most citedThe Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing stat.MLShow all

1 paper · 1 filter

stat.ML2026

Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

Seth Dobrin, Łukasz Chmiel

Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability, the linear recovery of the world's tr…