AI RESEARCH
MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning
arXiv CS.LG
•
ArXi:2605.08512v1 Announce Type: new Temporally contrastive representation learning induces a latent structure capable of reducing long-horizon planning to inference in a low-dimensional linear system. However, existing contrastive planning work learns a single latent geometry which cannot distinguish multiple valid behaviors trading task efficiency against risk exposure for the same start-goal query. We