Readable Is Not Steerable: Pre-Registered Tests of Physical Structure in Learned Fluid Representations
Read the original on arXiv AI →The paper reports three pre‑registered studies on 2D Navier‑Stokes flow that examine whether self‑supervised models organize their latent spaces around physical fluid quantities. In Study 1, a joint‑embedding predictive architecture (JEPA) fails to outperform an untrained network in capturing fluid dynamics, while a JEPA trained on non‑physical dynamics and a static invariance model perform equally well or better. Study 2 shows that plain autoencoders make enstrophy prominent in their slowest latent directions, and adding VICReg reduces this prominence but improves linear decodability. Study 3 constructs steerable latent directions (“dials”) via routing; a loudness dial is found in all eight trained models and a shape dial in three of five seeds, though neither control shows a shape dial. Across all studies, the content of a latent and what can be controlled through it diverge, and exploratory experiments reveal that supervised spectral‑shape directions do not affect the output when steered.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.