7 papers
Path-Measure Dynamics of Attention-Driven World Models: A Nonlocal Onsager--Machlup Approach
Gunn Kim
Attention enables a world model to condition on its entire history, providing long-term memory that facilitates long-range predictions. While the local Onsager--Machlup theory in o…
A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility
Gunn Kim
We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a…
Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning
Gunn Kim
Continual learning in artificial neural networks is fundamentally limited by the stability--plasticity dilemma: systems that retain prior knowledge tend to resist acquiring new kno…
Critical Scaling and Metabolic Regulation in a Ginzburg--Landau Theory of Cognitive Dynamics
Gunn Kim
We formulate a phenomenological effective field theory in which biological intelligence emerges as a macroscopic order parameter sustained by continuous metabolic flux. By modeling…
Topological Reorganization and Coordination-Controlled Crossover in Synchronization Onset on Regular Lattices
Gunn Kim
The transition to global synchronization in coupled dynamical systems is governed by the interplay between coupling strength and structural topology. Although abrupt, first-order-l…
Thermodynamic Isomorphism of Transformers: A Lagrangian Approach to Attention Dynamics
Gunn Kim
We propose an effective field-theoretic framework for analyzing Transformer attention through a thermodynamic lens. By constructing a Lagrangian on the information manifold equippe…