Adding temporal memory via LIF, precision-weighted gating, and anticipatory prediction to MoE routers recovers effective expert selection at distribution transitions, with ablation confirming a super-additive beta-ant interaction.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A neuro-symbolic method using logic-augmented generation and active inference improves completeness and semantic quality when extracting tacit knowledge into machine-interpretable knowledge graphs for manufacturing procedures.
citing papers explorer
-
Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts
Adding temporal memory via LIF, precision-weighted gating, and anticipatory prediction to MoE routers recovers effective expert selection at distribution transitions, with ablation confirming a super-additive beta-ant interaction.
-
Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference
A neuro-symbolic method using logic-augmented generation and active inference improves completeness and semantic quality when extracting tacit knowledge into machine-interpretable knowledge graphs for manufacturing procedures.