AI RESEARCH
Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA
arXiv CS.LG
•
ArXi:2603.13265v1 Announce Type: new Modern self-supervised predictive architectures excel at capturing complex statistical correlations from high-dimensional data but lack mechanisms to internalize verifiable human logic, leaving them susceptible to spurious correlations and shortcut learning. Conversely, traditional rule-based inference systems offer rigorous, interpretable logic but suffer from discrete boundaries and NP-hard combinatorial explosion.