cause damage, or endanger human life. Bimanual manipulators…
Sliced Distribution Matching based on Cumulative Distribution Functions with Applications to Control
Alexandros E. Tzikas, Arec Jamgochian, Nazim Kemal Ure +2
Computing the similarity between two probability distributions is a recurring theme across control. We introduce a unified family of distances between the probability distributions…
Scalable Importance Sampling in High Dimensions with Low-Rank Mixture Proposals
Liam A. Kruse, Marc R. Schlichting, Mykel J. Kochenderfer
Importance sampling is a Monte Carlo technique for efficiently estimating the likelihood of rare events by biasing the sampling distribution towards the rare event of interest. By…
Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
Liam A. Kruse, Alexandros E. Tzikas, Harrison Delecki +2
Importance sampling is a rare event simulation technique used in Monte Carlo simulations to bias the sampling distribution towards the rare event of interest. By assigning appropri…