Symmetries in next-token prediction targets induce corresponding geometric symmetries such as circulant matrices and equiangular tight frames in the optimal weights and embeddings of a layer-peeled LLM surrogate model.
arXiv preprint arXiv:2602.15029 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Diverse language models converge on similar periodic number features with a two-tier hierarchy of Fourier sparsity and geometric separability, acquired via language co-occurrences or multi-token arithmetic.
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.
citing papers explorer
-
Uncovering Symmetry Transfer in Large Language Models via Layer-Peeled Optimization
Symmetries in next-token prediction targets induce corresponding geometric symmetries such as circulant matrices and equiangular tight frames in the optimal weights and embeddings of a layer-peeled LLM surrogate model.
-
Convergent Evolution: How Different Language Models Learn Similar Number Representations
Diverse language models converge on similar periodic number features with a two-tier hierarchy of Fourier sparsity and geometric separability, acquired via language co-occurrences or multi-token arithmetic.
-
There Will Be a Scientific Theory of Deep Learning
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.