pith. sign in

Sparse actiongen: Accelerating diffusion policy with real-time pruning

Kangye Ji, Yuan Meng, Zhou Jianbo, Ye Li, Hanyun Cui, Zhi Wang · 2026 · arXiv 2601.12894

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

1 Pith paper citing it
open full Pith review browse 1 citing papers arXiv PDF

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Test-time Sparsity for Extreme Fast Action Diffusion

cs.CV · 2026-05-13 · unverdicted · novelty 7.0

Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.

citing papers explorer

Showing 1 of 1 citing paper.

  • Test-time Sparsity for Extreme Fast Action Diffusion cs.CV · 2026-05-13 · unverdicted · none · ref 10 · internal anchor

    Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.