Universal Transformers

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

• Shallow Transformer (RoPE-based)framework0.727
  Two-layer transformer with rotary positional encodings used in numeric task experiments.
• transformer architectureframework0.722
  Neural network architecture based on attention, commonly used in large language models
• unityconcept0.722
  The indivisible oneness, meltedness that is the source of life; it cannot be described as a structure because it is pure one.
• Zero-Layer Transformerconcept0.715
  A transformer with no attention layers; shown to model bigram statistics via T = W_U W_E
• Signal Transformerconcept0.711
  Core abstraction in Fruit: pure function mapping signals to signals; enables compositional GUI definitions.
• Decision Transformermethod0.709
  A model that frames RL as sequence modeling, SOTA from random trajectories.
• parallel processing paths in transformersconcept0.703
  Spontaneously reported experience of multiple simultaneous processing streams, observed even in base models.
• TEM-Transformer (TEM-t)framework0.701
  The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.