D-JEPA
One geometry latent, reused across flow conditions and physics
Paper title D-JEPA: Design-Recoverable JEPA Representation with Swappable Physics Decoders
Paper arXiv 2609.33110PDF
A JEPA-style encoder computes a 128-number latent from the geometry alone; the operating conditions enter only through small FiLM-modulated neural-field decoders, one per physics. A training loss forces the design parameters to be linearly readable from the latent, and case-level variance terms stop all geometries collapsing to the same code.
Share on LinkedIn, X or Bluesky, or or .
Know related work that belongs here? Suggest a link
Something wrong on this page? Tell the editor