The paper casts the standard Transformer block with RoPE as a first-order approximation of a radial–tangential state estimator and introduces a Polar Transformer variant that retains the discarded geometric corrections.
Neural SDE s as a unified approach to continuous-domain sequence modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
citing papers explorer
-
The Transformer as a Polar State Estimator
The paper casts the standard Transformer block with RoPE as a first-order approximation of a radial–tangential state estimator and introduces a Polar Transformer variant that retains the discarded geometric corrections.
- Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation