- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper studies an actionable question for dynamic robot manipulation: should a VLA explicitly predict velocity as well as position? VIPER adds a velocity expert to a position-based policy and trains the two experts jointly with shared flow noise and joint position–velocity conditioning. Their outputs define a continuous trajectory through Hermite interpolation. Experiments cover three policy configurations and six tasks, including three physical robot tasks. The results support a useful practical lesson: explicitly learning velocity can improve tasks in which the timing and speed of contact matter.
Critical strengths
- The problem is well chosen. Predicting a plausible sequence of positions is not necessarily enough for tossing, flipping, or interception. The paper connects the action representation to these concrete execution requirements, and its proposed modification is straightforward enough to be useful to people building dynamic manipulation systems.
- The empirical improvements are substantial and fairly consistent.
Critical weaknesses
-
The spline comparison supports a narrower conclusion than the paper suggests. The paper clearly describes Spline-FF as fitting a cubic B-spline through predicted position targets and differentiating the curve. Hechtl et al.'s continuous variant instead trains the policy to predict B-spline control points, using control points fitted to demonstrations as training targets. Both use B-splines, but they learn different action representations. The reported comparison therefore establishes an advantage over post-hoc spline interpolation, not over the cited continuous-action method in its original form. The baseline attribution and conclusions should reflect this distinction.
-
The specific role of shared noise remains unclear. As acknowledged in Appendix C, the alignment argument assumes that both experts recover the exact shape of their profiles, the only residual error is a single scalar temporal phase shared across all H timesteps and all joints, and the denoisers are population-optimal for the squared-error flow-matching objective. The experiments support the coupled design as a whole, but do not separate shared noise from joint position–velocity conditioning, leaving the contribution of shared noise itself to alignment unresolved.
-
The generality of the learned velocity behavior remains unclear. An interesting question is whether the velocity expert learns motion behavior that can adapt to unfamiliar objects and substantially different trajectories. The reported results establish its usefulness in the evaluated task settings, but leave readers uncertain about how far this behavior extends beyond the demonstrated motion patterns. Coupling velocity with position is compatible with generalization. As a result, readers gain a useful practical lesson, but limited insight into whether the learned velocity behavior is broadly transferable.
-
The consistently smaller gains on physical tasks remain insufficiently explained. In Table 1, all three backbones show smaller improvements on physical tasks than in simulation. Although the task sets differ and Section 5.3 offers an explanation for RTC, the broader pattern remains unresolved: does it reflect task demands or difficulty, or limitations of the proposed approach during physical execution? The paper provides no evidence from additional tasks or datasets to support a task-based explanation.
Questions for authors
See weakness and one more question: How much inference latency does the velocity expert add in the evaluated configurations, and does it change the policy replanning rate?
5 comments
Rebuttal to Reviewer Yxg5 [part 2]
W3.
"substantially different trajectories"
We report Cube Slide at held-out target distances, , 20 rollouts per band.
| Goal band | Distance (m) | Success [new] |
|---|---|---|
| Inside the training range | 0.43–0.73 | 60% (12/20) |
| Outside, shorter | 0.28–0.37 | 15% (3/20) |
| Outside, longer | 0.76–0.81 | 30% (6/20) |
- Inside the training range, 60% is in line with Table 1 Cube Slide (56% on 100 rollouts), on target distances that are not in the demonstrations.
- Outside the range, success is 15% and 30%, as expected for a policy trained on demonstrations between 0.43 and 0.73 m.
- Table 1 already varies the goal within each physical task: the basket position (Ball Push), the walking path (Bottle Handover), and the release time (Drop Catch) change across trials (App. D.1). Ball Push on goes 28% 52% under that variation.
We have added the distance-band discussion to Section 6 (blue) of the revised manuscript.
"unfamiliar objects"
Object recognition is the role of the frozen backbone, which VIPER leaves unchanged: the velocity expert conditions on the same backbone output as the position expert. Our evaluation targets motion variation, and we have listed unfamiliar-object evaluation as a future direction in Section 6 (blue) of the revised manuscript.
W4.
"task demands or difficulty, or limitations of the proposed approach during physical execution"
Table 1 supports the task-based reading in two ways.
First, the smaller physical is not VIPER-specific.
success vs Position-Only:
| Method | Phys | RTC Phys | TEMPO Phys | Sim | RTC Sim | TEMPO Sim |
|---|---|---|---|---|---|---|
| Spline-FF (post-hoc) | +1.3 | −2.0 | −2.0 | +11.0 | +10.3 | +6.0 |
| [new] Control-Point FF | −2.0 | −9.3 | −6.7 | +6.3 | +2.7 | −0.7 |
| VIPER | +17.3 | +2.7 | +10.0 | +35.3 | +34.3 | +19.7 |
is the mean of the per-task differences, as in Table 1.
Every source of velocity gains less on the physical tasks, which points to the tasks and not to VIPER. VIPER is the only one that stays positive on all three backbones; the two spline-based sources range from −9.3 to +1.3.
Second, Position-Only starts higher on the physical tasks (30.0 / 42.0 / 58.0) than in simulation (16.3 / 17.7 / 25.0), so less failure is left to remove.
Share of Position-Only failures that VIPER removes (%):
| Setting | RTC | TEMPO | |
|---|---|---|---|
| Physical | 25 | 5 | 24 |
| Simulation | 42 | 42 | 26 |
- On TEMPO, VIPER removes the same share of failures on the physical tasks as in simulation (24 vs 26).
- On , VIPER removes a quarter of the physical failures.
- RTC is the case Sec. 5.3 discusses: RTC blends each new action chunk into the committed actions, which smooths the transitions between chunks, where the short velocity peak can fall.
We have added this reading to Sec. 5.3 (blue) of the revised manuscript.
Q1.
"How much inference latency does the velocity expert add in the evaluated configurations"
We report wall-clock time on , RTC and TEMPO : A100, 10 denoising steps, per action chunk (Table 9). The backbone runs once and its output is shared, so the extra time is the velocity expert's denoising steps.
| Configuration | Position-Only (ms) | VIPER (ms) | Extra (ms) |
|---|---|---|---|
| [new] | 79.2 | 101.6 | 22.4 |
| [new] | 116.0 | 142.2 | 26.2 |
| [new] | 93.5 | 112.9 | 19.4 |
We have added this to App. D.8 (blue) of the revised manuscript.
"does it change the policy replanning rate?"
No. Every backbone runs VIPER, Spline-FF, and Control-Point FF at the replanning rate of its Position-Only row in Table 1.
Revised PDF (blue): Sec. 2, Sec. 5.1, and Table 1 (Spline-FF is post-hoc interpolation; Control-Point FF is the learned control-point baseline), Sec. 5.3 (physical ), Sec. 6 (Cube Slide distances), App. D.6 (shared-noise split), App. D.8 (Inference latency). We are happy to elaborate on any implementation-level detail in the discussion phase.
Rebuttal Summary
We believe we have objectively answered each concern in the review, with new results for every one. All of them strengthen the findings of the paper.
Is our response satisfactory? If not, we are happy to run more experiments in the remaining 1.5 days.
-
Learned control-point baseline (W1). We added the new baseline across the full Table 1 grid, covering 3 simulation and 3 real-robot tasks across 3 backbones. VIPER outperforms this baseline in 17 of 18 comparisons and ties in one. We also revised Sections 2 and 5.1 and Table 1 to clarify the distinction between baselines.
-
Shared noise vs. joint conditioning (W2). New ablation: 37.7% 48.3% with joint conditioning, 51.7% with shared noise.
-
Alignment during denoising (W2). Additional experiments: VIPER has a lower consistency error at every step (0.64 vs. 0.81 at step 5) when denoised from shared noise.
-
Unseen target distances (W3). Additional experiments: VIPER achieves 60% success on Cube Slide at distances not in the demonstrations, in line with 56% in Table 1.
-
Physical vs. simulation gains (W4). VIPER is the only method with a positive physical gain on all three backbones. On TEMPO, it removes the same share of failures on physical tasks as in simulation (24% vs. 26%).
-
Latency (Q1). An additional 22.67 ms per action chunk on average across 3 different backbones; the replanning rate remains unchanged.
We thank the reviewer for the detailed review, which has improved both the framing and the evidence. Given these new results, we sincerely hope the reviewer will reconsider the overall assessment.
Rebuttal to Reviewer Yxg5 [part 1]
We thank the reviewer for calling the problem well chosen and the gains substantial and fairly consistent, and for naming Hechtl et al.'s continuous variant and the shared-noise split so clearly.
Summary.
W1.
We incorporate the suggestion and report new results on Control-Point FF: the policy predicts cubic B-spline control points, trained on control points fitted to the demonstrations, and the low-level controller receives the derivative of that spline, following the time-continuous action space of Hechtl et al. Recipe: 28 control points per action chunk, 32 knot vector, flow-matching loss on the control points. The frozen backbone, the demonstrations, and the low-level controller are the same as in Table 1. Mean success (%) over the three tasks on each side.
Table 1 now covers two spline-based sources of velocity: Spline-FF fits the spline post hoc through the predicted position targets, and Control-Point FF learns the spline action space. In both, the controller receives the derivative of a position spline. VIPER is the only row whose velocity is supervised on the demonstrated joint velocities, and it is the highest on every average.
We have incorporated these changes into the revised manuscript in Sec. 2, Sec. 5.1, and Table 1 (blue).
W2.
We incorporate the suggestion and report a new variant that keeps joint conditioning and co-fine-tuning as in VIPER and draws independent noise for the two experts, at training and at inference. Table 3 setting (π0.5, simulation, 100 rollouts, success %).
The consistency error shows what shared noise contributes to alignment. Position–velocity consistency error Econs (App. D.3) at intermediate denoising steps, Cube Slide, 100 rollouts:
We have incorporated both tables into the revised manuscript Appendix D.6 (blue). The consistency table measures directly the alignment effect that Appendix C motivates.