Dzung Dinh

I am a Ph.D. student in Computer Science at UNC-Chapel Hill, working closely with Prof. Junier Oliva in the LUPA Lab. My research focuses on machine learning methods for reliable prediction and efficient information acquisition, with applications in active feature acquisition, longitudinal data, and trustworthy ML for scientific discovery.

In summer 2026, I was a Research Science Intern at Hitachi America, Ltd.'s Financial Innovation Lab, where I worked on detecting contradictions in financial documents.

I received my B.S. in Computer Science with a minor in Mathematics from Dickinson College, where I worked with Prof. John MacCormick on object detection and computer graphics projects. Earlier, I was an intern at the UIUC Coordinated Science Laboratory and a community researcher at Cohere For AI.

Dzung Dinh profile photo
ddinh (at) cs.unc.edu

Education

Publications (* denotes equal contribution)

  1. Contrastive Nonmyopic Objective Cost-Tradeoff Acquisition for Longitudinal Data teaser NeurIPS
    Contrastive Nonmyopic Objective Cost-Tradeoff Acquisition for Longitudinal Data
    Dzung Dinh*, Boqi Chen*, Yunni Qu, Marc Niethammer, Junier Oliva
    Conference on Neural Information Processing Systems (NeurIPS), 2026.
  2. Information Templates: A New Paradigm for Intelligent Active Feature Acquisition teaser NeurIPS
    Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
    Hung-Tien Huang*, Dzung Dinh*, Junier B. Oliva
    Conference on Neural Information Processing Systems (NeurIPS), 2026.

Last updated: September 2026