LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Thursday, 5 November 2026

World-model latents can read physics without letting you steer it

A three-study test finds that learned fluid representations can expose physical quantities without making those quantities controllable, a warning for anyone using latents to edit or simulate systems. On 2D decaying Navier-Stokes flow, autoencoders made enstrophy prominent with correlations of 0.80–0.86, but a supervised direction that nearly perfectly read spectral shape moved nothing when steered. Label-free rules found a shape-control dial in only 3 of 5 fresh seeds, while all 8 trained models yielded a scale dial.

Read the source: arxiv.org ↗In the 5 November issue →