framework
active
framework:looped-transformerLooped Transformer
Core subject of the paper: transformers that reapply layers cyclically to improve reasoning via test-time compute
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Core abstraction in Fruit: pure function mapping signals to signals; enables compositional GUI definitions.
- Prior Anthropic paper enabling circuit-level analysis of attention-only transformers; motivates current MLP decomposition
- Two-layer transformer with rotary positional encodings used in numeric task experiments.
- A model that frames RL as sequence modeling, SOTA from random trajectories.
- Foundational mechanistic interpretability paper on transformer circuit analysis
- Miniaturized model the authors train themselves to directly observe the training-time bifurcation into fractal basins.
- A transformer with no attention layers; shown to model bigram statistics via T = W_U W_E
- Neural network architecture based on attention, commonly used in large language models