Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
The free-energy principle: a unified brain theory?Nature reviews neuroscience, 11(2):127–138
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
A POMDP-MHNG model demonstrates that representational synchrony emerges early in parent-infant co-regulation via collective predictive coding and persists despite heterogeneous generative models.
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.
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
CogniFold extends Complementary Learning Systems theory to three layers with a prefrontal intent layer and uses graph self-organization to build proactive agent memory from continuous event streams.
DynoSys offers a unified dynamic systems model integrating genetic, environmental, and neurobiological signals to analyze longitudinal behavioral phenotypes in adolescents via harmonized representations and survival or state-space modeling.
citing papers explorer
-
A First-Principles Theory of Slow Thinking and Active Perception
Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
-
Dynamic Representational Synchrony through Collective Predictive Coding: A Computational Model of Parent-Infant Homeostatic Co-Regulation
A POMDP-MHNG model demonstrates that representational synchrony emerges early in parent-infant co-regulation via collective predictive coding and persists despite heterogeneous generative models.
-
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.
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
-
Axiomatizing Neural Networks via Pursuit of Subspaces
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
-
CogniFold: Always-On Proactive Memory via Cognitive Folding
CogniFold extends Complementary Learning Systems theory to three layers with a prefrontal intent layer and uses graph self-organization to build proactive agent memory from continuous event streams.
-
DynoSys: A Dynamic Systems Framework for Multimodal Integration of Genetic, Environmental, and Neurobiological Signals
DynoSys offers a unified dynamic systems model integrating genetic, environmental, and neurobiological signals to analyze longitudinal behavioral phenotypes in adolescents via harmonized representations and survival or state-space modeling.