- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes LLaDA-Nav, a diffusion-based visual navigation framework that uses full-mask parallel action decoding to avoid error propagation from previously generated action tokens. It further introduces Action Context Conditioning (ACC) to incorporate historical action information. Experiments demonstrate improvements in both open-loop trajectory prediction and closed-loop navigation performance.
Critical strengths
- The experiments cover both open-loop and closed-loop evaluations, providing a relatively comprehensive assessment of the proposed framework.
- The figures are clear and well designed, making the proposed method easy to understand.
Critical weaknesses
-
The paper attempts to mitigate the exposure bias caused by teacher forcing in AR models through diffusion-based full-mask parallel action decoding. However, the newly introduced ACC module may also cause a training–inference distribution mismatch, as it uses ground-truth action histories from the dataset during training but policy-executed action histories during inference. This design seems somewhat contradictory to the original motivation. Moreover, the main performance improvement appears to come from the addition of ACC (Table 3, rows 2 and 4), yet the AR baselines are not clearly evaluated with the same ACC module (or equivalent historical action information) for a fair comparison. Table A6 further raises this concern: with shorter ACC histories, the benefits of additional motion information may dominate, whereas with longer histories, the negative effects of training–inference distribution mismatch may become more pronounced, potentially explaining the substantial performance degradation. However, the paper does not further investigate this possibility.
-
The results in Table 4 are also somewhat confusing. Iterative Decoding (T=5) reuses previously predicted action tokens during denoising, potentially allowing errors in early predictions to mislead the remaining masked tokens. However, Table 4 shows that Iterative Decoding (T=5) achieves nearly the same SR as Single-pass Decoding (T=1), with even slightly higher SPL. This leaves both the core motivation of improving closed-loop performance by eliminating generated-token feedback and the source of the proposed method's performance gains insufficiently explained.
Questions for authors
-
Does ACC introduce a training–inference distribution mismatch similar to the exposure bias that the paper aims to address? How might this affect closed-loop performance?
-
Given the substantial gains from ACC in Table 3, could the authors provide a comparison where the AR baselines are equipped with the same action-history information to better isolate the benefits of prefix-free decoding?
-
Could the sharp performance degradation with longer ACC histories (k = 5) in Table A6 be related to an increased training–inference mismatch, rather than simply redundant historical information?
-
How do the authors explain the similar SR and slightly higher SPL of iterative decoding (T = 5) compared to single-pass decoding (T = 1) in Table 4, despite the reuse of predicted action tokens?
-
Do these results suggest that the performance gains mainly come from full-mask training rather than eliminating generated-token feedback during inference? Could the authors clarify the relative contributions of these two factors?
6 comments
Rebuttal by Authors (2/2)
W2-1 and Q4. Why the performance of one-pass and iterative decoding are similar?
A4. This similarity arises from PAM's full-mask training. Since PAM learns to predict the entire action chunk without conditioning on any target-action prefix, it does not strongly rely on previously generated actions even during iterative decoding.
To verify this, we conducted controlled prefix-corruption experiments (Table R4). We provided either a correct or an incorrect prefix (another sample's ground truth) of three actions and measured prediction errors for the remaining two actions.
Table R4. Controlled prefix corruption on the fixed PAM model (ATE/RPE).
| Condition | RECON | SCAND | HuRoN | TartanDrive |
|---|---|---|---|---|
| No prefix | 0.197 / 0.178 | 0.408 / 0.316 | 0.657 / 0.495 | 0.469 / 0.366 |
| Correct prefix | 0.200 / 0.174 | 0.385 / 0.306 | 0.585 / 0.479 | 0.475 / 0.371 |
| Wrong prefix | 0.203 / 0.177 | 0.379 / 0.290 | 0.599 / 0.480 | 0.511 / 0.394 |
As shown in Table R4, PAM maintains similar prediction accuracy regardless of prefix correctness, indicating limited dependence on previously generated target actions.
This explains why iterative decoding provides little additional benefit: PAM already generates accurate action trajectories in the first pass referred to as Single-pass in Table A4, while subsequent iterations have limited influence on the remaining predictions. Accordingly, achieves nearly identical SR 58.33% compared to Single-pass SR 59.03%. We therefore adopt single-pass decoding, achieving comparable navigation performance with only one forward pass instead of five.
W2-2 and Q5. Main contributions of PAM.
A5. As demonstrated in A4, PAM is trained without any target-action prefix, so it learns to predict action chunks without relying on previously generated actions. Consequently, even when iterative decoding reuses predicted tokens, their influence on subsequent predictions remains limited. This suggests that the main benefit comes from preventing target-prefix dependence during training, rather than simply eliminating token reuse at inference.
Table 4 further supports this interpretation. Under the same single-pass inference ((T=1)), replacing random masking with PAM improves SR from 38.89% to 59.03% (+20.14% points). In contrast, changing the decoding steps from (T=1) to (T=5) has little effect on PAM (59.03% vs. 58.33%).
Thus, as already highlighted in Section 5.3, full-mask training addresses target-prefix dependence at its source, while single-pass decoding ensures efficient, prefix-free inference.
Response Reminder
Dear Reviewer,
As we approach the end of the discussion period, we invite you to review the authors’ response to your comments. Please update us on whether your concerns have been sufficiently addressed and whether you wish to pose further questions to the authors.
We greatly appreciate your contribution.
Rebuttal by Authors (1/2)
W1-1 and Q1. Does ACC introduce a mismatch bias?
A1. The key distinction lies in how previous actions are used. In AR decoding, unexecuted predictions are reused to generate subsequent actions within the same chunk, allowing prediction errors to propagate before execution. In contrast, ACC conditions each new action chunk on executed motions and updated observations. Even if a previous action was suboptimal, its execution history still provides valid information about how the robot actually moved, helping maintain motion consistency without reintroducing within-chunk prediction errors.
We acknowledge that policy-executed histories may differ from expert histories. To quantify this distribution shift, we compared LLaDA-Nav's executed motions with the training data (Table R1).
Table R1. Distribution differences between policy-executed motions and training action histories.
Despite this substantial distribution shift, ACC improves closed-loop SR from 44.44% to 59.03% and reduces RPE from 0.49 to 0.34 (Table 3). These results show that ACC remains beneficial under the observed training–inference mismatch.
W1-2 and Q2. AR baseline with ACC.
A2. To answer this question, we evaluated Qwen3-VL-8B with and without ACC and compared standard AR fine-tuning against PAM under the same ACC setting.
Table R2. ACC ablation with AR baseline.
As shown in Table R2, adding ACC alone to standard AR fine-tuning decreases SR from 52.08% to 44.44%. However, under the same ACC setting, PAM improves SR to 58.33% (+13.89 points). These results demonstrate that the performance gains cannot be attributed solely to additional motion history, supporting PAM's contribution under matched conditions.
W1-3 and Q3. Discussion about the sharp performance drop in k=5 (ACC).
A3. The performance degradation at (k=5) also occurs in open-loop evaluation, where the model receives logged action histories, as during training. Compared with (k=3), (k=5) increases ATE from 0.68 to 0.97 and RPE from 0.34 to 0.47 (Table A6). This indicates that the degradation cannot be explained solely by the training–inference mismatch arising from policy-executed histories.
To investigate whether longer ACC histories cause excessive reliance on previous motions, we analyzed repeated in-place turning. Unlike repeated forward movements, which may indicate progress toward the goal, continuously turning in the same direction can lead to a full 360° rotation, returning the robot to its original heading without making progress. This provides a clear behavioral indicator of excessive motion persistence.
Table R3. Closed-loop turning behavior across ACC history lengths (144 episodes).
As shown in Table R3, (k=5) exhibits more repeated turn chunks than (k=3) (65.3% vs. 51.2%). While repeated turns can be necessary to reach the correct heading, excessive continuation becomes substantially more frequent: rotations continuing from 180° to 360° increase from 7.0% to 32.5%, and episodes containing a full spin increase from 4.9% to 23.6%.
These results suggest that redundant historical motion information encourages excessive persistence in previous movements, providing a plausible explanation for the substantial SR degradation at (k=5), beyond the proposed distribution mismatch.