- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Q-WAM, a post-training weight-and-activation quantization method for world action models. It estimates an Action Observability Gramian (AOG) through the unrolled denoising process to measure how activation perturbations affect the final action. Action-Subspace Protection (ASP) preserves the leading action-sensitive directions in a rank-32 16-bit branch while quantizing the complementary computation to 4 bits. For multi-expert models, aggregated sensitivity guides which experts receive protection. Evaluation covers three models on 50 RoboTwin 2.0 tasks under clean and randomized conditions, together with five physical-robot tasks. For success rates averaged over clean and randomized conditions, Q-WAM remains within 1.1 percentage points of bf16 and improves over SVDQuant by 2.53–8.69 points. The paper also reports 3.1–3.4× compression of targeted blocks and 1.06–1.56× speedups for the measured quantized action-token layers.
Critical strengths
-
An informative connection between action sensitivity and precision allocation. The paper measures sensitivity through the complete denoising process and uses its dominant directions to define a small protected subspace. Figure 3a provides direct motivation: in the Fast-WAM single-layer quantization study, AOG-based scores correlate with action damage at 0.95, compared with 0.04 for local activation error. The connection from this observation to ASP and expert selection gives the method a coherent rationale. This is consequential because it identifies a useful criterion for preserving behavior when compressing iterative action-generation models.
-
Consistent empirical gains with favorable storage costs. Table 1 reports improvements over SVDQuant across all three evaluated models, including both clean and randomized settings. Q-WAM uses fewer bits per weight on the two multi-expert models and the same BPW and reported memory on LingBot-VA, so its gains cannot be explained simply by a larger high-precision storage budget. Physical-robot results provide additional evidence of utility, with average improvements of 12.8 and 17.6 percentage points over SVDQuant. The actual 4-bit implementation also includes the transformation and protected-branch overheads in its block-level timings. Together, these results support practical value for the proposed method.
Critical weaknesses
-
The task-level contribution of AOG-based direction selection is not fully isolated. Table 3 adds the entire ASP component, including an additional 16-bit branch, while Table 5 retains ASP and adds SVDQuant on the weight side. Appendix A.5 compares AOG and random subspaces using local residual statistics and AOG-weighted damage, but does not report the corresponding closed-loop task success. Table 1 provides useful overall performance and storage comparisons; however, a comparison that holds preprocessing, protected experts, and low-rank budget fixed while changing only the protected subspace would more directly establish the value of the central direction-selection criterion. This limits the strength of the attribution, although the overall empirical gains remain supported.
-
The finite-probe subspace-estimation argument is incomplete for the sketch actually used. Appendix A.4 acknowledges that the cited dense Gaussian range-finder guarantee does not directly apply to its block-diagonal probe construction, but then relies on unbiasedness and the large total count NP to justify subspace recovery. These properties alone do not ensure accurate recovery: for example, if sensitivity were concentrated in one input and one token-step node, the estimate would have rank at most P regardless of how many zero-sensitivity inputs were added. Appendix C.3 provides useful stability evidence across calibration sets, but does not directly isolate error from the finite probe count. An applicable assumption or direct convergence evidence would strengthen confidence in the estimated subspace underlying ASP. This is a gap in the justification, rather than evidence that the reported estimates have failed in practice.
Questions for authors
-
Evidence for the central attribution: Do you have task-success results that replace the AOG subspace with a random or weight-SVD subspace while keeping smoothing/rotation, protected experts, rank, and precision budget fixed? If so, please clarify the exact matching conditions. This comparison would help determine how much of the task improvement comes specifically from AOG-based direction selection, beyond the benefit of a protected low-rank branch.
-
Clarification of estimator reliability: What assumptions make the subspace-recovery argument applicable to the block-diagonal sketch in Appendix A.4? Alternatively, with the calibration inputs fixed, can you provide evidence that the protected subspace and relevant action-error or task metrics stabilize as the probe count increases beyond P = 12? This would address uncertainty in the central sensitivity estimate without requiring a new application setting.
Follow up on our response
Thank you again for your careful review, in particular the close reading of App. A.4. We wanted to kindly follow up on our response:
We would welcome your thoughts on whether these address your two questions, and we are glad to clarify anything further.