4 papers
POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction
Brandon Smock, Libin Liang, Max Sokolov +4
Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundre…
PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction
Brandon Smock, Valerie Faucon-Morin, Max Sokolov +4
Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in dev…
Debiased Prediction Inference with Non-sparse Loadings in Misspecified High-dimensional Regression Models
Libin Liang, Zhiqiang Tan
High-dimensional regression models with regularized sparse estimation are widely applied. For statistical inferences, debiased methods are available about single coefficients or pr…
On Ridge Estimation in High-dimensional Rotationally Sparse Linear Regression
Libin Liang, Zhiqiang Tan
Recently, deep neural networks have been found to nearly interpolate training data but still generalize well in various applications. To help understand such a phenomenon, it has b…