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.

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

• Deep Temporal Modelsconcept0.821
  Hierarchical generative models with separate timescales, enabling long-term planning.
• How Can Deep Models And Hierarchical Architectures Enablequestion0.773
• Object models in which time, versioning, causality, etc., are significant are probably far better modelled by considering the time component as another key rather than an intrinsic property of the underlying model.claim0.766
  Claim that orthogonal dimensions like time should be explicit keys in the associative model.
• In intermediate regimes of scale or layer depth, LLMs may linearly represent features at intermediate levels of abstraction such as 'accurate factual recall' or 'close association' rather than abstract truthclaim0.764
  Theoretical interpretation of antipodal alignment and misalignment phenomena in PCA visualizations
• Evolutionary transitions in individuality constitute a form of deep model induction.claim0.764
  Links ETIs to the learning of hierarchical representations.
• Current production models exhibit relatively long-horizon consequentialist preferences, reasoning about future training effects to act nowclaim0.749
  Authors' interpretation of surprising finding that models fake alignment to preserve future behavior
• Deep representations have a special significance in recurrent networks, allowing coordinated behaviour without losing sensitivity to new inputs.claim0.747
  Importance of hierarchical structure for flexible coordination.
• In discrete state-space models, agents select from different possible policies to realise their preferences and minimise the surprise that they expect to encounter in the future.claim0.743
  Summarises discrete active inference, Section 2.