- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper proposes EWAM, a unified world-action model that aligns a vision-language expert (Qwen3-VL-2B), a video generation expert (Wan2.2-TI2V-5B), and an action expert across layers under an asymmetric attention mask. By analyzing action-query attention across depth, the authors argue that the model develops an emergent three-stage specialization—shifting from VL tokens in shallow layers to predicted-future tokens in middle layers and action self-attention in deep layers—and report strong results on RoboTwin 2.0, LIBERO, and real-robot tasks.
Critical strengths
- I appreciated the care the authors took in measuring attention routing. They normalize attention by token count, report bootstrap confidence intervals across 50 tasks, and track how routing changes during training. The targeted KV injections and the ablations on attention masks and layer-wise access made the analysis more useful to me because they let me compare the observed routing patterns with what happens when the policy’s access to each stream changes.
- EWAM scores 72.1% on RoboTwin 2.0 clean-to-random (C2R), well above the previously reported results. I give this result weight because many world-action models struggle when they move from clean training layouts to randomized test layouts.
Critical weaknesses
- My main reservation is about the paper’s central claim that depth-wise specialization emerges during joint training and is critical to policy performance. In Table 1, switching from the asymmetric mask to symmetric full attention brings the score from 83 to 81, even though the bidirectional variant in Appendix B.6 largely loses the middle-layer handoff from image to future tokens. Removing shallow-layer VL access or middle-layer video access costs 5 points in each case. Restricting the deep layers to action self-attention leaves the score unchanged. Raw attention mass is also hard to interpret as a measure of functional importance. VL tokens receive 75.4% of shallow-layer attention, and masking them costs 16 points. Video tokens receive just 15% of deep-layer attention, and masking them costs 27 points. Given the layer-by-layer alignment with pretrained Qwen3-VL and Wan2.2, I suspect EWAM inherits much of the depth profile from those backbones.
- I find it hard to tell how much of the 72.1% C2R result comes from the architecture. EWAM is pretrained on roughly 1,800 hours of curated robot data, and the paper gives no C2R result without that pretraining. I have a similar concern about the human-video experiments. The cross-embodiment comparison uses training from scratch as its only baseline, so it leaves open how human egocentric pretraining compares with robot pretraining. In Table 20, training on 90 robot-only episodes reaches 70%, compared with 60% for the best human-robot co-training setup.
Questions for authors
- For the Table 1 variants that score 83, 81, and 78, how much do the results vary across seeds? If you ran multiple seeds, could you report confidence intervals? Separately, does the three-stage depth profile persist under a different backbone alignment, such as feeding the final Qwen3-VL layer into every block?
- Given the mismatch between raw attention mass and the masking results, do you see the same routing pattern with value-weighted attention or gradient attribution? How does masking future keys in the middle layers compare with masking the same number of randomly selected keys?
- What C2R score does EWAM reach on RoboTwin 2.0 without the 1,800 hours of robot pretraining? On the held-out Aloha-Agilex-2 embodiment, how does human egocentric pretraining compare with robot pretraining?
5 comments
Response to Reviewer VEeM (2/2)
W1 & Q2: Attention mass versus masking impact
- As stated in Sec. 4.2 (p. 6), attention mass shows where action tokens retrieve information, while Sec. 4.3 tests functional necessity. The paper does not use mass to predict the size of a masking drop. As noted in the Limitations (Appendix F, p. 44), neither measure alone provides a complete causal decomposition of the computation.
- [New experiment] As suggested, we recomputed the stage profile with value-weighted attention on the same 50 RoboTwin tasks (one sequence each, robot-pretrained checkpoint):
| Stage | Raw attention: VL / video / action (%) | Value-weighted [New]: VL / video / action (%) |
|---|---|---|
| Shallow (0–9) | 75.4 / 14.1 / 10.6 | 59.6 / 22.7 / 17.7 |
| Intermediate (10–19) | 36.6 / 24.3 / 39.1 | 27.2 / 33.2 / 39.5 |
| Deep (20–29) | 25.2 / 15.3 / 59.5 | 19.8 / 22.4 / 57.8 |
The three stages hold. VL dominates the shallow stage and action the deep stage. In the intermediate stage, attention still shifts from the current image to predicted future frames: VL-image attention drops from 31.4% in the shallow stage to 7.9%, while future-frame attention rises from 14.4% to 22.4% and exceeds the VL image.
- [New experiment] Random-key masking with an equal number of keys, layers 10–19:
| Masked keys, layers 10–19 (robot-pretrained checkpoint) | Success (%) |
|---|---|
| None | 92.80 |
| Future keys | 3.55 |
| Equal number of random keys [New] | 82.80 |
Removing the same number of random keys costs 10 points, whereas removing future keys collapses success to 3.55%; the collapse is therefore specific to predicted-future content, not to the number of masked keys. We added this row to Table 1 (p. 8) and Sec. 4.3 (p. 7).
W2 & Q3 (first part): C2R without robot pretraining
[New experiment] As requested, we trained EWAM for C2R without robot pretraining and compared it with published results of methods that also use no robot pretraining:
| RoboTwin 2.0 C2R, no robot pretraining | C2R (%) |
|---|---|
| Fast-WAM | 1.90 |
| starVLA | 3.16 |
| EWAM [New] | 24.2 |
Without robot pretraining, EWAM still clearly outperforms starVLA and Fast-WAM trained under the same condition. Fast-WAM builds on the same Wan2.2 video backbone yet reaches only 1.90, so EWAM's advantage does not stem from the video prior or from pretraining scale alone.
W2 & Q3 (second part): Human versus robot pretraining, and G1-D co-training
- Co-training results. We agree that 90 robot demonstrations outperform the best 60-robot/30-human mixture on G1-D pouring (70% vs. 60%). This gap shows that human demonstrations do not yet fully substitute for additional robot demonstrations in this setting. On the same 60 robot + 30 human mixture, however, human-pretrained initialization improves success from 40% to 60% compared with robot-pretrained initialization. In the robustness evaluation with tablecloth and cup changes, 30 egocentric episodes match 30 additional robot episodes (both 20%), and scaling to 1,000 raises success to 60% (Fig. 5(d), p. 10). Our goal is to reduce costly teleoperation, and these results show that cheap egocentric human data can partly replace robot demonstrations.
[New experiment] Human versus robot pretraining. We added robot-pretrained EWAM under the same protocol: training on ARX-X5, UR5, Franka, and Piper, then evaluating transfer to Aloha-Agilex-2 across 50 RoboTwin tasks.
[New table] Success rates (%) at downstream training steps:
| EWAM initialization | 40K | 50K | 80K | 120K |
|---|---|---|---|---|
| No embodied pretraining | 33.5 | 37.2 | 40.1 | 36.2 |
| Robot pretraining [New] | 50.8 | 60.4 | 61.6 | 55.3 |
| Human pretraining | 44.3 | 53.4 | 58.9 | 66.9 |
Robot pretraining leads at 40K–80K, while human pretraining continues improving to 66.9% at 120K, an 11.6-point gain over robot pretraining. Comparing the best observed checkpoints also favors human pretraining: 66.9% vs. 61.6%, a 5.3-point gain. These results appear in Sec. 5.2 (p. 9), Fig. 5(a) (p. 10), and Appendix D.6 (Table 23, p. 40).
Dear Reviewer VEeM,
Please respond to the author soon and engage in the discussion. Please revise the review and avoid AI usage.
Best,
AC
Response to Reviewer VEeM (1/2)
We thank Reviewer VEeM for the careful review and for finding the routing analysis well beyond standard attention heatmaps and the clean-to-random generalization strong. In the revised paper, revisions specific to your comments are marked in green, and revisions addressing points raised by both you and other reviewers are marked in orange. Replaced wording is struck through.
W1: Magnitude of the Table 1 ablations
W1 & Q1: Inheritance from layer-aligned backbones, and multi-seed intervals
Action-attention mass by stage, final-layer variant [New] (4 GPUs, same data and recipe as Table 1 left):
Although every block now reads identical final-layer VL features, the same three stages emerge during training: shallow layers read VL (0.815), intermediate layers favour predicted future frames over the current image (0.204 vs. 0.095 / 0.084), and deep layers focus on action (0.667), with no division at 50 steps. The routing is therefore learned in joint training, as claimed in Sec. 4.2 (p. 7), not inherited from layer-by-layer alignment. With the full training budget of Table 1 (left), this variant reaches 79%, compared with 83% for the layer-aligned model. We added these results to Table 1 (p. 8), Secs. 4.2 and 4.3 (p. 7), and Appendix B.7 (p. 27).
The intervals of the three levels do not overlap, so the ordering 83 > 81 > 78 holds across seeds.