Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing approaches, however, require these mechanisms and their labels to be specified in advance. We ask whether a pretrained library can instead be adapted and grown from unlabele...
Lucas Thil, Jesse Read, G. Doquet et al.· 0 citations
SD-JEPA is proposed, a joint-embedding predictive world model whose latent is split into a small progression subspace and a large content subspace and whose latent becomes easier to read because its latent becomes easier to read.
Lucas Thil, Jesse Read, R. Kaddah et al.· arXiv.org· 13 citations· ⚡1
This work reframe the monitoring problem through a framework based on Phase Space Reconstruction (PSR), and shows that aligning the algorithmic bias with the geometric properties of the target system yields a pragmatic, traceable and easily deployable approach perfectly tailored to the realities of industrial constrain...
Martin Bonsergent-Brachet, Jesse Read, D. Abboud· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.