David Cho
dc424[at]duke[dot]edu
Hello! I go by David Cho, but I prefer to use my Korean name, Dong Heon Cho, for academic publications. I am currently a fourth-year PhD candidate in Computer Science at Duke University, advised by Professor Boyuan Chen in the General Robotics Lab. Before joining Duke, I earned my Bachelor's and Master's degrees from Columbia University. My research interests center on leveraging machine learning and artificial intelligence to advance scientific discovery and simulation. My recent work focuses on developing data-driven methods for discovering and analyzing dynamical systems from observations with minimal reliance on prior physical knowledge, as well as improving the accuracy and generalizability of physics-based simulations, particularly for sim-to-real transfer in robotics.
News
Presented our work on Residual Acceleration Field Learning (RAFL) at IROS 2026.
Successfully passed my PhD preliminary examination.
Delivered a talk at the AAAI Fall Symposium on Integrated Approaches to Computational Scientific Discovery.
Began my PhD in Computer Science at Duke University.
Publications
RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning. (IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2026).
Automated Discovery of Continuous Dynamics from Videos (npj Artificial Intelligence, 2026).
CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations (ICLR 2023).
"I Want to Figure Things Out": Supporting Exploration in Navigation for People with Visual Impairments (ACM CSCW 2023).
Teaching
Duke University
Teaching Assistant
January 2024 - May 2024
- CS345 GRAPHICS SOFTWARE ARCHITECTURE