Computer Vision and Pattern Recognition · arXiv:2611.09964 v2 · submitted 28 Oct 2026
How Many Demonstrations Does a VLA Need? On the Sample Efficiency of VLA Finetuning
The paper says
“π0.5 needs 2–5 × fewer demonstrations than π0 and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite.”
from the abstract · picked out as the main claim by a classifier
Reviews
Reviews by people
No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
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 (π0, π0.5, 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× in success with 50 demonstrations. π0.5 needs 2-5× fewer demonstrations than π0 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 π models whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models.
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-10 · no language-model review
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.74 · human participants 0.05 · controlled comparison 0.61 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.85 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Pretrained vision language action (VLA) models show strong zero-shot performance, but are rarely deployed directly and are often first post-trained on demonstrations from the target setting. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| Yet VLAs are typically compared by zero-shot or full-data fine-tuned success, revealing little about the data and compute required for adaptation. | gap 0.99 | 0.07 | 0.03 | asserted 1.00 |
| We study adaptation efficiency for six VLAs ($\pi_{0}$, $\pi_{0.5}$, and GR00T N1-N1.7) on four LIBERO suites, varying both demonstrations and training steps. | method 0.65 | 0.96 | 0.04 | asserted 0.99 |
| This reveals differences hidden by full-data fine-tuning: models within two points on the full LIBERO-Spatial dataset differ by up to $3\times$ in success with 50 demonstrations. | result 0.99 | 0.95 | 0.17 | asserted 1.00 |
| $\pi_{0.5}$ needs $2$--$5\times$ fewer demonstrations than $\pi_{0}$ and is the most sample-efficient model at every budget, with the largest gap on the long-horizon suite. | result 1.00 | 0.95 | 0.51 | asserted 1.00 |
| Within GR00T, N1.5 adapts more efficiently than N1.6 and N1.7 on three of four suites, despite their stronger zero-shot performance. | result 1.00 | 0.94 | 0.11 | asserted 1.00 |
| We study one pretraining factor behind these differences by freezing the VLM during finetuning: this severely degrades the $\pi$ models, whose VLM is jointly trained with the action expert during pretraining, but barely affects GR00T models. | result 0.73 | 0.96 | 0.10 | asserted 1.00 |
| Finally, validation loss on held-out demonstrations tracks closed-loop success within a suite, but understates how much more sample-efficient $\pi_{0.5}$ is than $\pi_{0}$. | result 0.96 | 0.94 | 0.10 | asserted 1.00 |
What kind of paper the classifier reports this is: empirical study 0.99 · evidence from observation or experiment 0.97
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-10: 1 request, 6,532 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Cited by 1 Pith paper
Reviewed papers on Pith that cite this one. The full citation record
Challenges and discussion
Know something about this paper? Leave a comment.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment