- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies whether a latent world model should use a globally shared predictor or separate regional predictors for a given latent-space partition. The main experiments use spectral clustering of frozen representations and regional affine regression to estimate centered action responses. Worst-Case Partition Gain (WCPG) uses the minimum normalized squared 2-Wasserstein distance between regional response summaries and a frozen threshold to select a branch. A conditional theoretical connection to planning success is established under deviation budgets and a sufficient margin. Both branches are post-trained and evaluated across four tasks and two backbones. WCPG achieves 8/8 correct region-count-transfer selections and 10/12 correct backbone-transfer selections, yielding 90% overall and 93.75% balanced accuracy.
Critical strengths
-
A meaningful problem with an interpretable comparison. Sharing frozen representations and planning protocols reduces representation-related confounding and helps isolate the trade-off between parameter sharing and data splitting.
-
A simple criterion with promising cross-region-count results. WCPG can be computed without fully training both target branches. Its frozen threshold achieves 8/8 correct selections on a cross-K set containing four Regional and four Global winners, with supporting matched aggregation ablations.
Critical weaknesses
-
Regional modeling partitions samples through latent-state clustering and fits separate predictors. However, multimodality of the pooled data does not necessarily require regional models: a sufficiently expressive state-conditioned global model may capture the same local dynamics. The experiments do not sufficiently distinguish benefits of dynamical decomposition from capacity or optimization limitations of the chosen global predictor, and matching component architectures does not equalize total capacity. The evidence supports an empirical criterion for particular model families and partitions more directly than a broadly applicable selection principle.
-
Appendix A.1’s 21 alternatives are author-constructed statistical selectors. This is reasonable, but a cost-explicit comparison against direct validation-prediction-error-based selection is missing. Calibration uses only three retained configurations, and testing reuses the same four tasks. All 12 backbone-transfer cases favor Global, where Always Global achieves 100%, exceeding WCPG’s 83.33%; recognition of Regional winners under backbone transfer is therefore untested.
Questions for authors
-
Do Regional gains persist after controlling total capacity and training budget? Can existing evidence distinguish benefits of dynamical decomposition from expressiveness or optimization limitations of the global predictor, and delimit the threshold’s model-family dependence?
-
Is there a direct baseline using limited trial training followed by validation-prediction-error-based selection? What is WCPG’s accuracy–compute trade-off after accounting for partitioning, response estimation, and candidate-training costs?
-
How stable are the success gaps and selector ranking under the paired, nested evaluation? Do existing results support transfer to uncalibrated tasks or recognition of Regional winners under another backbone?
10 comments
Response to Reviewer 6PUZ (Q1b)
Q1b. Can existing evidence distinguish benefits of dynamical decomposition from expressiveness or optimization limitations of the global predictor?
A1b. We ran an additional random-partition control. Yes. The random-partition control distinguishes two gains in the original comparison: the additional gain from choosing a spectral split with the same experts, and the gain from using regional predictors even under a random split. TwoRoom showed both gains, Cube only the second, Reacher only the first, and PushT neither.
The two benefits are differences in mean success rates.
| Task | Benefit 1 | Benefit 2 | WCPG correct |
|---|---|---|---|
| TwoRoom | +2.05 pp | +1.20 pp | Yes |
| Cube | −1.11 pp | +2.67 pp | Yes |
| Reacher | +0.71 pp | −1.47 pp | Yes |
| PushT | −1.02 pp | −0.80 pp | Yes |
We evaluated all three branches on the same 250 paired instances per task at a 50-step horizon. Both Regional variants used three experts and the same training protocol. The first contrast isolates partition choice at fixed capacity. The second measures the gain over Global under a random split, without separately attributing that gain to Global’s expressiveness or optimization.
Response to Reviewer 6PUZ (Q1c)
Q1c. Can existing evidence delimit the threshold’s model-family dependence?
A1c. Theorem 3 delimits when a shared threshold applies.
Within the stated comparison class, the same theoretical threshold gives the correct selection whenever the following margin condition holds.
When all configurations satisfy these conditions, the same threshold can be reused across them. Changing the predictor family can change the cost of specialization and hence the required margin (Appendix G.3, Eq. 93 and G.6, Eq. 130). On Sub-JEPA, WCPG correctly selected Global in 10/12 configurations where Global won (Table D.1) and Regional in 2/2 configurations where Regional won (A3d), for a combined accuracy of 12/14 (85.71%).
Response to Reviewer 6PUZ (Q1a)
We were impressed by the expertise you brought to your review. We feel fortunate that our paper received such a careful and thorough reading. Thank you for the time and effort you devoted to the review and for your expert advice. To address your questions, we conducted a series of follow-up experiments. Their results have substantially strengthened our work. We will include all these follow-up experiments in the revised manuscript. Your questions cover the concerns raised in the weaknesses section of your review, so we address those concerns in our answers below.
A1a. To answer this question, we ran an additional experiment matching total trainable capacity and training budget. We find that regional gains persist after controlling total trainable capacity and training budget measured by sample exposure. On both tested LeWM tasks, spectral Regional retained a higher mean success rate than Global-wide: +2.71 pp on TwoRoom (61.38% vs. 58.67%) and +0.76 pp on Cube (49.69% vs. 48.93%). Global-wide matched the three experts’ combined trainable parameter count within 0.003%. It trained for 50 epochs on the full dataset. Each expert trained for 50 epochs on its own subset, giving both branches the same nominal sample exposure.