- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates whether adversarial training (AT) can improve the generalization of multi-view Vision-Language-Action (VLA) models under natural distribution shifts, revealing a failure mode termed "view collapse": direct adversarial training can cause the policy to primarily rely on the wrist view. Consequently, while the model achieves high success rates when the third-person camera undergoes distribution shifts, this does not demonstrate that the model can robustly utilize information from that camera. The authors validate this phenomenon through experiments including view blacking, progressive blurring, training dynamics analysis, and altering the attacked view, and subsequently explore SFT initialization and View Swap to mitigate fixed view reliance. Experiments covering seven categories of distribution shifts in LIBERO-Plus across various model configurations show that View Swap alleviates fixed view reliance, whereas further adding adversarial training yields selective rather than universal gains.
Critical strengths
The core finding carries practical significance and is supported by compelling interventional evidence. On LIBERO-Object, Direct AT maintains a 98.8% success rate even after removing the third-person view, but its success rate drops to 0% when the wrist view is removed. Progressive blurring experiments support the same asymmetry in reliance, and altering the attacked view reverses the direction of policy reliance (Table 10). These results convincingly demonstrate that performance gains under a specific view's shift may stem from simply evading that view, highlighting a crucial pitfall in evaluating the robustness of multi-view policies.
The inclusion of matched-condition comparisons among SFT/AT/Swap/AT+Swap, View Dropout baselines, perturbation budget and norm ablations, as well as experiments across different backbones and action decoders, enhances the credibility of the study. The authors also report performance drops under certain shifts, along with distinct results observed in the robot-pretrained 0 model, maintaining reasonable boundaries for the applicability of their conclusions rather than merely emphasizing optimal configurations.
Critical weaknesses
The distinction between "robust perception" and "robust fusion" lacks sufficient empirical validation. Figure 3 demonstrates that the model copes better with degradation when either view is removed or blurred, but it does not directly clarify how the policy adjusts its reliance when both views retain useful information while their relative reliability changes. Thus, it remains unclear whether the additional gains from adding AT on top of View Swap stem from improved perception, improved fusion, or other training effects. Although the authors acknowledge this limitation in Section 6, it still constrains the mechanistic insights provided by this core conceptual distinction. Furthermore, detailed view-intervention experiments are primarily concentrated on LIBERO-Object, whereas the distribution shift results are aggregated across four task suites.
Questions for authors
- Could you evaluate view reliance under conditions where both views still contain useful information but their relative reliability is altered, covering representative tasks beyond LIBERO-Object?
- How many independent training runs were performed for the main comparisons? What is the number of rollouts evaluated per task suite and per shift category?
- All reported AT configurations utilize single-step Fast-AT. Does view collapse still occur when training with multi-step PGD? How does it compare to training with random perturbations under matched conditions?
4 comments
Rebuttal to Reviewer aXJW (2/2)
[Q3: Does View Collapse Persist Under Multi-Step PGD?]
We added matched random-noise and two-step PGD controls, confirming that view collapse is not reproduced by random perturbations but also occurs under multi-step AT.
1. Matched Random Noise Does Not Reproduce AT's Effects
| Training (30k updates) | Camera | Noise | Wrist only |
|---|---|---|---|
| Direct Rand. | 21.8 | 45.8 | 16.3 |
| Direct AT | 88.4 | 86.8 | 79.4 |
Success rates (%), four-suite averages; ε=1/255 with matched initialization and training schedule. Camera/Noise: LIBERO-Plus; wrist only: clean LIBERO.
- Finding: Random perturbations reproduce neither AT's Camera/Noise gains nor its extreme wrist-dominant reliance.
2. View Collapse Persists Under Two-Step PGD
| Training (10k updates) | Clean | Third only | Wrist only |
|---|---|---|---|
| Direct AT (1-step) | 99.2 | 0.0 | 100.0 |
| Direct AT (2-step PGD) | 74.4 | 0.0 | 74.2 |
LIBERO-Object success rates (%); ε=1/255. Two-step PGD uses a random start and step size α=ε.
- Finding: Both methods fail completely with only the third-person view while retaining success with the wrist view alone. Thus, view collapse is not specific to single-step AT, although the two-step checkpoint has lower clean performance.
Summary of Q3
These experiments establish that the observed collapse is not explained by matched random noise and can persist under multi-step adversarial optimization.
--
Summary of the rebuttal
Overall, our additional experiments strengthen the evidence that AT's generalization gains are shift-dependent and must be interpreted alongside view reliance. Four-suite view interventions confirm wrist-dominant collapse under Direct AT and its mitigation by View Swap. Degraded-view experiments provide behavioral evidence consistent with contributions from robust perception and robust fusion. Matched random-noise and two-step PGD controls further show that view collapse is not reproduced by random noise and can persist under multi-step AT.
We hope these additional results and clarifications address your concerns and strengthen the conclusions of our work.
Thanks for the thorough rebuttal and helpful new experiments on multi-suite interventions and PGD controls. Overall, I remain positive about the view-collapse insights and will maintain my original score.
Dear Reviewer,
Thank you again for reviewing our rebuttal and additional experiments. We are pleased that you remain positive about our view-collapse insights, and we truly appreciate your continued support toward the acceptance of our work.
Thank you once again for your time and consideration.
Best regards,
The Authors
Rebuttal to Reviewer aXJW (1/N)
Rebuttal to Reviewer aXJW
We sincerely appreciate your recognition that (1) the core finding carries practical significance with compelling interventional evidence, and (2) the matched comparisons and ablations enhance the credibility of the study.
Below, we address the raised concerns in detail.
[W1, Q1: Robust Perception vs. Robust Fusion Beyond LIBERO-Object]
We added view interventions under Camera/Noise shifts and joint-degradation experiments, providing behavioral evidence consistent with contributions from both robust fusion and perception. We also extended Fig. 3 to all four LIBERO suites.
1. Camera and Noise Shifts Reveal Different Sources of Improvement
LIBERO-Plus success rates (%), four-suite average, seed 42.
2. Joint Degradation Reveals Improved Robustness and Asymmetric View Reliance
We additionally evaluated different combinations of third-person and wrist-view degradation on LIBERO-Object, including cases where neither view remains intact.
LIBERO-Object success rates (%), 500 episodes per condition. Pairs denote (third-person blur σ, wrist blur σ); removed views are blacked out.
The four-suite averages also show gains under joint blur, although smaller: 3.0% versus 8.4% at (6,6) and 3.2% versus 12.0% at (8,6) (Table 4).
3. View Interventions Extended to All Four Suites (Revised Fig. 3)
We expanded Fig. 3 from LIBERO-Object to four-suite averages and added suite-wise results in the Appendix. The results confirm that Swap-based models remain functional when either view degrades, whereas Direct AT exhibits wrist-dominant reliance across all four suites. AT+Swap does not consistently outperform Swap, particularly under wrist blur. The extent of mitigation varies across suites.
Additional Control: Random-Noise Training
Matched random-noise controls do not reproduce AT's Camera gains (see our response to CunZ, W1-1), indicating that these improvements are not explained by noise augmentation alone.
Summary of W1/Q1
The results provide behavioral evidence for reduced interference from unreliable views and improved robustness to degraded inputs, while showing that these effects remain shift- and task-dependent. They do not establish the internal mechanisms.
Paper: Secs. 5.2–5.3; revised Fig. 3; Appendix E.3 (Fig. 5); Appendix G (Table 18)
[Q2: Training Runs and Rollouts]
We clarified the training-run counts and evaluation protocol in the Appendix.
The Appendix provides the complete suite-by-shift breakdown.