SOURCE-LINKED INTELLIGENCE

Dynamical phase selection controls compute scaling in looped transformers

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

A looped transformer performs inference by iterating a weight-tied map, making its computation a dynamical process whose cost is set by the resulting inference dynamics. Here we show that networks with identical architecture and objective, trained to identical accuracy, nevertheless realize distinct dynamical phases depending strongly on initialization, and that the bifurcation defining each phase determines how test-time compute scales. The phases are distinguished by their bifurcation mechanisms, including a saddle-node fold and a Neimark-Sacker-type transition to bounded nonstationary motio

Read original source ↗ Open in workspace

recordType

paper

region

Global