RoPE frequency usage is determined by a data-induced dependency width W, with the optimal frequency scaling as π/W, explaining both learned spectra and the success of position interpolation.
Neural machine translation by jointly learning to align and translate
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
citing papers explorer
-
How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization
RoPE frequency usage is determined by a data-induced dependency width W, with the optimal frequency scaling as π/W, explaining both learned spectra and the success of position interpolation.
-
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.