EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
Annealing in Variational Inference Mitigates Mode Collapse:
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Proper EFE-based planning is VFE plus planning and epistemic entropy corrections, realized by channel-reparameterized message passing that captures novelty.
Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.
citing papers explorer
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
-
What Type of Inference is Active Inference?
Proper EFE-based planning is VFE plus planning and epistemic entropy corrections, realized by channel-reparameterized message passing that captures novelty.
-
The critical slowing down in diffusion models
Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.