AI RESEARCH
Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts
arXiv CS.LG
•
ArXi:2605.00604v1 Announce Type: new Sparse MoE routing fails at domain transitions, where the current token belongs to one distribution and the next to another. In a controlled experiment (4 experts, 5 seeds), standard affinity routing assigns only 0.006 +/- 0.001 probability to the correct expert at the transition.