cs.CVOct 28, 2026

How Many Demonstrations Does a VLA Need? On the Sample Efficiency of VLA Finetuning

Authors: Rahul Chand, Miguel Villa Floran

Organizations: Stanford University · California Polytechnic State University

Abstract

Pretrained vision language action (VLA) models show strong zero-shot performance but they are rarely deployed directly and are often first post-trained on demonstrations from the target setting. Yet VLAs are typically compared by zero-shot or full-data fine-tuned success which reveals little about the data and compute required for downstream adaptation. We study adaptation efficiency for six VLAs (π0π_0, π0.5π_{0.5}, and GR00T N1-N1.7) on four LIBERO suites, varying both demonstrations and training steps. This reveals differences hidden by full-data fine-tuning: models which are within two points on the full LIBERO-Spatial dataset differ by up to 3×\times in success with 50 demonstrations. π0.5π_{0.5} needs 2-5×\times fewer demonstrations than π0π_0 and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite. Within GR00T, N1.5 adapts more efficiently than N1.6 and N1.7 on three of four suites, despite their stronger zero-shot performance. We also study one pretraining factor behind these differences by freezing the VLM during finetuning: this severely degrades the ππ models whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models

    Sep 16, 2026Shahram Najam Syed, Arthur Jakobsson, Prayuj Sachdev +1VLA Model AdaptationLow-Rank Adaptation

  2. How Much of Your VLA Is kNN

    Nov 9, 2026Denis Grachev, Damien LaRocque, Omar MouredVision-Language-Action ModelsVLA Model Evaluation