method
active
method:char-rnn

Char-RNN

Recurrent neural networks trained character-by-character for text generation, early precursor.

Neighborhood — ranked by edge-count

Artifacts (1)

artifact

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.
  • Karmanconcept0.686
    Buddhist concept of intentional action as a world-constructing force; linked to goal-directedness.
  • Alternative alignment metric compared in appendix; calculates longest common subsequence of nearest neighbor lists
  • Recurrent networksconcept0.665
    Networks with loop connections that can maintain internal state and exhibit dynamical attractors.
  • Edit k-NNmethod0.660
    Computes edit distance required to match nearest neighbors between two datasets, normalized by maximum edit distance
  • Jailbreakconcept0.657
    Methods to bypass model safety training; features may activate during jailbreaks.
  • Prior work on recurrently generated position encodings; cited as precedent for TEM-t's recurrent position encoding method.
  • Key modification to transformers proposed in this paper: position encodings generated by a recurrent network trained on action sequences.