Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images

Aiqing Zhu, Yuting Pan, Qianxiao Li

Keywords: Latent dynamical system, Autoencoders, Learning dynamics, Continuity-preserving

TL;DR: Preserving continuity of latent states for learning continuous dynamics from discrete image observations

Confirmation Of Submission Requirements: I submit a previously published paper. It was published in an archival peer–reviewed venue on or after September 8th 2024, I specify the DOI in the field below, and I submit the camera-ready version of the paper.

DOI: https://iclr.cc/virtual/2025/poster/29910

Submission Number: 39