Pith. sign in

On the connection between local attention and dynamic depth-wise convolution

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Dynamic Short Convolutions Improve Transformers

cs.LG · 2026-06-02 · unverdicted · novelty 6.0

Dynamic short convolutions applied to key/query/value projections and linear layers in Transformers yield consistent performance gains and 1.33-1.60x compute advantages over standard models on language modeling from 150M to 2B parameters.

citing papers explorer

Showing 2 of 2 citing papers.

  • Dynamic Short Convolutions Improve Transformers cs.LG · 2026-06-02 · unverdicted · none · ref 3

    Dynamic short convolutions applied to key/query/value projections and linear layers in Transformers yield consistent performance gains and 1.33-1.60x compute advantages over standard models on language modeling from 150M to 2B parameters.

  • Linear-Time Global Visual Modeling without Explicit Attention cs.CV · 2026-05-03 · unverdicted · none · ref 15

    Dynamic parameterization of standard layers can replace explicit attention for linear-time global visual modeling.