arXiv cs.LG
· Papers
SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors
arXiv:2608.04060v1 Announce Type: new Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps. We introduce SJEPA, a reconstruction-free JEPA framework that learns predictive representa