2 papers
cs.LG2025
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
Aditya Gorla, Ryan Wang, Zhengtong Liu +2
We present CACTI, a masked autoencoding approach for imputing tabular data that leverages the structure in missingness patterns and contextual information. Our approach employs a n…
cs.CL2024
Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text
Michael Burnham, Kayla Kahn, Ryan Yank Wang +1
Social scientists quickly adopted large language models due to their ability to annotate documents without supervised training, an ability known as zero-shot learning. However, due…