Profile Picture

Gordon Lim

gbtc (at) umich (dot) edu

I am graduating from the University of Michigan in April 2025.
I am broadly interested in improving machine learning robustness. My work includes developing benchmarks to advance robust learning methods and conducting human studies to investigate error patterns in human annotation.

Résumé Scholar GitHub

Publications

Towards Fair Pay and Equal Work: Imposing View Time Limits in Crowdsourced Image Classification

Gordon Lim, Stefan Larson, Yu Huang, Kevin Leach

arXiv:2412.00260
Paper

Robust Testing for Deep Learning using Human Label Noise

Gordon Lim, Stefan Larson, Kevin Leach

ICSE DeepTest 2025 (To appear)
Paper Code Project Dataset

Label Errors in the Tobacco3482 Dataset

Gordon Lim, Stefan Larson, Kevin Leach

WACV VisionDocs 2025 (To appear) / ICDAR Document Analysis Systems 2024 (Poster)
Paper Poster

On Evaluation of Document Classification using RVL-CDIP

Stefan Larson, Gordon Lim, Kevin Leach

EACL 2023
Paper

Evaluating Out-of-Distribution Performance on Document Image Classifiers

Stefan Larson, Gordon Lim, Yutong Ai, David Kuang, Kevin Leach

NeurIPS D&B 2022
Paper Poster