Pith. sign in

Attention is not all you need: pure attention loses rank doubly exponentially with depth

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

Converting Transformers into DGNNs Form

cs.LG · 2025-02-01 · conditional · novelty 4.0

A Transformer variant called Converter replaces self-attention with a learnable unitary spectral filter (Synvolution/Kernelution) and reports much higher accuracy on Long-Range Arena and other long-sequence tasks, without releasing code or variance estimates.

citing papers explorer

Showing 1 of 1 citing paper.

  • Converting Transformers into DGNNs Form cs.LG · 2025-02-01 · conditional · none · ref 8

    A Transformer variant called Converter replaces self-attention with a learnable unitary spectral filter (Synvolution/Kernelution) and reports much higher accuracy on Long-Range Arena and other long-sequence tasks, without releasing code or variance estimates.