Eric Xing

I am a Ph.D. student in the Multimodal Vision Research Lab, part of the McKelvey School of Engineering at Washington University in St. Louis, where I work on computer vision and multimodal learing. I am advised by Nathan Jacobs.

I received my B.S. in Computer Science with a minor in mathematics from Western Kentucky University. I also worked with Dongwon Lee as part of an REU at Penn State University.

Email  /  CV  /  LinkedIn  /  Scholar  /  GitHub

Research

My research broadly lies in computer vision and multimodal learning. I am interested in learning representations from multimodal data for powerful and versatile AI systems.

We develop a probabilistic, multi-scale, and metadata-aware embedding space that connects audio, text, and overhead imagery.

An authorship obfuscation method that demonstrates a ~10x speedup over previous methods while outperforming them in terms of attack success, semantic preservation, and fluency.

Quantification and analysis of neural network decision-making criteria inconsistency and three algorithms to mitigate this inconsistency with minimal performance sacrifice.

Quantitative and clustering-based analyses of learned features spaces of U-Net architechtures for medical image generation.

A versatile online exam toolkit with plagarism and cheating detection as part of the vLab learning management system.

Interpretability over a new state-of-the-art pipeline for motorcycle crash severity predicition for the analysis of factors contributing to severe motorcycle crashes.

Thank you to Jon Barron for the site template.