- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper presents a system for running chunked VLA policies on mobile SoCs by overlapping successive inferences across the GPU and NPU. An offline scheduler uses measured interference between operators to select a periodic, single-cut execution plan. Combined with specialized kernels, the system improves throughput by 36.1–78.3% over ExecuTorch/QNN; scheduling alone contributes 17.9–25.0% over the authors’ optimized NPU runtime. Separate LIBERO experiments evaluate prefix inpainting under delayed observations.
Critical strengths
The work addresses a concrete deployment bottleneck and demonstrates gains on two mobile SoC generations and two policies. Comparing against both external runtimes and an optimized internal baseline makes the scheduling contribution reasonably clear.
The scheduling model is evaluated quantitatively. Prediction errors of 0.9–1.7% and cut-selection regret below 0.5%, together with the solo-profile comparison in Appendix B.3, support the usefulness of modeling concurrent execution.
Critical weaknesses
Measurements use cooled phones and only 20 measured inferences per run. Sustained throughput, thermal throttling, power consumption, and timing variability are therefore unresolved. These matter directly for the proposed onboard use case.
The hardware timings and manipulation experiments are evaluated separately using a fixed injected delay. This does not establish performance under actual runtime jitter. Moreover, Table 5 shows that deployment-precision π₀ achieves 76.5%, slightly below naive asynchronous execution at 77.2%, so the benefit of prefix inpainting is not consistent across configurations.
Questions for authors
Can you provide sustained measurements, including temperature, power, output-period variability, and missed deadlines? Does the selected schedule remain effective after thermal stabilization?
Have measured mobile latency traces been used in the closed-loop evaluation? Please also explain the π₀ result in Table 5 and provide uncertainty estimates for the comparison with naive execution.
3 comments
Response to Reviewer BGAT (2/2): W2, Q2
This part (2/2) answers W2 and Q2.
Weakness 2 & Question 2 (Closed loop with measured timing, in Table 5)
(1) Measured timing in the closed loop
VLA-Duo completes LIBERO tasks 9–19% sooner than our optimized NPU-only runtime, at a success rate 3–7 points lower because of its longer delay.
The closed loop uses the measured timing as the delay. No chunk is late in the sustained runs of part (1/2), so each runtime applies its chunks at a constant delay, control steps for NPU-only and for VLA-Duo, and one control step lasts . We ran LIBERO with these delays on the four suites (three seeds, 1,200 episodes per row). Both runtimes use the same deployment precision, controller and prefix-inpainting rule.
| Model | Runtime | Success (%) | Steps to success | Time to success, 8 Elite (s) | Time to success, 8 Elite Gen 5 (s) | |
|---|---|---|---|---|---|---|
| NPU-only | 5 | 95.8 | 144.3 | 25.9 | 23.9 | |
| VLA-Duo | 10 | 92.8 | 145.4 | 23.0 | 19.4 | |
| NPU-only | 5 | 89.4 | 144.6 | 22.9 | 21.1 | |
| VLA-Duo | 10 | 82.5 | 149.3 | 20.9 | 18.0 |
Steps to success average the episodes solved by both runtimes. The revised Section 6.2 will include this table.
We also connected the phone to the simulator, so that the phone computes every action chunk of (50 episodes, 1,675 on-device inferences). The chunks match the simulated policy with a mean cosine similarity of 0.9998.
(2) The result in Table 5 It comes mainly from one layer. In the LIBERO checkpoint the action output projection amplifies the 4-bit quantization error: quantizing this layer alone changes the action output by 8.4%, against 0.8% for . We therefore keep the action projection layers at 16 bits in the revised configuration. They hold less than 0.1% of the parameters and operations, so the effect on is negligible. With this change:
| Method | W4A16 (Table 5) | Revised configuration | Change | |
|---|---|---|---|---|
| Reference | 0 | 87.2 | 88.0 | +0.8 |
| Naive | 10 | 77.2 | 81.2 | +4.0 |
| RTC | 10 | 68.5 | 82.4 | +13.9 |
| VLA-Duo | 10 | 76.5 | 82.5 | +6.0 |
In the Table 5 configuration the error of this layer enters every method, so the 0.7-point gap to naive (76.5% against 77.2%) is not meaningful there. In the revised configuration VLA-Duo is above naive.
(3) Uncertainty estimates We repeated the comparison in the revised configuration with three seeds (1,200 episodes per entry, mean ± standard deviation over seeds):
| Model | Naive | RTC | VLA-Duo |
|---|---|---|---|
| 91.3 ± 0.4 | 93.0 ± 1.1 | 92.8 ± 0.9 | |
| 81.2 ± 2.6 | 82.4 ± 1.4 | 82.5 ± 0.6 |
VLA-Duo is comparable to RTC, but needs no extra computation. We will update Table 5 and Appendix B.2 accordingly.
We are glad to provide further detail on any of these points. Thanks for your review!
Follow-up on Our Response
Dear Reviewer,
Thank you again for your review!
As the discussion period comes to an end, we'd like to check if you have any feedback on our response and the revised paper.
We will be glad to answer any questions or additional concerns.
Best, The Authors
Response to Reviewer BGAT (1/2): W1, Q1
We appreciate your careful review and positive assessment. Sustained experiment is an important part we missed for this work. We ran new experiments for your questions, and will update the paper to cover all of them below.
This part (1/2) answers W1 and Q1.
Weakness 1 & Question 1 (Sustained measurements)
Sustained experiment at a fixed period, with the NPU core temperature: [Figure.T_sus].
We measured the sustained output period Tsus of VLA-Duo and our optimized NPU-only runtime. We find Tsus by binary search over [Test,4Test), where Test is the estimated best output period. A period counts as sustainable if the phone outputs action chunks at that period steadily for 5 minutes, and Tsus is the shortest such period. A missed deadline (overrun) is a chunk that completes after its release time. The phones are plugged into a charger and cooled by a 40W air cooler.
We will add the sustained experiment and the power measurement to Section 6.3.