- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents Vela, a vision-language-action model that represents future actions using a fixed number of cubic B-spline control points and a predicted temporal horizon. A noise-aware fitting criterion constructs adaptive-horizon supervision from demonstrations, while decoded-trajectory flow matching weights control-point errors by their effects on the resulting action trajectories. The method is evaluated on LIBERO-X, EBench, and two real-world manipulation tasks.
Critical strengths
-
The representation is well motivated. It enables the model to allocate a fixed representation budget adaptively across different action segments.
-
The experiments are extensive, and the pretrained version demonstrates the scalability of the method.
Critical weaknesses
- Table 4 does not specify the fixed horizon used. The authors should also experiment with different fixed horizons to determine whether adaptive temporal support consistently provides an improvement.
Questions for authors
- Which robot embodiments are included in the pretraining data?
- Could the authors provide uncertainty estimates or statistical significance tests for the small gains? For example, the improvement in Table 5 is only around one percentage point, making it difficult to tell whether it is robust to training and evaluation variability.
3 comments
Responses to Reviewer jMxd Question 1 and 2
Answer to Question 1: Robot embodiments in the pretraining data
Thank you for the question. The main robot embodiments are AgiBot G1 and G2, Franka/Panda (single- and dual-arm), ARX X5, AgileX PiPER/ALOHA, UR5, and YAM. Smaller contributions, mainly from Open X-Embodiment (OXE), include Google Robot, WidowX, FANUC Mate, and DLR EDAN.
We have added this list to Appendix E.1, in the “Robot embodiments” paragraph.
Answer to Question 2: Uncertainty of the loss-ablation results
1. How we measured variability. For each loss configuration in Table 5, we ran three additional training seeds. Together with the original run, this gives four training runs per configuration (n=4). For each run, we record its LIBERO-X average success rate. The table reports the mean ± standard deviation (SD) of these four values, showing how the results vary across training seeds:
| Geometry objective | Avg. success rate (%, mean ± SD; n=4) |
|---|---|
| CP-FM | 44.3 ± 0.3 |
| CP-FM + DT-FM (equal weighting) | 45.0 ± 0.3 |
| DT-FM | 45.4 ± 0.2 |
2. What the results show. DT-FM has the highest mean success rate, 1.1 percentage points above CP-FM. Combining the two losses does not improve the mean over DT-FM alone (45.0% vs. 45.4%). The SDs quantify the observed variation across training seeds; we do not claim statistical significance or equivalence between the losses.
3. Why we use DT-FM. Table 5 tests how much the choice of loss matters for learning our trajectory representation. All three losses produce effective policies. DT-FM gives the highest observed mean, and adding CP-FM does not improve it, so we use DT-FM as the default. These results suggest that DT-FM's decoder-aware weighting is a useful refinement, while the action representation also works well without it.
We have updated Table 5 and Sec. 4.4 (“Geometry supervision and uncertainty”), with the four-run protocol and original-run results documented in Appendix E.7 (“Loss uncertainty,” Table 13).
Thanks for the response. My concerns are addressed and I will keep the current positive score.
Responses to Reviewer jMxd Weakness 1
Thank you for pointing out this omission. The fixed horizon in the original Table 4 is H=25. To examine whether adaptive temporal support consistently improves over alternative fixed choices, we evaluated H∈{16,20,25,30,35,40} on LIBERO-X. All fixed-H variants are post-trained from the same Vela pretrained checkpoint as the adaptive model, with the same post-training budget and execution settings. Success rates (%):
Consistency under a different initialization. We also ran the same comparison from the original π₀.₅ checkpoint, which was pretrained with pointwise actions and never exposed to adaptive horizons. Both variants use Vela's spline representation (N=12) with the same post-training budget and execution settings, differing only in fixed versus adaptive horizon:
Adaptive H again improves the average by 1.8 points and is better at all five levels. The improvement therefore holds against the best fixed horizon in the sweep, across candidate ranges, and under both Vela and pointwise π₀.₅ initialization.
We have added the sweep to Sec. 4.4 (“Adaptive versus tuned fixed horizons,” Table 4), with the additional initialization and candidate-range controls in Appendix E.2 (Tables 7–8).