- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces variable-length latent world model which improves long-horizon planning by directly predicting future latent states conditioned on action sequences of varying lengths, rather than relying exclusively on recursively applied one-step predictions.
It uses a shared action-token interface to support multiple prediction horizons with one predictor, together with a progressive horizon curriculum that introduces longer prediction targets while retaining shorter-horizon supervision.
The main contributions are:
- a variable-length latent prediction objective and action-token architecture that support multi-horizon endpoint prediction;
- a cumulative horizon curriculum to stabilize training across prediction horizons
- five planning strategies that exploit variable-length predictions, including predefined chunk schedules, cost-adaptive chunking, and joint optimization of actions and chunk boundaries.
It evaluate VLWM on LeWorldModel (LeWM) and DINO-WM across PushT, OGBench-Cube, and TwoRoom. It report average planning-success improvements of 8.1 percentage points with the predefined long-to-short planner and 8.7 points with joint action–chunk optimization, increasing to 11.8 and 12.8 points.
Critical strengths
1.an approach to reducing long-horizon prediction error in latent world models. The paper addresses an important limitation of one-step latent prediction: recursively rolling out predictions can accumulate errors and degrade long-horizon planning. It directly predicts future latent endpoints conditioned on variable-length action sequences, using a shared action-token interface and a progressive horizon curriculum.
2.Consistent empirical gains across multiple representations and planning strategies. The authors evaluate with both jointly learned visual representations (LeWM) and frozen pretrained DINO features (DINO-WM), across three simulated control environments.
Critical weaknesses
The contribution of variable-length prediction is not fully disentangled from the effects of planning strategy and curriculum. The reported improvements combine several factors: multi-horizon latent prediction, progressive horizon curriculum, and planning strategies that vary chunk lengths or jointly optimize chunk boundaries with actions. In particular, P3 and P5 introduce different planning mechanisms that may independently contribute to the observed gains. A more systematic isolation of these components, including comparisons against equally tuned one-step baselines and alternative multi-step prediction objectives, would help establish whether the core VLWM representation and training approach are responsible for the improvements. Without clearer attribution, it is difficult to assess the method's fundamental advantage over existing planning and prediction alternatives.
Questions for authors
- How much of the reported improvement comes from variable-length latent prediction itself, rather than the planning strategy and horizon curriculum?
2.How robust are the results to the choice of maximum prediction horizon and the distribution of chunk lengths?
4 comments
Response to Reviewer PPzr (2/2)
Q2. Robustness to prediction horizon and chunk-length distribution
How robust are the results to the maximum prediction horizon and the distribution of chunk lengths?
We interpret “maximum prediction horizon” as referring to the horizon used in training and planning, and “the distribution of chunk lengths” as referring to the inference-time chunk-selection rule. We therefore added two complementary experiments on PushT with LeWM at . Entries below are success rates (%, mean ± standard deviation over three training seeds).
Training and planning horizons. We trained VLWM with and evaluated P1–P5 with planning horizon , alongside the original setting. LeWM remains a one-step predictor and is evaluated at the corresponding planning horizon.
| Method | ||
|---|---|---|
| LeWM | 9.3 ± 2.3 | 2.7 ± 1.2 |
| LeWM+VLWM (P1) | 14.0 ± 2.0 | 24.7 ± 3.1 |
| LeWM+VLWM (P2) | 12.0 ± 2.0 | 24.7 ± 1.2 |
| LeWM+VLWM (P3) | 14.7 ± 3.1 | 30.0 ± 2.0 |
| LeWM+VLWM (P4) | 15.3 ± 3.1 | 30.7 ± 3.1 |
| LeWM+VLWM (P5) | 16.0 ± 2.0 | 32.7 ± 1.2 |
All five VLWM planners improve when the training and planning horizons are extended together. At ten model steps (50 environment steps), P3 and P5 reach 30.0% and 32.7%, respectively, compared with 2.7% for recursive LeWM. The benefit thus extends to a larger trained horizon range.
Inference-time chunk selection. Using the original checkpoints and fixing , we separately varied P3’s maximum allowed chunk length and its long-to-short bias strength . All other inference settings were held fixed within each sweep.
| Maximum chunk length () | 3 | 4 | 5 |
|---|---|---|---|
| P3 success (%) | 15.3 ± 3.1 | 16.0 ± 2.0 | 14.7 ± 3.1 |
| Bias strength (maximum chunk = 5) | 2 | 3 | 4 |
|---|---|---|---|
| P3 success (%) | 12.7 ± 1.2 | 14.0 ± 2.0 | 14.7 ± 3.1 |
At , P3 reduces to uniform sampling over feasible chunk lengths. Thus, stays closer to uniform sampling and imposes a weaker long-to-short preference than or , consistent with its slightly lower success.
The maximum chunk length sweep spans 14.7–16.0%, and the bias sweep 12.7–14.7%. Every setting exceeds LeWM’s 9.3% at . These results show that the planning benefit persists across the tested maximum chunk lengths and distribution strengths. We include the horizon and chunk-distribution results in Appendix K (Tables 15–16) and clarify the default planning horizon in Section 4.1 of the revised manuscript.
Thank you again for your detailed and constructive comments. We hope our responses address your concerns and welcome any further questions.
We understand that this is a particularly busy period, and we sincerely appreciate your time and consideration.
We have provided detailed responses to all of your questions and concerns. When you have a chance, we would be very grateful if you could take a look at our responses. We hope they help clarify our work, and we would welcome any further feedback.
Thank you again, and we wish you a pleasant day!
Dear Reviewer,
With approximately 6 hours remaining before the rebuttal deadline, we would be grateful if you could take a look at our updated responses. We have provided point-by-point responses to every concern raised in your review.
We understand that this is a busy period and sincerely appreciate your time. If your schedule permits, we would greatly appreciate hearing your feedback.
Thank you again for your careful consideration. Wishing you a pleasant day!
Response to Reviewer PPzr (1/2)
We thank Reviewer PPzr for recognizing the empirical gains across different visual representations. We appreciate your comments on attribution and robustness and address them below.
Q1. Isolating variable-length prediction, curriculum, and planning
Following your suggestions, we added action-token one-step, fixed-five-step direct, and five-step recursive training controls, alongside VLWM with and without curriculum. The non-curriculum action-token variants share the architecture, training data, update count, batch size, and global learning-rate schedule. Fixed-5 recursive is retrained with full backpropagation through five predictions and fifth-step endpoint supervision, without teacher forcing; Fixed-5 direct and VLWM-P1 both use one direct five-step prediction at evaluation.
Results below use LeWM on all three environments at Δ=100, with a planning horizon of five model steps, an execution budget of 200 raw steps, and 30 CEM iterations. Success rates are percentages (mean ± standard deviation over three training seeds).
The comparisons separate three effects:
The complete VLWM-P3 configuration exceeds Fixed-5 direct by 5.8 percentage points on average. These results identify how the predictive interface, training schedule, and chunk selection work together. We include these comparisons in Section 4.3 (Tables 1–3) and Appendix H of the revised manuscript.