- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes FastOPD, an efficient on-policy distillation method for compressing large flow-based VLA models into lightweight, few-step policies. Instead of evaluating the teacher at every denoising step, FastOPD uses supervision at a single sampled on-policy state, together with a self-consistency objective. The paper provides theoretical analysis and evaluates the method across several VLAs and a WAM in simulation, as well as one real-world robot task.
Critical strengths
-
Effective and efficient. The method substantially reduces training and inference costs while retaining much of the teacher's performance. The results across different VLAs and a WAM are promising and suggest that the approach is fairly general.
-
Interesting theoretical insights. The theoretical analysis helps explain why sparse on-policy supervision, combined with self-consistency, can work for few-step distillation.
Critical weaknesses
-
Performance still falls short of the teacher. While the method improves over the student baselines, there is still a noticeable gap to the teacher, especially on RoboTwin and in the real-world experiment. It is unclear how much of this gap comes from the smaller student architecture versus the distillation method itself.
-
Limited real-world evaluation. The real-world experiment only considers one relatively simple pick-and-place task (that presumably doesn't need VLA). It would be more convincing to see results on more challenging manipulation tasks.
Questions for authors
-
What do the authors think is the main reason for the remaining gap between the student and teacher, particularly in the MolmoAct2 real-world experiment? Is there a way to further close this gap?
-
Does distillation hurt the teacher's generalization capabilities? For example, how does the student perform on unseen objects, environments, or task variations compared to the teacher?
-
By supervising only one sampled on-policy state per trajectory, could FastOPD be losing useful supervision from the other denoising steps? Have the authors tried supervising multiple sampled states to see whether this improves performance?
3 comments
Response by Authors (2/2)
Q2. Does distillation hurt the teacher’s generalization capabilities? For example, how does the student perform on unseen objects, environments, or task variations compared to the teacher?
As shown in Table 2 of the revised manuscript, our evaluation on the RoboTwin benchmark covers unseen environments under both clean and randomized settings. Although an absolute performance gap remains between the teacher and student, FastOPD demonstrates robustness to environmental variations in these unseen environments. Specifically, the distilled student achieves higher success rates under randomization at NFE=2, 4, and 10, while maintaining comparable performance at NFE=1, as detailed in Table 19 and 20 of the revised manuscript. These results suggest that the distilled student maintains comparable performance across the evaluated clean and randomized environments.
Q3. By supervising only one sampled on-policy state per trajectory, could FastOPD be losing useful supervision from the other denoising steps? Have the authors tried supervising multiple sampled states to see whether this improves performance?
We appreciate the reviewer’s valuable suggestion. To investigate this, we evaluated an augmented supervision variant that queries the teacher at two sequential student rollout states on LIBERO.
As shown in Table 2, supervising two states yields comparable performance to our single-state approach, suggesting that a single on-policy state already provides effective teacher guidance without requiring additional teacher evaluations. This supports our design choice of using single-state supervision for efficient distillation.
Table 2. Ablation study on the number of supervised on-policy states on LIBERO. Success rates (%) are reported across different NFEs.
| # of supervised states | NFE=1 | 2 | 4 | 10 |
|---|---|---|---|---|
| Base | 69.1 | 71.4 | 72.8 | 71.6 |
| 1 (default) | 77.3 | 81.8 | 80.3 | 79.0 |
| 2 | 77.5 | 80.6 | 81.4 | 79.5 |
We thank the reviewer again for the valuable feedback, and hope these revisions address the reviewer's concerns.
Follow-up on Author Response
Dear reviewer zM3F,
Thank you again for your time and constructive comments. As the discussion period is ended within a couple of days, we would like to kindly follow up and ask whether our responses have addressed your concerns. If any concerns remain, we would be glad to address them within the remaining time.
Thank you very much for your effort in reviewing our work.
Response by Authors (1/2)
We sincerely thank reviewer zM3F for the encouraging comments and constructive suggestions. Below we provide point-by-point responses on your questions and concerns.
W1 & Q1. Performance still falls short of the teacher on RoboTwin and in the real-world experiment. Is there a way to further close this gap?
We appreciate the reviewer for the constructive comment. We acknowledge that a performance gap remains relative to the teacher and the 10-step base student.
To further investigate this gap, we conducted an additional real-robot experiment on a challenging long-horizon, multi-stage task (“open-close”). Since MolmoAct2 achieved only 52.0% success on this task, we adopted π0.5 as a more reliable teacher. All policies were evaluated over 50 trials. Further experimental details are provided in Appendix B.5 of the revised manuscript.
As shown in Table 1, our method achieves performance close to the teacher and outperforms the base student at both 4 and 10 steps. Thus, using a stronger teacher improves the performance and narrows the gap between the teacher and the student. This suggests that more reliable and less noisy teacher supervision may facilitate more effective knowledge transfer.
Further closing this gap will require addressing remaining challenges, including limited student capacity. Nevertheless, FastOPD provides a practical framework for efficiently distilling large foundation teacher policies into lightweight students, reducing the computational cost of on-policy distillation while enabling few-step inference.
Table 1. Real world results on the open-close task.
W2. Limited real-world evaluation
We agree that a more challenging task would better demonstrate the effectiveness of our approach. Following the reviewer’s suggestion, we conducted an additional real-world experiment on a long-horizon, multi-stage task: “open the drawer, pick up the black ball, put it in the drawer, and close the drawer.” (“open-close” task in Appendix B.5). As shown in Table 1 above, our method outperforms the base student at both 4 and 10 steps and even achieves performance close to the teacher.
Unlike the original pick-and-place task, this task requires the policy to execute a sequence of distinct manipulation stages, including articulated-object interaction, object grasping and placement, and drawer closure. Successful execution thus requires maintaining coherent behavior across multiple stages rather than completing a single pick-and-place operation. The strong performance of FastOPD on this task provides additional evidence that our distillation approach can preserve useful teacher capabilities in more complex manipulation settings.