- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies high-norm spatial tokens in World Action Models and finds that their influence on predicted actions persists after normalization and K/V projection attenuate their extreme magnitudes. It proposes RegisterWAM, combining non-spatial registers with observation flow-matching supervision and using register states to condition action generation. An additional noisy-observation objective trains current-scene recovery. The method is evaluated on LIBERO-Plus, RoboTwin 2.0, real-world manipulation, and an ImageWAM backbone.
Critical strengths
-
The representation analysis distinguishes activation magnitude from downstream action relevance. Tracing tokens through the K/V interface and measuring masked-token action sensitivity provides useful evidence beyond norm visualizations alone.
-
The method is motivated through informative controls. Registers alone do not eliminate final-layer outliers, while observation supervision and registers have complementary effects across layers. The comparison between register-only and combined conditioning also helps justify the interface choice.
-
Evaluation covers several complementary settings. The full LIBERO-Plus evaluation supports robustness across distribution shifts, while real-world experiments and ImageWAM transfer provide evidence beyond a single simulation benchmark.
Critical weaknesses
-
The explanatory depth of the representation findings remains limited. Masked-token sensitivity establishes that a token affects predicted actions, but does not establish what information it carries. Likewise, moving high-norm responses from spatial tokens to registers does not directly demonstrate a corresponding transfer of information. The relationship between this reorganization and improved policy performance therefore remains unresolved, particularly because observation supervision also helps without registers.
-
The methodological novelty is incremental, which makes the empirical evidence especially important. Registers and compact latent interfaces are established designs, while the paper does not report performance variability across training runs. This limits confidence in smaller gains, such as the RoboTwin improvement, although the broader LIBERO-Plus results are encouraging.
Questions for authors
-
Please specify the exact targets and weighting of the clean- and noisy-observation FM losses, particularly at . Does the zero-noise implementation use the standard velocity target ?
-
How was the 20% LIBERO-Plus evaluation subset selected? Please clarify the sampling unit, selection rule, task and perturbation coverage, and provide the instance list or generation procedure. Does Table 3 use this subset or the full benchmark?
-
How many independent training runs and evaluation trials support the principal comparisons? What variability is observed for the key ablation, RoboTwin, and ImageWAM results?
-
Beyond token norms and masked-token sensitivity, is there evidence distinguishing the proposed non-local representational role of outliers from the behavior of ordinary background tokens? Such evidence would strengthen my assessment of the empirical contribution.
3 comments
Q3/W2
About Q3/W2: Contribution, repeated training, and performance variability
Our contribution is the identification and functional analysis of spatial outliers in Video-DiT world-action models, together with the resulting register-based action interface and observation supervision.
We have supplemented the empirical evaluation with additional trained Full models, repeated additional component ablations, and an additional ImageWAM model. The current descriptive summaries are:
| Model/evaluation | Success rate (%) | Training results |
|---|---|---|
| Full, LIBERO-Plus: 10,030 instances | 3 | |
| Full, fixed subset: 2,008 instances | 3 | |
| No registers, fixed subset | 2 | |
| No clean FM, fixed subset | 2 | |
| ImageWAM + Ours, fixed subset | 2 |
The key component controls each include two separately trained checkpoints. The no-register results are 79.43% and 80.53%, and the no-clean-FM results are 79.38% and 79.18%, evaluated on the same fixed 2,008-instance subset.
Two ImageWAM training runs achieve 85.42% and 85.68%, yielding . Both runs use the original ImageWAM implementation and directly adopt the 20% LIBERO-Plus subset provided with its source code.
Given the substantial computational cost of repeating the RoboTwin training and evaluation pipeline, we prioritized supplementary experiments on LIBERO-Plus and ImageWAM.
All the above changes have been included in the latest revision.
Q1/Q2
About Q1: Observation FM targets and weighting at
At , the input is the clean observation latent , and we supervise the prediction with . This is the conditional expectation of the FM velocity target at the clean endpoint, since the noise is independent and zero-mean:
Under squared-error regression, this deterministic target has the same optimal predictor as the sampled velocity target at this endpoint. The loss averages over latent channels and spatial positions. The clean-observation term shares the visual-loss weight of 2 and the valid-frame normalization with future frames.
For the noisy-observation branch, the input is and the target is , with loss weight . We have clarified these targets and weights in Appendix D.1.
About Q2: Construction of the 20% subset and Table 3
The sampling unit is a benchmark instance (suite, task_id). We partition all 10,030 LIBERO-Plus instances into 28 suite perturbation-category strata, sort buckets and task IDs, and use a random generator initialized with sampling seed 42 to sample max(1, round(0.2*n)) without replacement per bucket. This yields 2,008 instances. This generation procedure specifies the instance selection reproducibly; the fixed instance list is retained for all component-ablation comparisons. Each selected instance has one rollout; this gives suite/category coverage rather than exact balance over task difficulty.
Table 1 uses the full 10,030-instance benchmark; Table 3's ImageWAM+Ours directly uses the 20% LIBERO-Plus subset (2,008 instances) provided with the original ImageWAM code, where our method achieves using the original ImageWAM implementation. The baseline of 83.10% is taken from the ImageWAM paper.
We will release the subset-generation code and the fixed 2,008-instance evaluation list alongside our code release to enable exact reproduction of the evaluation subset.
All the above changes have been included in the latest revision.
Summary and Q4/W1
We thank the reviewer for recognizing the representation analysis and the breadth of our evaluation. We have added local/global generation interventions in FastWAM and OpenWAM[1](extra WAM), clarified the flow-matching implementation and evaluation protocol, and supplemented the empirical evidence with additional training and evaluation results on LIBERO-Plus and ImageWAM.
About Q4/W1: The non-local role of spatial outliers and policy performance
Our additional experiments support a non-local computational role for spatial outliers, consistently across FastWAM and OpenWAM. We mask observation-token K/V contributions in layers 20-27 and compare future-video generation with the unmasked output using the same initial noise. Local and global generation-change MSE measure the spatial extent of the intervention, while PSNR changes characterize its effect on reconstruction fidelity (new Figures 13-14).
Compared with ordinary-token masking, outlier masking produces smaller changes at its corresponding spatial location but larger changes across the generated video. The median per-observation outlier-to-ordinary local/global MSE ratios are 0.0144/6.54 for FastWAM and 6.45×10−6/10.63 for OpenWAM. The global PSNR distributions also show a broader response to outlier masking.
This distinction persists within the same padding region. In OpenWAM, we compare the outlier with the other 19 tokens in its native padding region. Relative to their mean perturbation effect within each observation, the outlier exhibits median local/global MSE ratios of 0.0137/30.92, demonstrating substantially stronger global influence despite sharing the same padding region. These analyses use 200 observations from distinct episodes spanning all 40 LIBERO tasks.
Together, these interventions provide evidence beyond action sensitivity that spatial outliers exert influence beyond their corresponding image regions. This motivates dedicated non-spatial registers, together with observation FM supervision to constrain spatial representations. Figure 15 shows their complementary effects: registers attenuate intermediate-layer spatial peaks, while observation supervision suppresses residual terminal-layer peaks. The component ablations further connect this design to task performance (Appendix C.2, Table 9).
We interpret the norm redistribution as representation reorganization; the generation interventions establish its non-local functional motivation, and the component controls assess the resulting policy design.
[1] Wang et al. OpenWAM. https://arxiv.org/abs/2609.07398