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.
When attention sink emerges in language models: An empirical view
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test
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.
-
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test