- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies continued adaptation, which involves continuing to train models under a limited budget for performance improvement, for VLA models. It raises the concern that increasing the sampling frequency of particular frames also increases their effective weights in the training objective, motivating the decoupling of temporal allocation from objective reweighting. It therefore introduces ReTime (Residual-Guided Temporal Resampling), which uses flow-matching residuals from a frozen starting policy to sample high-residual frames more frequently and applies importance correction to preserve the continuation objective. Experiments show that ReTime can boost performance better than uniform under both simulation and real-world experiments.
Critical strengths
-
The idea is simple and requires minor modifications to the original training pipelines and recipes. The scoring stage is performed offline, without introducing extra inference latency or structural modifications.
-
The authors conduct experiments in both simulation and real-world settings, providing evidence over longer training horizons. The experiments show improvements across multiple backbones and benchmarks, demonstrating the method’s effectiveness.
Critical weaknesses
-
While this paper centers its main challenge and contribution on “decoupling temporal allocation from objective reweighing,” it doesn't sufficiently explain the significance of decoupling itself. I would like to hear more about how decoupling, as well as an unchanged continuation objective, can contribute to either general VLA performance or future VLA research.
-
This paper conducts experiments only on GR00T-style policies implemented in StarVLA. Although different backbones are tested, I wonder whether the proposed pipeline and its performance gains can be transferred to other SOTA VLA foundation models, especially .
Questions for authors
-
Can you explain more about the importance of decoupling temporal allocation from objective reweighting? How could this contribute to VLA research in a broader sense?
-
Besides GR00T, can your pipeline also be applied to other foundation models with different architectures, such as and other flow-matching-based VLA models? Can the idea be transferred to non-flow-matching models?
-
As the training budget is a core factor in this paper, could you explain more about why 500 additional updates were chosen for the simulation experiments and how the relative performance of the methods changes under smaller or larger training budgets? More specifically, over what range of training budgets does ReTime remain effective?
6 comments
Response to Reviewer zvvm (2/2)
[Q3] Sensitivity to continuation budget.
As the training budget is a core factor in this paper, could you explain more about why 500 additional updates were chosen for the simulation experiments and how the relative performance of the methods changes under smaller or larger training budgets? More specifically, over what range of training budgets does ReTime remain effective?
Why 500 updates. Our simulation protocol deliberately targets the small-budget regime: starting from policies with basic task competence whose training losses had largely converged, 500 additional updates test how efficiently ReTime uses a limited continuation budget. We have now extended this to larger budgets.
Budget sweep. Specifically, we extended Florence–SimplerEnv continuation to 3,000 updates, evaluating ReTime and Uniform every 500 updates from the same starting checkpoint (starting-policy success: 36.46%).
| Additional updates | 500 | 1,000 | 1,500 | 2,000 | 2,500 | 3,000 |
|---|---|---|---|---|---|---|
| Uniform | 42.19 | 44.27 | 46.61 | 47.14 | 43.23 | 42.45 |
| ReTime (Ours) | 59.38 | 59.64 | 60.68 | 61.20 | 63.02 | 64.32 |
| Gain (pp) | +17.19 | +15.36 | +14.06 | +14.06 | +19.79 | +21.88 |
Table R2. Florence–SimplerEnv strict success (%) across continuation budgets (training seed 117465; 384 rollouts per checkpoint).
Result. ReTime consistently outperforms Uniform across the entire 500–3,000-update range, with success increasing from 59.38% to 64.32%. In contrast, Uniform peaks at 2,000 updates before declining to 42.45%. Together with the longer-horizon Florence–Phone study, these results demonstrate ReTime's sustained advantage under extended continuation, whereas additional uniform training can degrade an already well-trained policy.
Revisions. We have added this analysis to Sec. 4.4 (Fig. 7), with task-level results in Appendix C.4 (Table 16).
We hope these responses address your concerns, and would be glad to clarify any remaining points.
Thanks the authors for their response and the work put into this rebuttal, but the response does not sufficiently address my concern.
Although the -FAST experiments provide evidence of transferability to non-flow-matching VLAs, they do not establish transferability to other flow-matching VLAs. Architectural compatibility alone does not establish that the performance gains transfer to . As stated in my review, my concern is specifically about performance on SOTA VLA foundation models, given the substantial capability gap between and /-FAST. The availability of only ’s flow-matching head explains the choice of -FAST for the non-flow-matching evaluation, but the authors do not explain why itself was not evaluated. This makes me doubt the generalizability of the proposed framework.
Therefore, I decide to maintain my score.
Response to Reviewer zvvm (1/2)
We thank the reviewer for the thoughtful questions. We address each point below; all new results are included in the revised manuscript.
[W1 & Q1] Significance of decoupling temporal allocation from objective reweighting.
We thank the reviewer for raising this important question.
Motivation. In VLA continuation, non-uniform temporal sampling changes not only how frequently trajectory moments are encountered but also their relative contributions to the training objective. Whether such implicit objective reweighting benefits continued adaptation remains unclear, making it difficult to disentangle the effects of temporal allocation and objective modification. This motivates our central question: can we improve finite-budget VLA continuation by reallocating temporal exposure while preserving the original training objective?
Empirical evidence. Under identical temporal proposals, importance correction improves average success across four simulation settings from 31.96% to 34.93% for ReTime and from 30.74% to 32.63% for Shuffle, including a +4.69 pp gain for ReTime on Florence–SimplerEnv. Preserving the original objective thus further enhances the effectiveness of non-uniform temporal sampling.
Broader significance. This decoupling treats temporal allocation as an independent design dimension. Because the training objective remains fixed, alternative priority signals (e.g., FM residuals vs. action MSE, Table 2) and sampling strategies can be compared on equal footing, without confounding from objective changes.
Revisions. We agree that the original manuscript did not sufficiently articulate this significance and have revised:
[W2 & Q2] Generalization across VLA architectures and learning objectives.
We thank the reviewer for this valuable suggestion.
Setup. We have extended ReTime to π0-FAST, evaluating its applicability beyond GR00T-style architectures and flow-matching-based policies. Since π0.5 [1] shares the π0 [2] architecture and its flow-matching action expert, ReTime applies to it directly. To test a non-flow-matching objective, we use π0-FAST [3], as the public openpi release [4] supports only the flow-matching head of π0.5. As an autoregressive VLA trained with discrete action tokens, π0-FAST changes both the architecture and the learning objective, providing a stricter test. We evaluate Uniform, Loss-IS, and ReTime on 20 RoboTwin tasks under identical continuation budgets, with 100 rollouts per task and condition.
Table R1. π0-FAST success rate (%) on 20 RoboTwin tasks (100 rollouts per task and condition).
Result. ReTime achieves 35.90% average success, exceeding Uniform and Loss-IS by +8.88 and +7.45 pp, respectively.
Why it transfers. Because the importance correction depends only on temporal sampling probabilities, not on the form of the policy's training loss, the priority signal can be adapted to the autoregressive objective (the frozen policy's token-averaged negative log-likelihood of expert action tokens) while retaining the same objective-preserving resampling mechanism. These results suggest that the benefits of objective-preserving temporal allocation are not restricted to flow-matching policies. The results and discussion have been added to Sec. 4.5 (Table 4b), with task-level results in App. C.2.
References: