← Search

Hongyi Ye

1 accepted papers

2026

Incomplete Data, Complete Dynamics: A Diffusion Approach

ICLR 2026poster

Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inherently incomplete and irregularly sampled, posing significant challenges for existing data-driven approaches. In this work, we propose a principled diffu…

Cited by 0SourceScholar