William Gay — accepted AI-conference papers

2026

Sampling and Identity-Testing Without Approximate Tensorization of Entropy

William He, Nicholas Kocurek, William Gay, Ryan O'Donnell

ICML 2026poster

We study the problems of approximate sampling from and distribution testing of \emph{mixture models}, where the modes satisfy a functional inequality called \textit{approximate tensorization of entropy} (ATE). While it is known that ATE makes these tasks more efficient in the unimodal setting, mixtu…

Cited by 0 Source ↗Scholar ↗

2024

cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers

Anirudh Sundar, Jin Xu, William Gay, Christopher Gordon Richardson, Larry Heck

NeurIPS 2024poster

An emerging area of research in situated and multimodal interactive conversations (SIMMC) includes interactions in scientific papers. Since scientific papers are primarily composed of text, equations, figures, and tables, SIMMC methods must be developed specifically for each component to support the…

Cited by 0 Source ↗PDF ↗Scholar ↗