- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Copper-Policy learns a compact, task-conditioned world representation through joint future prediction and action supervision. An EMA compactor provides future targets, while an asymmetric interface preserves current-frame visual details for action generation. Future prediction is omitted at deployment. Evaluations on LIBERO, LIBERO-Plus, RoboTwin, and three real-robot tasks demonstrate competitive control performance with substantially reduced training costs.
Critical strengths
1.A practically useful combination of predictive representation learning and efficient control. The compact prediction pathway and separate current-frame visual pathway provide a sensible balance between temporal representation learning and precise execution. The reported training cost(9.67 hours on eight RTX 5090 GPUs) makes the approach practically relevant.
2.Broad empirical evidence supporting the complete system. Evaluation spans standard manipulation, distribution shifts, and physical robot tasks. Component ablations support the usefulness of both predictive supervision and current-frame features, while representation diagnostics provide additional evidence of complementary information in the two pathways. Together, these results offer useful insights beyond aggregate benchmark performance.
Critical weaknesses
1.The specific methodological contribution could be better isolated. FLARE already employs compact, action-aware representations and EMA target adaptation. Although this is acknowledged, the additional benefit of Copper-Policy’s target-space formulation remains insufficiently established. Removing prediction does not distinguish jointly learned targets from fixed or staged targets, and removing current-frame features does not isolate the asymmetric attention design. These gaps limit the strength of the novelty and attribution claims.
2.Some empirical conclusions require stronger qualification. Independent training seeds are not reported for the main policy results, limiting interpretation of both small comparative gains and large ablation drops. Robustness improvements also vary across perturbation categories. The representation diagnostics are informative, but their connection to improved closed-loop control remains primarily correlational.
Questions for authors
1.What is the precise distinction between your jointly learned target space and FLARE’s action-aware encoder with EMA adaptation? Is there controlled evidence demonstrating the benefit of this distinction?
2.Do you have comparisons isolating the asymmetric attention mask or comparing future flow matching against direct feature regression or cosine alignment?
3.How reproducible are the real-robot ablation results? In particular, why does removing prediction severely degrade towel folding and banana placement while leaving bowl stacking unchanged?
4 comments
# Response to Reviewer u539 — Part 2/3
Response to Reviewer u539 — Part 2/3
W1 / Q2: Auxiliary vision, asymmetric mask, and direct regression
Asymmetric attention mask
The original visual-feature ablation tests the auxiliary pathway; the new mask ablation tests its access constraint while retaining that pathway. The asymmetric interface has two parts: action decoding receives auxiliary current-frame features, and the mask restricts future queries from directly accessing them. Removing visual features tests the first part; allowing all Future-branch tokens to attend to them tests the second.
| Configuration | LIBERO Avg. | LIBERO-Plus Total | RoboTwin Clean | RoboTwin Random | RoboTwin Avg. |
|---|---|---|---|---|---|
| Copper-Policy | 97.25 | 80.85 | 70.84 | 12.98 | 41.91 |
| w/o Visual Features | 95.45 | 74.11 | 67.82 | 10.22 | 39.02 |
| w/o Asymmetric Mask | 96.65 | 81.03 | 65.72 | 10.48 | 38.10 |
All entries are success rates (%) using training seed 42. Removing the mask reduces LIBERO by 0.60 points and RoboTwin average by 3.81, while increasing LIBERO-Plus by 0.18. Camera, Robot, and Noise improve without the mask, while Light, Background, and Layout decline. Section 4.5 reports these category-dependent effects. Removing the auxiliary visual pathway is especially harmful on the real robot, reducing the score from 96.3 to 20.7. The two interventions therefore examine complementary aspects of the interface.
Direct future-embedding regression
We also evaluated direct future-embedding regression. Specifically, we replaced the Future Expert's noise input with a learnable input and trained it with L1 loss:
| Configuration | LIBERO Avg. | LIBERO-Plus Total | RoboTwin Avg. |
|---|---|---|---|
| Copper-Policy | 97.25 | 80.85 | 41.91 |
| Learnable input + L1 loss | 96.65 | 77.04 | 33.55 |
The predictor struggled to reduce L1 training loss. We hypothesize that future multimodality contributes to this fitting difficulty; investigating this explanation remains future work. This variant changes both input and objective; Appendix E, Table A6 reports it as that specific regression configuration.
W2: Independent seeds and the robustness claim
Independent training seeds
We have added three independent training seeds, 0, 7, and 42, for the main simulation policy:
| Benchmark | Mean sample std (%) |
|---|---|
| LIBERO Avg. | 97.0 0.2 |
| LIBERO-Plus Total | 80.8 0.2 |
| RoboTwin Clean | 70.87 0.08 |
| RoboTwin Random | 13.00 0.05 |
| RoboTwin Avg. | 41.94 0.03 |
Tables 2–3 report these comparison statistics separately from the ablations, which use a common seed 42 reference.
Robustness across perturbation categories
The effects vary by category:
| Configuration | Camera | Robot | Noise |
|---|---|---|---|
| Copper-Policy | 78.67 | 73.74 | 94.44 |
| w/o JE Pred. | 76.17 | 78.58 | 91.63 |
LIBERO-Plus success rates (%), with training seed 42. Removing prediction lowers Camera and Noise performance while improving Robot. Removing the mask also has mixed effects, improving Camera, Robot, and Noise but lowering Light, Background, and Layout (Section 4.5).
Changes in the learned representation
The original representation diagnostics characterize changes associated with predictive shaping: temporal organization, sensitivity to perturbations, and complementary action information in the two pathways (Section 4.6; Appendix C):
| Diagnostic | w/o JE Pred. | Copper-Policy |
|---|---|---|
| Perturbation–temporal overlap (rank 8) | 0.798 | 0.187 |
| Paired perturbation distance | 0.344 | 0.134 |
| Action-probe input | |
|---|---|
| World features | 0.802 |
| Current-frame features | 0.910 |
| Both pathways | 0.927 |
These correlational analyses describe how the representation changes with predictive shaping. We leave further analysis of how these changes causally affect closed-loop success to future work.
# Response to Reviewer u539 — Part 3/3
Response to Reviewer u539 — Part 3/3
Q3: Real-robot evaluation and unchanged bowl stacking
All policies are evaluated on the same 50 initial scenes per task, with the same platform, observations, action space, and execution protocol. Appendix D.3 and Table A5 provide the full/half/failure counts. Copper-Policy scores 96.3 overall, compared with 94.3 for [1] and 84.0 for Fast-WAM [2]; we describe its performance relative to as comparable.
The prediction ablation has different effects across tasks:
| Configuration | Fold Towel | Put Banana | Stack Bowls | Average |
|---|---|---|---|---|
| Copper-Policy | 93 | 96 | 100 | 96.3 |
| w/o Joint-Embedding Prediction | 4 | 26 | 100 | 43.3 |
| w/o World Branch | 84 | 82 | 88 | 84.7 |
We thank the reviewer for highlighting this task difference. We checked the prediction ablation with three independent training seeds, 0, 7, and 42, after observing the original degeneration. Across all three seeds, towel folding and banana placement degraded, while bowl stacking remained successful. The manuscript retains the seed 42 models as the common ablation reference, and the table above reports those scores.
The original RoboTwin per-task results show the same contrast among tasks on which the full model already succeeds at high rates:
| RoboTwin task (Clean) | Copper-Policy | w/o Joint-Embedding Prediction |
|---|---|---|
| adjust bottle | 100 | 100 |
| shake bottle horizontally | 100 | 100 |
| place cans plasticbox | 92 | 29 |
| place empty cup | 95 | 44 |
All entries are success rates (%), with 100 rollouts per task. The first two retain their high performance, while the latter two lose 63 and 51 percentage points. The task-dependent effect therefore also occurs in simulation among tasks with high full-model performance. The scores are reported in the original supplementary RoboTwin per-task results.
This pattern is consistent with tasks differing in fitting difficulty and control-information requirements. It supports a task-dependent role for predictive shaping, including tasks where removing prediction preserves performance and tasks where it causes a large decline.
References
[1] K. Black et al., “: A Vision-Language-Action Model with Open-World Generalization,” in Proc. 9th Conf. Robot Learning (CoRL), ser. Proceedings of Machine Learning Research, vol. 305, 2025, pp. 17–40. [Online]. Available: https://proceedings.mlr.press/v305/black25a.html
[2] T. Yuan, Z. Dong, Y. Liu, and H. Zhao, “Fast-WAM: Do World Action Models Need Test-time Future Imagination?,” arXiv preprint arXiv:2603.16666, 2026.
Final Response to Reviewer u539
As the discussion period draws to a close, we would like to sincerely thank you once again for recognizing the value of our representation design and empirical evaluation. Your constructive comments helped us strengthen the experimental evidence, clarify our methodological contribution, and improve the manuscript. We will ensure that these improvements are incorporated into the final version of the paper. We sincerely appreciate your careful review and valuable feedback, and look forward to further academic exchanges with you.
# Response to Reviewer u539 — Part 1/3
Response to Reviewer u539 — Part 1/3
We sincerely thank the reviewer for recognizing the practical value of the representation design, the broad empirical evaluation, and the complementary information in the two visual pathways. We have clarified the description of our representation design to better reflect our central research question: how to learn and use a compact World representation for control. We have also added attention-mask, action-gradient, learnable-input regression, and multi-seed results.
W1 / Q1: Relationship to FLARE and the representation design
FLARE [1] indeed shares EMA adaptation and action-aware representations with Copper. The distinction lies in the complete representation design, including what prediction shapes and how action decoding accesses the resulting information.
FLARE uses a Q-former-based vision-language encoder to provide current-observation context to an action-denoising DiT. Learnable future tokens interact with action and state tokens within that DiT. The cosine alignment is applied to the future-token hidden representations at an internal Transformer layer of the action DiT, using future-observation embeddings from an EMA policy encoder as targets.
Copper's online and EMA compactors map current and future observations into the same compact, task-conditioned World space. A separate Future Expert predicts future-view embeddings from the current World representation, while action supervision shapes both the compact input and its contextual pathway. The asymmetric interface additionally supplies current-frame visual features to action decoding while restricting future queries from directly reading them. Action tokens never read predicted future tokens. These learning and information-flow relationships distinguish the formulation; EMA adaptation alone is a shared ingredient. We have clarified these relationships in the Introduction and Related Work.
A matched FLARE reproduction requires architectural and training changes across its coupled prediction and action pathways; we have not undertaken that transfer. Our controlled evidence comes from interventions within Copper, described below; these directly test predictive shaping, auxiliary vision, masking, and action-gradient flow.
The original component ablations test the World and visual pathways and predictive shaping. The original diagnostics examine temporal organization and complementary action information in these pathways. Together, they support the representation's usefulness for control.
To further explain the mechanism, we added three simulation variants: w/o Asymmetric Mask and the two action-gradient interventions. The mask variant complements the original w/o Visual Features ablation to examine information routing. The action-gradient results are:
Success rates (%), with training seed 42.
The larger losses after additionally blocking the contextual World pathway support the role of action shaping throughout that pathway. This intervention retains joint-embedding prediction, also testing whether a World space shaped by prediction alone can support the policy. The performance drop shows that predictive shaping alone is insufficient to sustain the full policy’s performance. Section 4.5 distinguishes the purposes of these comparisons.
References
[1] R. Zheng et al., “FLARE: Robot Learning with Implicit World Modeling,” in Proc. 9th Conf. Robot Learning (CoRL), ser. Proceedings of Machine Learning Research, vol. 305, 2025, pp. 3952–3971. [Online]. Available: https://proceedings.mlr.press/v305/zheng25a.html