- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3(+1)
Read review
Paper summary
This paper investigates what information should be preserved during the quantization of latent world models, comparing planning-cost reconstruction, terminal relative-representation reconstruction, and module-level output reconstruction for the encoder and predictor. The authors analyze how local quantization errors propagate to terminal representations and impact candidate action rankings, providing motivation for the Module-MSE calibration objective. Experiments across three latent world models on four control tasks demonstrate that, under symmetric per-channel W4 weight quantization, Module-MSE achieves an average success rate of 79.33%, closely matching the full-precision baseline of 79.83%, while exhibiting favorable performance in planning-decision fidelity and calibration sensitivity evaluations.
Critical strengths
-
Beyond standard task success rates, the paper evaluates candidate inversion rate, elite set overlap, and selection regret. These metrics provide deeper insight by revealing that even when overall reconstruction error is modest, relative errors among candidates can alter CEM action selection. The authors also distinguish between preserving full-precision model decisions and improving empirical task success rates.
-
Evaluating across three world models and four control tasks ensures the findings are not confined to a single architecture. Comparing four learnable-rounding objectives under identical quantization parameterizations and optimization steps allows for a controlled study of the calibration objectives. Supplementary analyses on learning rate sensitivity, calibration set size, and adjacent-path supervision provide practical empirical support for module-level reconstruction.
Critical weaknesses
-
Module-MSE applies reconstruction loss to encoder and predictor outputs within an existing learned rounding framework. While the paper discusses prior layer-wise and block-wise reconstruction approaches, it does not sufficiently isolate and demonstrate what concrete benefits arise specifically from coarsening the reconstruction granularity to the entire encoder or predictor.
The analysis motivates module-level reconstruction, but does not by itself establish a comparative advantage over alternative calibration objectives. The error bound depends on propagation gains and may be loose, as acknowledged in Appendix A.2. The counterexamples illustrate that matching a scalar terminal cost need not preserve the terminal relative representation, and that matching the terminal relative representation need not preserve intermediate states. However, they do not establish that these ambiguities necessarily cause substantial performance deficits under sufficiently diverse calibration goals and trajectories. Consequently, the paper currently reads more like a useful empirical benchmarking study of calibration targets, and its methodological novelty as well as theoretical explanatory power require clearer delineation.
-
Tables 2–3 do not report confidence intervals, error bars, or variance across independent calibration seeds, making it difficult to assess whether the marginal performance advantage of Module-MSE is statistically significant. Near-full-precision average performance does not imply uniform preservation across settings. For example, PLDM’s success rate on PushT decreases from 48.0% to 39.0%, although Module-MSE remains tied with GPTQ as the best quantized method in this setting.
Additionally, the experiments rely largely on a fixed W4 configuration and fixed prediction horizons. Because multi-step error propagation serves as a central motivation for the proposed approach, the lack of evaluations across varying prediction/planning horizons leaves the applicable scope of module-level reconstruction unclear.
Questions for authors
-
What is the statistical uncertainty surrounding the reported gains of Module-MSE over Module-L1 and GPTQ? How many independent calibration seeds were executed per configuration? Could you provide paired confidence intervals on success rate differences using aligned test episodes across methods?
-
Operationally, what are the exact distinctions between Module-MSE and standard reconstruction calibration in the utilized AutoRound implementation? Under a comparable calibration budget, could you provide an ablation directly comparing layer-wise, block-wise, and whole encoder/predictor-level reconstruction to isolate the impact of module-level granularity itself?
-
Does the relative advantage of Module-MSE vary as a function of the planning/prediction horizon? Can empirically measured module errors account for terminal representation errors or ranking flip rates under different calibration targets? Demonstrating this link would substantially strengthen the connection between the theoretical analysis and empirical claims.
9 comments
Rebuttal to Reviewer EJu2 Part 2
Part 2
Weakness 1 (continued)
Experiment 1. Does reducing module error improve terminal representations and candidate rankings? The bound relates the terminal relative-representation error to the second moments of module residuals. We compare the errors of quantized models and then hold the dynamics fixed to test the roles of residual magnitude and second moment.
(a) Quantized models. We compare six DINO-WM quantization methods using the same start states, candidates, and prediction horizon.
Table 1. DINO-WM: one-step prediction error, terminal representation error, and candidate inversion rate.
| Method | One-step MSE with matched inputs ↓ | Step-5 free-rollout MSE ↓ | Terminal relative-representation MSE ↓ | Candidate inversion rate ↓ |
|---|---|---|---|---|
| RTN | 0.02155 | 0.4753 | 4.126 | 45.53% |
| GPTQ | 0.003615 | 0.1048 | 0.3127 | 19.39% |
| Module-MSE | 0.00225565 | 0.0305719 | 0.114752 | 10.66% |
| Module-L1 | 0.0027545 | 0.0403121 | 0.1484 | 11.62% |
| Relative-MSE | 0.05295 | 0.1451 | 0.1986 | 13.33% |
| Cost-MSE | 0.06565 | 0.6953 | 0.9238 | 32.55% |
We use 64 shared start states, 64 common candidates per state, and five prediction steps. One-step MSE with matched inputs compares the FP and quantized predictor outputs on the fifth call, given the same FP history and action. Step-5 free-rollout MSE compares the two models’ latents after their own five-step rollouts. Terminal relative-representation MSE compares the vectors obtained by subtracting each model’s goal latent from its terminal latent. All MSEs are averaged over output components.
Module-MSE has the lowest one-step MSE with matched inputs, step-5 free-rollout MSE, terminal relative-representation MSE, and candidate inversion rate.
(b) Controlled replay of one-step prediction residuals. We hold the FP predictor, initial representation, goal, and candidate actions fixed and change only the prediction residuals injected at each step. On DINO-WM, halving the one-step residuals from Module-MSE reduces terminal prediction MSE by 68.39% and the inversion rate from 9.25% to 5.17%. We also match the residuals from Module-MSE and Module-L1 to the same mean absolute error (MAE) to compare their second moments and how their errors propagate. Table 2 also reports native LeWM W3 rollouts for comparison.
Table 2. Error by prediction step: native rollout and matched-MAE replay with fixed dynamics.
| Prediction step | LeWM W3 native rollout: MSE / L1 | DINO-WM W4 matched MAE: MSE / L1 |
|---|---|---|
| 1 | 0.0177986 / 0.0188794 | 0.00274727 / 0.00282599 |
| 3 | 0.0358500 / 0.0378888 | 0.0120057 / 0.0132801 |
| 5 | 0.0644336 / 0.0682705 | 0.0249888 / 0.0270521 |
Each entry is the prediction-latent MSE relative to FP, normalized by output dimension. MSE/L1 identifies the calibration objective or residual source. LeWM uses native rollouts; DINO-WM uses matched-MAE replay. Both use 64 shared candidates.
On LeWM W3, Module-MSE has 6.73% lower mean injected MSE than Module-L1 and lower accumulated error over successive prediction steps. On DINO-WM at matched MAE, the Module-MSE residuals have a 2.72% lower second moment and yield 7.63% lower terminal MSE (95% CI: [1.13%, 13.25%]). The quantized-model comparison and the fixed-predictor replay together support the link between lower second-moment error, better multi-step representations, and better ranking fidelity.
Rebuttal to Reviewer EJu2 Part 3
Part 3
Weakness 1 (continued)
Experiment 2. Can score perturbations and candidate margins explain RTN sensitivity and recovery after calibration? For each model, we use 64 start states and 300 shared candidates per state. We compare the score perturbations and decisions of RTN and Module-MSE at the same FP margins.
Table 3. RTN sensitivity and recovery after Module-MSE calibration.
| Model | Method | Top-two margin / IQR | Score perturbation RMS / IQR ↓ | Inversion rate ↓ | Closed-loop success ↑ |
|---|---|---|---|---|---|
| LeWM | RTN | 0.554931 | 0.185505 | 5.94% | 79.50% |
| LeWM | Module-MSE | 0.554931 | 0.111623 | 2.82% | 84.50% |
| DINO-WM | RTN | 0.276811 | 0.875031 | 44.95% | 7.00% |
| DINO-WM | Module-MSE | 0.276811 | 0.306242 | 11.20% | 76.00% |
RMS is the root mean square of the score perturbation after subtracting its common offset, and IQR is the interquartile range of the FP costs. We normalize the margins and RMS by the IQR before averaging across start states. The horizon is five prediction steps and the elite set has 30 candidates. Closed-loop success rates use the same checkpoints on 200 aligned episodes.
DINO-WM is more sensitive to RTN because its score perturbations are larger relative to its candidate margins. Its normalized perturbation is about 4.7 times LeWM’s, while its top-two margin is about half as large, making rankings easier to reverse. The similar elite-boundary margins (0.01770 for DINO-WM and 0.02004 for LeWM) further highlight the difference in perturbation magnitude. Module-MSE reduces DINO-WM’s normalized score perturbation by 65.0% and its inversion rate from 44.95% to 11.20%. Closed-loop success rises from 7.0% to 76.0%, close to FP’s 76.5%. Both RTN sensitivity and recovery after calibration can thus be understood in terms of the size of the score perturbations relative to the candidate margins.
Calibration data and robustness. More data or a wider variety of goals may improve Cost-MSE, but it was less robust than Module-MSE in Section 5.3: its success-rate range was 17.5–28.5 percentage points, compared with 1.0–7.5 for Module-MSE. With just 13 trajectories, Module-MSE reaches 64.33% mean success across three models, compared with 34.67% for Cost-MSE using 128 trajectories. These results highlight the practical value of deriving the calibration objective from representation reuse and error propagation: Module-MSE combines sample efficiency and calibration robustness with planning fidelity.
Controlled granularity ablation. Layer-MSE, Block-MSE, and Module-MSE share the quantization parameterization, optimizer, calibration data, and FP input source. All use 384 updates per parameter and a learning rate of 1/768. Only the reconstruction target changes: an individual linear layer, a full Transformer residual block, or the output of the entire encoder or a full predictor call.
Table 4. Reconstruction granularity ablation. Each cell reports terminal relative-representation MSE ↓ / inversion rate ↓ / success rate ↑.
| Reconstruction granularity | LeWM–PushT | DINO-WM–PushT |
|---|---|---|
| Layer-MSE | 0.02791 / 4.56% / 80.0% | 1.525 / 25.83% / 41.0% |
| Block-MSE | 0.02173 / 4.18% / 82.5% | 0.2600 / 12.75% / 74.0% |
| Module-MSE | 0.01999 / 3.95% / 83.0% | 0.1439 / 10.46% / 75.0% |
All variants use the same test episodes. Supervising full module outputs reduces terminal representation errors and inversions and increases success on both models. With matched inputs, the DINO-WM predictor’s reconstruction MSE also decreases from 0.007314 for layer-level supervision and 0.004198 for block-level supervision to 0.002924 for module-level supervision. The benefit is thus visible directly at the predictor output.
Rebuttal to Reviewer EJu2 Part 1
Part 1
Paper: What Must Quantization Preserve in Latent World Models?
Dear Reviewer EJu2, thank you for your careful review and for raising questions about reconstruction granularity, statistical uncertainty, and performance across prediction horizons. Below, we respond to each weakness and question in turn.
Weakness 1
Reviewer comment
Response
Thank you for examining the reconstruction granularity, the explanatory power of the analysis, and the role of multi-goal supervision.
Our contribution starts from the computational structure of world models and connects the choice of calibration target to multi-step error propagation and planning decisions. It consists of two related analyses.
First, representation reuse determines what quantization should preserve. The encoder and predictor outputs are reused in subsequent prediction steps and goal comparisons. We therefore propose preserving the full representations at these interfaces. We decompose multi-step error into start and goal encoding errors, newly introduced prediction error at each step, and propagation of earlier errors. When local propagation gains are bounded, the second moments of the module reconstruction errors control an upper bound on the terminal relative-representation error. This motivates Module-MSE. The contribution is the choice of what to calibrate and the analysis of its downstream effects, not a new calibration algorithm.
Second, the interaction between score perturbations and candidate margins explains changes in planning. A score error of the same magnitude can have different effects depending on the candidate margin. We characterize when the difference in score perturbations between two candidates exceeds their FP margin, reverses their ranking, and changes the CEM update through elite selection. This connects representation error to planning decisions and provides a common explanation for differences in RTN sensitivity and recovery after calibration.
The following experiments test these two analyses by measuring module error, its accumulation over prediction steps, and candidate decisions, rather than relying only on final task success.