Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces
arXiv:2610.00257v1 Announce Type: new Abstract: In standard transformer attention, a source token sends the same value vector to every receiver. The query determines \emph{how much} to attend but not \emph{what} to extract. This work introduces \textbf{attention manifolds}: learned 2D B-spline surf…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-02 04:00 · arXiv cs.LG
Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces