- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Z-WAM adapts an image-editing backbone to jointly denoise a single future multi-view observation and a 48-step robot action chunk. Sequential action-to-visual and visual-to-action attention couples the two streams. Training proceeds through robot visual adaptation, joint world-action pretraining, and task-specific fine-tuning. Additional objectives supervise cumulative joint displacement around gripper closure and emphasize gripper state transitions. Preliminary evaluation on six real-robot tasks reports 18 successes in 30 trials and 82.5% average partial completion, compared with lower scores for several available policy baselines.
Critical strengths
-
The endpoint formulation is practically motivated. Predicting one future visual state while retaining a full executable action sequence is a reasonable way to reduce visual prediction requirements. The manuscript correctly states that the editing stream remains active at inference even when RGB decoding is omitted.
-
The action supervision is described concretely. The cumulative joint-increment representation, closure-window weighting, detached selector, underreach penalty, and gripper BCE are explicitly defined. The distinction between commanded joint configuration and measured Cartesian outcome is useful.
-
The preliminary real-robot results are encouraging. The tasks include bimanual transport and handover, and Table 1 reports a substantial observed completion-rate advantage. The paper includes pose/gripper and cumulative-pretraining comparisons rather than only a full-system result.
-
The manuscript is candid about unfinished evidence. It identifies reused physical trials, missing provenance, pending generalization, and limits of the five-trial comparisons. This transparency is valuable, although the missing evidence still affects the recommendation.
Critical weaknesses
-
The main evaluation is not yet a finalized experimental record. Each method/task has only five trials, and Appendix E says terminal success, assistance/safety conditions, scoring versions, resets, and method ordering remain to be reconciled with the reported records. Appendix A also leaves final demonstration counts and split manifests unresolved. These are necessary details for interpreting the reported 18/30 success rate and baseline gap, not merely optional documentation.
-
The central architectural contribution lacks its decisive control. Image-editing-based robot control is already established by ImageWAM. Z-WAM's distinctive sequential bidirectional coupling therefore needs a controlled comparison, but that experiment is explicitly pending. The planned removal of feedback only after bidirectional pretraining would test retention during adaptation, not the full effect of coupling throughout training.
-
The component results do not isolate the proposed mechanisms. Table 2 lacks a gripper-BCE-only condition and a uniformly weighted BCE control; PredU is not separated from uniform closure-window supervision or ordinary accumulated-command loss. Table 3 adds data and compute together with training stages and omits joint pretraining without robot-visual adaptation. The observed gains cannot yet be attributed specifically to transition weighting, prediction-weighted closure alignment, or progressive staging.
-
The efficiency motivation is unmeasured. A single future target reduces token requirements in principle, but the editing backbone still participates in ten joint denoising steps. Appendix D leaves measured inference costs and deployment settings unfinished, including the executed prefix. Without observation-to-action latency, memory/compute, and matched endpoint-versus-video comparisons, the practical efficiency advantage remains unestablished.
-
Generalization and baseline comparability remain unresolved. Held-out object, layout, and background tests are planned rather than reported. Run-specific baseline checkpoint, training-exposure, normalization, and execution records also remain incomplete. Consequently, the present six-task comparison supports preliminary feasibility but cannot separate architectural benefits from differences in initialization, adaptation, or deployment.
Questions for authors
- Can you provide finalized per-trial outcomes under one success protocol, including deadlines, interventions, matched resets, randomized ordering, and uncertainty estimates?
- What is the effect of bidirectional coupling when pretraining and adaptation are both controlled, using the same initialization, data, and compute?
- Do the benefits persist with gripper-only, uniformly weighted BCE, fixed/uniform closure-window, and equal-exposure pretraining controls?
- What are the complete inference latency, executed action prefix, and baseline deployment settings? Are any held-out generalization results available in the completed experiment set?
5 comments
Response to Reviewer jPd4
Response to W3: Loss Functions and Pretraining Attribution
Thank you for pointing this out. We conducted additional controlled ablations on gripper supervision, action supervision, and progressive pretraining. All variants were evaluated on Place Three Objects and Hand Over the Object, with 15 independent trials per task under the same protocol.
1. Gripper Supervision Ablation. We compare BCE-only, uniform BCE, and transition-weighted BCE configurations, with and without PredU, to isolate the contribution of gripper supervision and transition weighting. As shown in Table R6, with PredU fixed, transition-weighted BCE achieves 86.7% SR and 93.9% CR, outperforming uniform BCE (56.7% SR / 73.1% CR). Notably, uniform BCE does not consistently outperform the no-BCE variant, highlighting the importance of transition-aware weighting.
Table R6: Ablation study on gripper supervision. Each entry reports success rate (SR, %) followed by mean completion rate (CR, %).
| PredU | Gripper Supervision | Place Three Objects | Hand Over the Object | Average |
|---|---|---|---|---|
| × | None | 40.0 / 63.3 | 20.0 / 41.7 | 30.0 / 52.5 |
| × | BCE-only | 46.7 / 91.1 | 20.0 / 33.3 | 33.3 / 62.2 |
| ✓ | None | 53.3 / 87.8 | 60.0 / 70.0 | 56.7 / 78.9 |
| ✓ | Uniform BCE | 73.3 / 91.1 | 40.0 / 55.0 | 56.7 / 73.1 |
| ✓ | Transition-weighted BCE (Z-WAM) | 86.7 / 97.8 | 86.7 / 90.0 | 86.7 / 93.9 |
2. Action Supervision Ablation. Without auxiliary gripper BCE, we compare ordinary accumulated-command loss, fixed reference closure, uniform and prediction-weighted closure windows, and the complete PredU objective. As shown in Table R7, PredU achieves the highest average SR (56.7%) and CR (78.9%). Although ordinary accumulated-command supervision performs better on Place Three Objects, PredU achieves substantially stronger performance on Hand Over the Object, suggesting improved robustness for grasp-sensitive manipulation. The weaker results without directional underreach further indicate the importance of combining the two components.
Table R7: Ablation study on action supervision without auxiliary gripper BCE. Each entry reports SR / CR (%).
| Action Supervision | Place Three Objects | Hand Over the Object | Average |
|---|---|---|---|
| None (base loss only; NoPose) | 40.0 / 63.3 | 20.0 / 41.7 | 30.0 / 52.5 |
| Ordinary accumulated-command loss | 80.0 / 96.7 | 26.7 / 45.0 | 53.3 / 70.8 |
| Fixed reference closure | 26.7 / 67.7 | 0.0 / 0.0 | 13.3 / 33.9 |
| Uniform closure window | 40.0 / 86.7 | 6.7 / 25.0 | 23.3 / 55.8 |
| Prediction-weighted closure window | 0.0 / 41.1 | 26.7 / 45.0 | 13.3 / 43.0 |
| PredU (full, without auxiliary BCE) | 53.3 / 87.8 | 60.0 / 70.0 | 56.7 / 78.9 |
3. Progressive Pretraining Ablation. We compare joint world–action pretraining with and without preceding robot-domain visual adaptation. To control for additional training exposure, we include an extended-pretraining variant that reallocates the visual adaptation budget to joint pretraining, matching the total training budget. As shown in Table R8, the full progressive pipeline achieves 86.7% SR and 93.9% CR, substantially outperforming all alternatives. In particular, extended joint pretraining fails to recover the performance of the full pipeline, supporting the benefit of progressive staging beyond additional computation.
Table R8: Ablation study on progressive pretraining. Each entry reports SR / CR (%). All variants retain general editing initialization and task-specific fine-tuning; extended pretraining matches the total training budget of the full pipeline.
| Robot-domain Visual Adaptation | Joint World–Action Pretraining | Place Three Objects | Hand Over the Object | Average |
|---|---|---|---|---|
| × | × | 0.0 / 21.1 | 0.0 / 8.3 | 0.0 / 14.7 |
| ✓ | × | 0.0 / 11.1 | 0.0 / 5.0 | 0.0 / 8.1 |
| × | ✓ | 53.3 / 87.8 | 0.0 / 25.0 | 26.7 / 56.4 |
| × | ✓ (extended pretraining) | 0.0 / 73.3 | 13.3 / 35.0 | 6.7 / 54.2 |
| ✓ | ✓ (Z-WAM) | 86.7 / 97.8 | 86.7 / 90.0 | 86.7 / 93.9 |
Overall, these controlled experiments provide further evidence for the effectiveness of transition-weighted gripper supervision, the complete PredU objective, and progressive pretraining. The expanded results will be incorporated into the revised manuscript.
Response to Reviewer jPd4
Response to W4: Efficiency and Execution Settings
To evaluate the practical inference efficiency of Z-WAM, we conducted additional latency benchmarks against representative video-based WAMs, including LingBot-VA, Motus, and Fast-WAM-Joint.
The measurements cover model-side observation-to-action inference, including visual preprocessing and encoding, all denoising required for action prediction, and action postprocessing. For Z-WAM, this includes all ten joint denoising steps. Camera capture, communication, and physical execution are excluded. For each configuration, we collected 150 timed measurements across three independent model loads after warm-up, reporting mean, P50, and P95 latency.
As shown in Table R4, Z-WAM achieves a mean inference latency of 672.05 ms, lower than LingBot-VA (4,535.49 ms), Motus (1,464.98 ms), and Fast-WAM-Joint (809.81 ms). Z-WAM also achieves the lowest P50 and P95 latency among these configurations.
We have clarified the deployment settings in Appendix B.2: at each inference call, Z-WAM predicts a 48-step action chunk (H = 48) and executes the first 24 steps (K = 24) before replanning based on the latest observation. The measurement protocol and complete latency results are reported in Appendix F. These results demonstrate a model-side latency advantage under the evaluated configurations.
Table R4: Model-side inference latency of representative world–action models.
| Method | Inference Mode | Denoising Steps | Mean (ms) ↓ | P50 (ms) ↓ | P95 (ms) ↓ |
|---|---|---|---|---|---|
| LingBot-VA | Video + Action (successive stages) | 10 + 10 | 4,535.49 | 4,527.02 | 4,583.00 |
| Motus | Joint Video–Action | 10 | 1,464.98 | 1,483.59 | 1,539.54 |
| Fast-WAM-Joint | Joint Video–Action | 10 | 809.81 | 796.95 | 856.09 |
| Z-WAM (Ours) | Joint Image–Action | 10 | 672.05 | 672.67 | 680.01 |
Response to W5: Generalization and Baseline Comparability
Thank you for pointing this out. We have conducted additional generalization experiments and clarified the baseline configurations to address these concerns.
Generalization. Building on the preliminary demonstrations in our supplementary video, we conducted quantitative experiments under three progressively accumulated variations involving object types, basket shapes, spatial arrangements, and backgrounds. Z-WAM and ImageWAM were evaluated under the same conditions without additional fine-tuning, with 15 independent trials per setting. As shown in Table R3, Z-WAM consistently achieves higher completion rates across all three settings, reaching 53.3% SR under G1 and G2. Although performance decreases under the more challenging G3 setting, Z-WAM still outperforms ImageWAM in completion rate (58.3% vs. 16.7%). These results provide further evidence of generalization under varying task conditions.
Baseline Comparability. We have clarified the baseline configurations, including model initialization, training data and exposure, normalization, deployed checkpoints, and execution settings, in Section B.1 and B.2 of the revised Appendix. Furthermore, the controlled ablations in Tables R1 and R6–R8 use matched initialization, training data, and training budgets to isolate the contributions of bidirectional interaction, action supervision, and progressive pretraining. Together, these results provide additional evidence that Z-WAM's performance improvements are supported by its architectural and training designs, rather than solely by differences in experimental configurations.
Response to Reviewer jPd4
We thank the reviewer for their careful review and constructive feedback. To address the key concerns, we expand real-world evaluations to 15 trials per task and method and clarify the evaluation protocol (W1), provide a controlled bidirectional ablation across pretraining and fine-tuning (W2), add ablations on gripper supervision, action supervision, and progressive pretraining (W3), report measured inference latency and deployment settings (W4), and present quantitative generalization results alongside clarified baseline configurations (W5). We detail these findings and address the related questions below.
Thank you for pointing this out. We have finalized the real-world evaluation protocol and expanded the experiments from 5 to 15 independent trials per task and method. The updated results are reported in Table R2 and have been incorporated into Table 1 of the revised manuscript.
We have also revised the Appendix to clarify the task-specific success and completion criteria, intervention and safety conditions, reset procedures, and evaluation ordering. In addition, we have finalized the demonstration counts and data split manifests to ensure consistency between the experimental records and reported results. These revisions provide a more complete and reproducible evaluation of Z-WAM and its baselines.
Thanks for pointing this out. We conducted an additional controlled ablation comparing the full Z-WAM with a unidirectional variant that allows only visual-to-action information flow. Specifically, the unidirectional variant removes action-to-visual feedback throughout both joint world–action pretraining and task-specific fine-tuning, rather than only during fine-tuning. Both variants use the same image-editing backbone, training data, objectives, and training schedule, ensuring a controlled comparison.
We evaluated both variants on two representative real-world manipulation tasks, Place Three Objects and Hand Over the Object. As shown in Table R1, bidirectional interaction improves success rates by 40.0 and 66.7 percentage points on the two tasks, respectively, while also increasing completion rates from 87.8% to 97.8% and from 40.0% to 90.0%. These results demonstrate the effectiveness of bidirectional visual–action interaction in improving manipulation performance.
Table R1: Ablation study on bidirectional interaction. Each entry reports success rate (SR, %) followed by mean completion rate (CR, %), separated by a slash. Each variant is evaluated over 15 independent trials per task. The full-model trials are shared with the corresponding rows in the other tables and are not additional independent trials.