Josh DeOliveira

Josh DeOliveira

PhD Candidate @ WPI Data Science DAISY LAB | (He/Him) jcdeoliveira@wpi.edu

Publications

I am currently looking for internships in summer 2025!

You can also find a full list of my publications on my Google Scholar page.


Paper Figure
Agree to Disagree: Robust Anomaly Detection with Noisy Labels
Dennis Hoffmann, Peter VanNostrand, Lei Ma, Joshua DeOliveira , Lei Cao, Elke Rundensteiner.
(To Appear in) SIGMOD, 2025.
Paper Figure
The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training
Joshua DeOliveira , Walter Gerych, Elke Rundensteiner.
AAAI, 2025.
Paper Figure
GAN Stabilization Under Practical Training Assumptions.
Joshua DeOliveira , Walter Gerych, Elke Rundensteiner.
IEEE Big Data, 2024.
Paper Figure
HAR-CTGAN: A Mobile Sensor Data Generation Tool for Human Activity Recognition.
Joshua DeOliveira , Walter Gerych, Aruzhan Koshkarova, Elke Rundensteiner, Emmanuel Agu.
IEEE Big Data 4th Special Session on HealthCare Data, 2022.
Paper Figure
GAN for Generating User-Specific Human Activity Data From An Incomplete Training Corpus.
Walter Gerych, Harrison Kim, Joshua DeOliveira , MaryClare Martin, Luke Biquichhio, Kavin Chandrasekaran, Abdulaziz Alajaji, Hamid Mansoor, Elke Rundensteiner, Emmanuel Agu.
IEEE Big Data 3rd Special Session on HealthCare Data, 2021.
Paper Figure
Human Context Recognition: A Controllable GAN Approach.
Joshua DeOliveira , Harrison Kim, MaryClare Martin, Walter Gerych, Elke Rundensteiner.
IEEE MIT URTC, 2021.