cs.RONov 17, 2026

Stochastic Diversity Windows: Diagnosing Noise Influence in Robotic Diffusion Sampling

Authors: Tina Lakhani, Jing Wu, Yu-Kun Lai, Ze Ji

Organizations: School of Computer Science and Informatics, Cardiff University, UK · School of Engineering, Cardiff University, UK

Abstract

Diffusion models are increasingly adopted in robotics and control due to their capability to express multiple feasible solutions to a given task. However, the role of stochasticity in the diffusion model-sampler across denoising remains poorly understood. We introduce a per-timestep counterfactual diagnostic that tests how changing the sampled noise affects the final output. Across five model-sampler configurations spanning three robotics benchmarks, diverse architectures, domains, and conditioning mechanisms, we reveal highly varied temporal sensitivity profiles, where noise-induced deviations can amplify, partially contract, or undergo near-total attenuation downstream. From these profiles, we define stochastic diversity windows (SDWs): compact intervals that identify where sampler stochasticity has the strongest measured influence on the final output. Guided by these windows, we apply two heuristic interventions: targeted stochastic amplification, which increases sample diversity exploration of the solution space, and an SDW-hybrid sampler, which replaces DDPM steps with DDIM skips in low-impact regions, resulting in network evaluation reductions of up to 40-60% and wall-clock time by up to 85%, with no consistent changes detected in feasibility, cost, or diversity across held-out tasks.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. On the Error-Correcting Effects of Stochasticity in Discrete Diffusion

    May 26, 2026William Yuan, Sungwon Jeong, Amirali AghazadehMarkov ModelsDiffusion Sampling

  2. Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation

    Nov 10, 2026Yuchen Jiao, Na Li, Changxiao Cai +2Diffusion SamplingDiffusion Model Acceleration

  3. The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis

    Jun 13, 2025Bernardo P. Schaeffer, Ricardo M. S. Rosa, Glauco ValleStochastic Differential EquationsDiffusion Sampling