- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes training-free visual-token compression for navigation. It combines low-rank feature grouping and within-group selection with instruction relevance, temporal novelty from semi-relaxed optimal transport, and diversity-aware historical selection. Evaluation covers R2R-CE, RxR-CE, and additional deployment examples.
Critical strengths
-
The reported SPL improvements over A-MMR are consistent across both benchmarks and all three pruning ratios. The stronger gains under aggressive compression suggest that the method addresses a meaningful limitation of uniform or saliency-dominated selection.
-
The component ablations are reasonably comprehensive and identify grouping and instruction relevance as useful components. The additional NaVILA evaluation also provides some evidence of transfer beyond the main StreamVLN backbone.
Critical weaknesses
-
The main comparative evidence is not fully controlled. Baseline results are imported from A-MMR, and equivalence of checkpoints, history settings, and decoding configurations is not demonstrated. The appendix acknowledges this limitation, but that qualification does not resolve the uncertainty behind the main improvement claims. A-MMR is also absent from the efficiency comparison despite being the most relevant baseline.
-
Important implementation and measurement details remain unresolved. The threshold in Equation 5 can exceed 1, in which case the cosine-based suppression accepts every candidate. Its actual range and any clipping therefore matter. Table 3 additionally reports 4.43 FPS alongside 248.26 ms latency without explaining the timing definitions; the other pruning rows approximately follow the reciprocal relationship.
Questions for authors
-
Is the threshold in Equation 5 clipped or normalized? What values occur in practice, and how often does within-group suppression remove tokens?
-
Can you reproduce A-MMR under matched conditions, include all selection preprocessing in timing, and reconcile the FPS and latency measurements?
5 comments
Response to Reviewer p3cV (2/2)
W2: Important implementation and measurement details remain unresolved.
A2: We appreciate the reviewer for identifying these issues. After carefully re-examining the formulation and experimental records, we have made the following corrections.
-
Eq. (5). The normalization factor in Eq. (5) is . The correct formulation is: where represents the token retention ratio. Since , the resulting threshold remains below 1, avoiding the issue raised by the reviewer. As the pruning ratio increases, the threshold becomes stricter, while proportional budget allocation ensures group coverage and the required output budget.
-
Tab. 3. We sincerely apologize for the error in the reported latency value in Tab. 3. The correct inference latency of our method at 90% pruning is 225.62 ms, corresponding to 4.43 FPS. We have further clarified the definitions and protocols of all efficiency metrics and extended the comparison to 70%, 80%, and 90% pruning, as presented in Tab. R2.
We apologize for these reporting errors and have corrected the corresponding descriptions in the revised manuscript.
Q1: Is the threshold in Equation 5 clipped or normalized? What values occur in practice, and how often does within-group suppression remove tokens?
A1: The threshold in Eq. 5 is normalized by the token count . As explained in our response to W2, the corrected formulation ensures that . To further clarify the practical behavior of within-group suppression, we analyzed 10 navigation trajectories under different pruning ratios. For each trajectory, we measured the average threshold and token suppression rate across all navigation steps. The results are as follows:
Table R3. Average adaptive threshold and within-group token suppression rate across 10 navigation trajectories under different pruning ratios. Suppression rates are measured before budget allocation.
Pruning Stage Suppression Rate (%) Mean 90% (72) Current frame 96.45 0.0259 Historical frames 93.35 0.0532 80% (146) Current frame 93.43 0.0527 Historical frames 86.04 0.1065 70% (218) Current frame 90.04 0.0785 Historical frames 78.36 0.1581
The results show that the average threshold ranges from 0.03 to 0.16, while within-group suppression removes 78.36%–96.45% of input tokens before budget allocation. These results demonstrate that the suppression mechanism effectively removes redundant tokens across different pruning ratios.
Q2: Can you reproduce A-MMR under matched conditions, include all selection preprocessing in timing, and reconcile the FPS and latency measurements?
A2: We have reproduced A-MMR under matched experimental conditions and provided an extended efficiency comparison. Please refer to our response to W1 for the detailed results.
Dear Reviewer p3cV,
Thank you again for your careful review and constructive suggestions. We sincerely appreciate the time and effort you have devoted to evaluating our work.
We have provided point-by-point responses, additional experiments, and clarifications in our rebuttal. As the discussion period draws to a close, we would be grateful if you could let us know whether these responses have addressed your concerns and which issues, if any, remain unresolved. We welcome further discussion and would be happy to provide timely clarifications before the deadline.
Thank you for your careful consideration and the effort you have invested in helping us improve our work.
Best regards,
The Authors
Response to Reviewer p3cV (1/2)
We sincerely thank the reviewer for the careful evaluation and constructive comments, particularly regarding comparisons, threshold, and efficiency. We have carefully revisited these issues, conducted additional experiments, and corrected the relevant errors in the manuscript. Below, we address each concern in detail.
W1: The main comparative evidence is not fully controlled.
A1: Thank you for raising this point. We clarify the evaluation setup and provide additional results to address the concern.
A-MMR reproduction. To ensure a consistent and fair comparison, we made every effort to reproduce A-MMR based on its published paper, as shown in Tab. R1. Our reproduced results closely match the originally reported performance, and even surpass in some metrics, further supporting the reliability and fairness of our comparison. Since the official implementation is unavailable, we carefully aligned the model checkpoint (StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln_v1_3), evaluator (Habitat 0.2.4), history configuration (8 uniformly sampled frames), decoding settings, and all other publicly specified configurations. Only a few undisclosed inference settings could not be exactly replicated.
Efficiency. We have also incorporated the reproduced A-MMR into the efficiency comparison and extended the evaluation to 70%, 80%, and 90% pruning, as shown in Tab. R2. Our method consistently achieves higher throughput and lower inference latency than the reproduced A-MMR, while maintaining comparable computational costs.
Together with the reproduced navigation results, these experiments provide stronger evidence of the favorable navigation–efficiency trade-off achieved by our method.