Deep Temporal Models

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Deep temporal models enable long-term policies, modelling slow transitions among hidden states at higher levels in the hierarchy, to contextualise faster state transitions at subordinate levels.claim0.821
  Describes hierarchical planning in Section 6.4.
• Deep Model Inductionframework0.778
• Diffusion modelsmethod0.774
  Generative models that reverse a noising process, mentioned in quasi-simulator table.
• Deep Representationsconcept0.762
  Hierarchical representations in neural networks that allow compression and coordinated behaviour while retaining sensitivity to input changes.
• dynamic causal modelsconcept0.755
  Nonlinear models of brain dynamics that can be inverted via DEM.
• Reasoning Modelsconcept0.748
  Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
• Autoregressive modelsframework0.748
  Second model system studied; used to show why flat autoregressive LLMs struggle with long-range coherence.
• Generative Modelconcept0.745
  Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.