SWIM: Learning What Matters from Behaviors for JEPA World Models
arXiv:2610.36662v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) enable world models to plan from images by predicting future embeddings. However, their visual prediction objectives do not explicitly incorporate task-relevant state information, so the physical state…
Read original reporting ↗This Observatory page contains only an indexed headline and short summary. It does not reproduce the article or substitute for the publisher’s reporting, corrections, context or terms.
Read the original at arXiv cs.RO ↗