Pith. sign in

Espformer: Doubly-stochastic attention with expected sliced transport plans.ArXiv, abs/2502.07962

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

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Sliced Inner Product Gromov-Wasserstein Distances

stat.ML · 2026-05-08 · unverdicted · novelty 6.0

A sliced IGW distance is introduced with closed-form 1D expressions, rotational invariance, and studied structural and computational properties for efficient data alignment.

Sinkhorn doubly stochastic attention rank decay analysis

cs.LG · 2026-04-09 · unverdicted · novelty 4.0

Sinkhorn-normalized doubly stochastic attention preserves rank more effectively than Softmax row-stochastic attention, with both showing doubly exponential rank decay to one with network depth.

citing papers explorer

Showing 2 of 2 citing papers.

  • Sliced Inner Product Gromov-Wasserstein Distances stat.ML · 2026-05-08 · unverdicted · none · ref 67

    A sliced IGW distance is introduced with closed-form 1D expressions, rotational invariance, and studied structural and computational properties for efficient data alignment.

  • Sinkhorn doubly stochastic attention rank decay analysis cs.LG · 2026-04-09 · unverdicted · none · ref 18

    Sinkhorn-normalized doubly stochastic attention preserves rank more effectively than Softmax row-stochastic attention, with both showing doubly exponential rank decay to one with network depth.