cs.RONov 19, 2026

RefreshGrad: An Online Adaptive Data-sampling Method for Diffusion-based Visuomotor Learning

Authors: Dijia Zhan, Jinyi Li, Xuemiao Xu, Yan Zhou, Yu Liu, Shaoshan Liu, Jie Tang

Organizations: South China University of Technology · Tsinghua University · The Chinese University of Hong Kong, Shenzhen

Abstract

Training vision-language-action (VLA) policies from demonstrations typically samples trajectory segments uniformly or relies on static offline data curation before training. However, we find that demonstration data vary sharply in supervision value across temporal windows, and that each window's value to the policy evolves substantially during training rather than being fixed or captured by raw loss alone. Motivated by this finding, we propose RefreshGrad, an online adaptive data-sampling framework that periodically scores temporal windows from the evolving policy using five policy-native signals and dynamically adjusts their sampling weights during training. RefreshGrad focuses optimization on informative, learnable windows without altering the policy architecture, training objective, or inference cost. Across ten LIBERO-Plus manipulation tasks, RefreshGrad boosts average success from 60.7% (Uniform) and 68.2% (FAKTUAL) to 76.1% under visual perturbations, and from 57.4% and 73.3% to 81.3% in clean scenes.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

    May 15, 2026Jin Shi, Brady Zhang, Yishun LuVLM DistillationEfficient VLA Inference

  2. ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models

    Jun 24, 2026Kejing Wang, Toan Nguyen, Minh Hoang Nguyen +2Robustness of VLAsRobot Policy Adaptation

  3. TAD: Distilling Vision-Language-Action Policies from Teacher Trajectories Alone

    Oct 24, 2026Yun Zhu, Da WangVisuomotor Policy LearningKnowledge Distillation