- Rating
- 3(+1)
- Confidence
- 1(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces DVA, which predicts how important the current control step is and allocates the visual-token budget accordingly. The supervision comes from counterfactual suffix rollbacks, measuring how much sustained pruning from a given step hurts the rest of the rollout. A predictor and monotone calibrator are added on top of existing pruners, and experiments show consistent but generally bit performance gains over static pruning at matched average retention.
Critical strengths
- This paper is well-organized with relatively clear figures and tables.
- The main assumption seems reasonable: The right token budget varies across control phases, so a fixed ratio can waste computation or starve difficult steps.
- The devised DVA is modular and keeps the original pruner and policy weights unchanged.
- I like the idea of the approach to generating counterfactual labels.
Critical weaknesses
- Sometimes an important frame which seems hard to human intuitions actually require less tokens than we expected. This process is actually can be learned, since I found some related works which aim to guide the VLA/VLM model learns how to adaptively select tokens [1-3]. Authors are expected to follow and compare some highly related works beyond the tradition baselines including FastV, SparseVLM and other classic baselines. The author shouldn't avoid comparing with more powerful VLA pruning or lightweight VLA methods.
- From the experimental perspective, though as mentioned above in the strengths, the decision-importance labels rely on simulator suffix rollbacks and are expensive or unavailable on a real robot. The main training signal is therefore tied to resettable simulation.
- The FLOPs comparison is estimated and excludes some components, including parts of action-head computation and the DVA predictor. A full hardware-level accounting would make the efficiency claim more convincing. Authors can give the wall-clock time report and this is acceptable for me.
[1] VLA-ADP: ICLR'26
[2] LightVLA, ICRA'26
[3] SpecPrune-VLA, ICML'26
Questions for authors
See above.
4 comments
Response to Reviewer KGbT (Part 2/2): Weakness 3 (Full-model latency and hardware costs)
To Weakness 3 (Measured Latency and Predictor Overhead):
We appreciate your constructive advice on reporting practical inference costs. We have added StarVLA runtime measurements to Section 4.2, Table 7, Appendix D.2, and Table D.2 in the updated submission, with changes highlighted in .
The wall-clock measurements in Table 2 already include the costs omitted from the FLOPs estimate. They time visual encoding, budget prediction and selection, the decoder, and complete action generation. In particular, the parenthesized DVA value is the predictor and calibrator latency already included in the total, as stated in the caption. The approximately 37% retention result is therefore a speedup with budget-control overhead included:
| Architecture | Full tokens (ms) | DVA (ms) | DVA speedup |
|---|---|---|---|
| OpenVLA-OFT | 107.0 | 88.8 (1.12) | 1.20× |
The 1.12 ms contribution is part of the reported 88.8 ms total. To test whether this practical benefit extends to other action heads, we measured the VLM, complete action head, and full call on StarVLA-π and GR00T. Each comparison uses identical inference settings on an exclusive A800 and the Table 2 sampling procedure, with the corresponding full-token run as reference.
| Architecture | StarVLA-π | StarVLA-π | StarVLA-π | StarVLA-GR00T | StarVLA-GR00T | StarVLA-GR00T |
|---|---|---|---|---|---|---|
| Component | VLM | Action head | Full model call | VLM | Action head | Full model call |
| Full tokens (ms) | 160.8 | 181.5 | 348.9 | 161.6 | 21.1 | 189.3 |
| DVA (ms) | 135.6 | 149.0 | 291.2 | 143.3 | 18.9 | 168.7 |
| Speedup | 1.19× | 1.22× | 1.20× | 1.13× | 1.12× | 1.12× |
These calls include the corresponding predictor, calibrator, and token-selection operations, while the VLM component includes visual encoding and the language decoder. Shorter visual conditioning reduces computation in both the VLM and the action head’s key/value projections and cross-attention, so the measured full-model gains include savings from both components after budget-control costs. Appendix D.5 specifies the timing setup.
References
[1] Xiaohuan Pei et al. Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation. arXiv:2509.22093, 2025.
[2] Titong Jiang et al. The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning. arXiv:2509.12594v2, 2025.
[3] Hanzhen Wang et al. SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning. ICML, 2026.
If you have more questions or suggestions, please let us know, and we would be happy to have further discussions.
Reply
I appreciate authors' response. Though I think the experimental improvement is rational and not that promising for all evaluated benchmarks, the extra results and LIBERO-plus experiments enrich the experimental analysis to a certain extent though I still think more related pruning methods for VLA should be incorporated. I raise my rating from 2 to 3 with the low confidence.
Best wishes,
Reviewer KGbT
Response to Comments by Reviewer KGbT
To the Follow-up Comment (Additional VLA Pruning Comparisons)
Thank you for reassessing our work, raising your rating, and suggesting further VLA pruning comparisons. We have added SAFE-Pruner, VLA-ACL, and VLA-Pruner results to Section 4.2 and Table 2, and expanded the related-work discussion in Appendix A.3 of the updated submission, with changes highlighted in .
Building on the existing EfficientVLA [1], VLA-Cache [2], VLA-ADP [3], and SpecPrune-VLA [4] comparisons, the updated table includes SAFE-Pruner [5], VLA-ACL [6], and VLA-Pruner [7]. This gives seven VLA acceleration methods alongside DVA at three retention ratios. VLA-ADP uses Ratio=0.05, whose speedup is close to DVA's, to support comparison at similar inference cost.
These methods cover a range of acceleration approaches: VLA-ACL learns token selection under a fixed budget, VLA-ADP and SpecPrune-VLA adjust pruning using action information, and VLA-Pruner and SAFE-Pruner use historical information for training-free pruning. VLA-Cache and EfficientVLA additionally introduce caching across frames and model-structure compression, respectively. The comparisons therefore cover static and dynamic budgets, learned selection, temporal information, and computation reuse.
| Method | Model-call latency (ms) | Speedup | Success (%) |
|---|---|---|---|
| EfficientVLA [1] | 70.4 | 1.52× | 88.9 |
| VLA-Cache [2] | 103.9 | 1.03× | 96.8 |
| VLA-ADP (Ratio=0.05) [3] | 92.4 | 1.16× | 78.2 |
| SpecPrune-VLA [4] | 106.4 | 1.01× | 95.0 |
| SAFE-Pruner [5] | 88.2 | 1.21× | 96.4 |
| VLA-ACL (K=128) [6] | 91.1 | 1.17× | 96.5 |
| VLA-Pruner (Ratio=0.10) [7] | 89.5 | 1.20× | 93.8 |
| DVA (r̄=0.37) | 88.8 (1.12) | 1.20× | 97.0 |
| DVA (r̄=0.28) | 85.4 (1.08) | 1.25× | 96.5 |
| DVA (r̄=0.22) | 83.4 (1.09) | 1.28× | 96.2 |
At operating points near DVA's 1.20× speedup, SAFE-Pruner, VLA-ACL, and VLA-Pruner achieve 96.4%, 96.5%, and 93.8% success, respectively, compared with 97.0% for DVA. At tighter budgets, DVA maintains 96.5% and 96.2% success at 1.25× and 1.28× speedups. Thus, the expanded comparison with recent VLA-specific pruners continues to show higher success for DVA at the evaluated operating points with similar runtime cost. Parenthesized values report the budget-control overhead already included in total latency.
If you have more questions or suggestions, please let us know, and we would be happy to have further discussions.
References
[1] Yantai Yang et al. EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models. arXiv:2506.10100, 2025.
[2] Siyu Xu et al. VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching. NeurIPS, 2025.
[3] Xiaohuan Pei et al. Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation. arXiv:2509.22093, 2025.
[4] Hanzhen Wang et al. SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning. ICML, 2026.
[5] Shilin Ma et al. SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation. ECCV, 2026.
[6] Owen Du et al. VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models. arXiv:2610.08133, 2026.
[7] Ziyan Liu et al. Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference. arXiv:2511.16449, 2025.
Response to Reviewer KGbT (Part 1/2): Weaknesses 1–2 (VLA baselines and real-robot adaptation)
We appreciate your recommendations of relevant work and suggestions for broader baseline comparisons. We have added baseline results to Section 4.2 and Table 2, and expanded the discussion of pruning objectives in Appendix A.3 in the updated submission, with changes highlighted in blue.
The original Table 2 includes VLA-ADP at Ratio=0.50 and 0.30, reporting success, measured latency, and speedup alongside the general VLM pruners [1]. Your suggestion helped us extend this VLA-specific comparison and explain more clearly which pruning objective DVA addresses.
LightVLA learns to reduce visual computation within a model call while preserving action prediction, but that objective does not directly measure the effect of sustained pruning on the remaining task [2]. SpecPrune-VLA exploits spatial and temporal redundancy and adjusts pruning according to action granularity [3]. However, states with similar action speeds can require different visual information, so action granularity does not directly measure whether continued pruning will cause later failure or extra completion steps.
DVA learns from those execution consequences. As Section 3.1 explains, full suffixes under different ratios are compared from the same state, and failures and additional completion steps supervise the budget module. The module is learned separately from the frozen policy, and Table 3 and Figure 4 evaluate its use across action heads. Our revised characterization therefore includes learned adaptive pruning and distinguishes DVA by its execution-based supervision. The Abstract and Introduction state this distinction.
To compare the resulting success–latency trade-off with VLA-specific alternatives, we extended the VLA-ADP sweep to Ratio=0.05 and evaluated SpecPrune-VLA on OpenVLA-OFT. Both follow the standard LIBERO success-rate protocol and the Table 2 timing procedure, with speedups referenced to the corresponding full-token run.
At these measured operating points, DVA achieves both higher success and greater speedup, showing a practical benefit in comparisons with VLA-specific dynamic pruning.
Thank you for your feedback on presenting the application of DVA to real robots. We have expanded the labeling and adaptation protocol in Section 4.2 and Appendix D.7 in the updated submission, with changes highlighted in blue.
Comparable restored states are needed to construct DI labels, because the candidate retention ratios must be tested from the same starting conditions. Simulation supports this comparison directly, while physical resets cost more. We therefore collect the main supervision in simulation and adapt the resulting predictor with a small set of real-robot labels. Once trained, the predictor and calibrator assign budgets from current observations without online rollback.
The real-robot experiment follows this separation by fine-tuning the simulator-pretrained predictor on four labeled states per task, as described in Section 4.1. To obtain each label, we return the robot to a predefined pose, reset the objects, and replay the full-token prefix. Each candidate ratio then remains fixed through the suffix, and its success and additional completion steps relative to the full-token reference contribute to the state’s DI label. Thus, the reported deployment follows simulator pretraining and a small real-robot adaptation stage. The Conclusion in Section 5 also states this adaptation protocol.