Pith. sign in

Learnable sparsity for vision generative models

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

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

MobileWan: Closing the Quality Gap for Mobile Video Diffusion

cs.CV · 2026-07-07 · conditional · novelty 6.0

A 5B-parameter video diffusion transformer is made deployable on mobile hardware via recurrence distillation, learnable head pruning, step distillation, and decoder optimization, achieving 83.79 VBench at 20s latency.

citing papers explorer

Showing 1 of 1 citing paper.

  • MobileWan: Closing the Quality Gap for Mobile Video Diffusion cs.CV · 2026-07-07 · conditional · none · ref 48

    A 5B-parameter video diffusion transformer is made deployable on mobile hardware via recurrence distillation, learnable head pruning, step distillation, and decoder optimization, achieving 83.79 VBench at 20s latency.