Predictive coding equals proximal gradient descent on MAP problems, with priors setting nonlinearities via proximal operators and yielding leaky firing-rate networks plus hierarchical MRFs.
Active inference: A process theory.Neural Computation, 29(1):1–49, 2017
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
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.
PUMA applies the Free Energy Principle to maintain beliefs over latent user states and select actions by minimizing expected free energy in multi-turn personalized dialogues.
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
-
Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation
PUMA applies the Free Energy Principle to maintain beliefs over latent user states and select actions by minimizing expected free energy in multi-turn personalized dialogues.