Pith. sign in

Not all patches are what you need: Expediting vision transformers via token reorganizations

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Representative Attention For Vision Transformers

cs.CV · 2026-05-14 · unverdicted · novelty 6.0

RPAttention achieves linear-complexity global attention in Vision Transformers by performing token compression in representation space via a Gather-Interact-Distribute process with learned representatives.

citing papers explorer

Showing 1 of 1 citing paper.

  • Representative Attention For Vision Transformers cs.CV · 2026-05-14 · unverdicted · none · ref 20

    RPAttention achieves linear-complexity global attention in Vision Transformers by performing token compression in representation space via a Gather-Interact-Distribute process with learned representatives.