- Rating
- 4(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a novel model and a novel dataset for the task of visual aerial image-goal navigation. In their setting, a world-model is used to rank different candidate trajectories (i.e., future actions) given a history of observations and a goal image. The proposed algorithm consist mainly of a deterministic baseline module that predicts a single future image and a projection module (HEP) that estimates the error between the goal and predicted images at multiple scales in order to better compute a score for a candidate trajectory. These ideas are tested on a novel aerial benchmark, showing that their methods excel in navigation and are faster than similar world-based methods. Real world experiments are also provided to validate the practicality and transferability of the method.
The paper overall seems to be of high quality and I commend the authors for their work. I believe it could be of benefit to the community, so my recommendation leans towards acceptance. I do have certain questions and concerns that prevent me from assigning a higher score, as will be expanded later in the review.
Critical strengths
Perhaps the main strength of the submission is that the proposed method seems to be thoroughly validated and performs very well on the benchmarks. This includes the main aerial benchmark (both the novel dataset and how UA-NWM and other methods perform in it), the real world experiments and even 2D navigation tasks presented in the appendix. Though I raise certain perceived weaknesses in much more detail in my review, I still believe the authors provide reasonable and extensive evidence that the proposed ideas have merit and could be valuable to the community.
I also believe the resulting algorithm to be reasonably lightweight compared to similar work, such that it could be a good starting point for future work, particularly under a more limited computational budget and for embedded systems.
Critical weaknesses
In my perception, the paper doesn't analyze nor discuss of the deterministic baseline properly. Some experimental choices may also be inflating the reported performance in relation to previous work
The most impactful component (deterministic baseline) is underexplored
Most of the benefits of the proposed methods in relation to previous work, both in terms of computation time and navigation performance, seem to already be present in the deterministic baseline. The introduction states that the main issue of stochastic world models is that they are computationally expensive (the issue of sampling sensitivity is also raised and is reasonable, but is never quantified or explored further, so it seems to be of lesser importance). One would then expect to observe a tradeoff between performance and computational cost. This, however, seems incongruent with the reported experiments, where the deterministic baseline is already both less expensive and more performant than the other methods presented even without the proposed HEC. So either the introduction doesn't frame the problem correctly or there is a very impactful part of the model that is not present in previous work, yet is never identified.
In the lack of relevant discussion or ablation, it would seem that this key underappreciated component is the delta parametrization. This formulation seems to have come from Delta-World (Kerssies et al., 2026), as the authors of this submission properly cite, and by itself it reduced the FLOP count of other world models by 3 orders of magnitude. That seems to be a very important component that could explain a significant part of the reported performance, perhaps more so than the ideas introduced in UA-NWM. It would seem that not identifying this, or whatever other aspect of the model was most significant, obscures valuable insight and potentially fails to acknowledge the significance of previous work.
To be clear, I am not diminishing the value of the HEC module (which seems valuable by itself and is properly discussed) or other contributions related to the deterministic baseline (e.g., the other components and how to integrate them or how to apply the delta parametrization in this setting). My critique is that the paper focuses on the HEC module, while almost ignoring the baseline that seems essential to their results, even when it seems to contradict what is claimed in the introduction.
Potentially unfair comparisons with previous work
The authors use DINOv3 for their own method, but appear to pick the older and less capable DINOv2 as the backbone for RAE-NWM. There doesn't seem to be any justification for that choice and the natural expectation is that it would unfairly degrade the other method's performance. It could be argued that the authors of RAE-NWM originally used DINOv2, but it could also be counter-argued that the RAE-NWM paper is older and DINOv3 is still relatively new. One-step WM is a newer paper that used the stable diffusion VAE (i.e., it's not in the same family of models), so perhaps the same cannot be said in its case, but it would seem ideal to control for the effect of the encoder choice in the experiments to the extent possible. Otherwise, it's hard to separate the benefits of the paper's own contributions from those resulting from a better encoder choice.
For fairness, I'll acknowledge that adapting other works for a new dataset is an open ended task and many reasonable choices are possible. I'll also acknowledge that the experiments in table 12 do seem to use previous work in their original settings and UA-NWM still outperforms them. Still, that appears to be a weakness of the main experimental results that may also help explain the improved navigation performance of the deterministic baseline as pointed in the previous weakness
Questions for authors
Question (related to assessment):
- What dominates the computational cost of previous methods? Given that One-step WM used a single diffusion step and was relatively similar to UA-NWM in terms of time per frame, while the other ones took multiple steps and were significantly slower, I am led to believe that using a stochastic world model isn't as much of an issue as the submission seems to claim and ultimately the problem is the cost of multi-step diffusion
Questions and suggestions (not related to assessment):
- Unless I missed where that was written, I think it would facilitate reading if the other world models tested (NWM, RAE-NWM, etc) were explicitly classified as being stochastic or deterministic, given that is a central point in the text.
- I believe many readers expect a certain type of content when they see the words "uncertainty". For instance: covariances, ensemble, MC-dropout, aleatoric vs. epistemic uncertainty, calibration. This submission doesn't seem to meet this expectation that well as the connection to uncertainty is relatively lax. For comparison, consider how the works this paper cites (Seo et al., 2025; Mei et al., 2025) do met those expectations and are more rigorous about the topic. So I'd suggest the authors to consider ways to manage this expectation from potential readers earlier in the text. Adding other relevant works that use "uncertainty-aware" and OOD in a similar way would also be helpful
- Did you try running UA-NWM on the Orin NX rather than the laptop? I believe many practitioners are familiar with the capabilities of all kinds of Jetson GPUs, so understanding how they perform in this task (if they can do it all) seem useful for future work.
7 comments
Response to Reviewer f9Rc (2/5)
- Across many existing stochastic models and our deterministic baseline, there is also a trade-off between visual detail and inference cost. Here, visual detail refers only to image sharpness and fine-grained appearance, not to semantic, physical, or navigation accuracy. As shown in Fig. 5 and Appendix Figs. 21--23, stochastic models such as NWM and RAE-NWM produce images with finer visual detail than our deterministic baseline. This difference partly reflects the tendency of deterministic prediction to average multiple possible futures, and it is also strongly influenced by the iterative denoising used by many stochastic models to improve visual detail.
However, finer visual detail does not necessarily imply better navigation performance. Our new NWM diffusion-step comparison provides a direct control for this distinction because it changes the inference denoising budget while keeping the checkpoint, test cases, candidate sets, and task protocol unchanged. The official 250-step setting performs substantially more denoising and would generally be expected to produce finer visual detail than the 25-step setting. Nevertheless, 250 steps do not improve navigation performance, while 25 steps achieve equal or lower errors in every comparison. This result shows that visual detail and navigation performance are not equivalent. We added this diffusion-step analysis to Appendix A.9.2.
| NWM inference | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE | Planning ATE / RPE |
|---|---|---|---|---|
| 25 steps | 1.47 / 0.40 | 1.40 / 0.38 | 1.37 / 0.37 | 1.40 / 0.39 |
| 250 steps | 1.48 / 0.40 | 1.43 / 0.39 | 1.40 / 0.38 | 1.42 / 0.39 |
We do not claim a universal trade-off between inference cost and navigation performance for the stochastic and deterministic categories. The Introduction, Related Work, and Fig. 2 describe the respective strengths and limitations of both categories without assuming that either must navigate better. In our experiments, stochastic world models are often outperformed by the deterministic approach, indicating that sampling sensitivity can outweigh the benefit of finer visual detail for navigation performance.
Ablation and discussion for the deterministic baseline
The original submission did not sufficiently isolate and analyze the deterministic baseline. We have therefore moved the staged-training and delta-representation ablation from the appendix to Sec. 5.4 and expanded it to evaluate both the deterministic baseline and UA-NWM. The updated results are shown below.
| Method | Staged training | Delta representation | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE |
|---|---|---|---|---|---|
| Deterministic Baseline | 1.424 / 0.393 | 1.411 / 0.389 | 1.423 / 0.392 | ||
| Deterministic Baseline | 1.420 / 0.388 | 1.351 / 0.370 | 1.281 / 0.351 | ||
| Deterministic Baseline | 1.423 / 0.392 | 1.389 / 0.383 | 1.403 / 0.387 | ||
| Deterministic Baseline | 1.391 / 0.380 | 1.325 / 0.364 | 1.267 / 0.348 | ||
| UA-NWM | 1.383 / 0.380 | 1.321 / 0.363 | 1.297 / 0.357 | ||
| UA-NWM | 1.309 / 0.360 | 1.222 / 0.338 | 1.189 / 0.330 | ||
| UA-NWM | 1.370 / 0.375 | 1.309 / 0.359 | 1.263 / 0.347 | ||
| UA-NWM | 1.256 / 0.347 | 1.174 / 0.326 | 1.091 / 0.304 |
For both the deterministic baseline and UA-NWM, the delta representation provides the largest gain, followed by staged training. Predicting inter-frame changes reduces the visual redundancy shared by adjacent observations and directs model capacity toward dynamic variations. Staged pretraining provides a stable initialization for the compressor, fuser, and delta decoder before future prediction is learned.
Beyond the demonstrated contributions of staged training and delta representation, an additional plausible explanation for the strong baseline is deterministic prediction itself, which produces a repeatable, conservative future estimate without inference-time sampling variance. This property may contribute to the observed gap over stochastic world models when sampling sensitivity outweighs the benefit of generating sharper visual details.
Response to Reviewer f9Rc (3/5)
3. Encoder fairness (W2)
Thank you for highlighting the visual encoder as a potential source of the observed performance differences. We agree that the visual encoder is an important part of a world model because it determines the representation space in which future prediction is learned. In the original comparison, we followed the official configurations as closely as possible, including DINOv2 for RAE-NWM and the VAE for One-Step WM. To separate the effect of the encoder from that of the world-model design, we have now conducted controlled comparisons in which competing methods use the same visual encoder.
Shared DINOv3 encoder.
| Method | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE | Planning ATE / RPE |
|---|---|---|---|---|
| RAE-NWM (DINOv3) | 1.50 / 0.41 | 1.42 / 0.39 | 1.42 / 0.39 | 1.37 / 0.39 |
| One-Step WM (DINOv3) | 1.55 / 0.42 | 1.51 / 0.41 | 1.50 / 0.41 | 1.63 / 0.47 |
| InJepa (DINOv3) | 1.43 / 0.39 | 1.34 / 0.37 | 1.27 / 0.35 | 1.42 / 0.42 |
| Deterministic Baseline (Ours, DINOv3) | 1.39 / 0.38 | 1.33 / 0.36 | 1.27 / 0.35 | 1.26 / 0.35 |
| UA-NWM (Ours, DINOv3) | 1.26 / 0.35 | 1.17 / 0.33 | 1.09 / 0.30 | 1.22 / 0.33 |
Shared DINOv2 encoder.
| Method | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE | Planning ATE / RPE |
|---|---|---|---|---|
| RAE-NWM (DINOv2) | 1.54 / 0.42 | 1.54 / 0.42 | 1.50 / 0.41 | 1.46 / 0.43 |
| Deterministic Baseline (Ours, DINOv2) | 1.38 / 0.38 | 1.28 / 0.35 | 1.23 / 0.34 | 1.30 / 0.36 |
| UA-NWM (Ours, DINOv2) | 1.35 / 0.37 | 1.26 / 0.35 | 1.21 / 0.33 | 1.28 / 0.35 |
Shared V-JEPA 2.1 encoder.
| Method | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE | Planning ATE / RPE |
|---|---|---|---|---|
| InJepa (V-JEPA 2.1) | 1.48 / 0.40 | 1.41 / 0.39 | 1.33 / 0.37 | 1.54 / 0.45 |
| Deterministic Baseline (Ours, V-JEPA 2.1) | 1.34 / 0.37 | 1.26 / 0.35 | 1.19 / 0.33 | 1.29 / 0.36 |
| UA-NWM (Ours, V-JEPA 2.1) | 1.33 / 0.37 | 1.25 / 0.35 | 1.18 / 0.33 | 1.27 / 0.36 |
Shared VAE encoder.
| Method | Ranking-8 ATE / RPE | Ranking-16 ATE / RPE | Ranking-32 ATE / RPE | Planning ATE / RPE |
|---|---|---|---|---|
| NWM (VAE) | 1.47 / 0.40 | 1.40 / 0.38 | 1.37 / 0.37 | 1.40 / 0.39 |
| One-Step WM (VAE) | 1.52 / 0.41 | 1.48 / 0.40 | 1.44 / 0.39 | 1.53 / 0.44 |
| MWM (VAE) | 1.58 / 0.43 | 1.60 / 0.43 | 1.59 / 0.43 | 1.54 / 0.43 |
| InJepa (VAE) | 1.66 / 0.46 | 1.70 / 0.46 | 1.74 / 0.47 | 1.93 / 0.58 |
| Deterministic Baseline (Ours, VAE) | 1.58 / 0.43 | 1.59 / 0.43 | 1.62 / 0.44 | 1.62 / 0.47 |
| UA-NWM (Ours, VAE) | 1.60 / 0.44 | 1.61 / 0.44 | 1.65 / 0.45 | 1.77 / 0.52 |
These results support three conclusions.
-
First, the encoder does matter. For example, RAE-NWM improves when DINOv2 is replaced by DINOv3, and InJepa similarly improves when V-JEPA 2.1 is replaced by DINOv3.
-
Second, the advantage of UA-NWM is not explained by using DINOv3 alone. Under the controlled DINOv3 comparison, UA-NWM outperforms RAE-NWM, One-Step WM, and InJepa in all four tasks. It also remains the best method in the corresponding DINOv2 and V-JEPA 2.1 comparisons. Moreover, HEP consistently improves over its matched deterministic baseline with these three feature encoders, showing that its benefit transfers across multiple representation spaces, although the gain varies with the encoder.
-
Third, the VAE control exposes an important limitation rather than favoring our method. Our deterministic baseline performs poorly with this encoder, and adding HEP further degrades the results. InJepa also deteriorates in every task when its native V-JEPA 2.1 representation is replaced with a VAE, with a particularly large planning degradation. Conversely, replacing One-Step WM's native VAE representation with DINOv3 features also reduces its performance. Thus, the controlled experiments do not support the conclusion that one encoder is universally better or that our advantage over stochastic models comes merely from replacing a VAE with DINOv3. Instead, they indicate an interaction between the representation space and the prediction formulation. A VAE latent is optimized for probabilistic image reconstruction and is naturally paired with a generative objective that models its distribution. Directly regressing its next latent with a deterministic causal Transformer can yield an inaccurate central prediction. Because HEP learns local residual directions around that prediction, an unreliable center can in turn produce an overly permissive subspace that absorbs discrepancies rather than preserving useful trajectory discrimination.
Response to Reviewer f9Rc (1/5)
Thank you for the constructive and perceptive review. We greatly appreciate your positive assessment of the paper's overall quality, extensive validation, and practical efficiency, as well as the concrete suggestions for strengthening our analysis. We have added controlled experiments and clearer discussion, and respond to each point below.
For clarity, our response is organized as follows:
1. What actually dominates the computational cost? (W1&Q1)
Thank you for asking us to distinguish the computational cost of stochastic world models from that of multi-step diffusion. We agree that the two should not be treated as equivalent. The extra computational cost of existing stochastic world models mainly comes from two sources.
First, many stochastic world models use multi-step diffusion because they place considerable emphasis on the visual quality and details of generated observations. Iterative denoising is therefore a major source of computational cost for most existing stochastic world models. However, this is not an inherent requirement of every stochastic world model. One-Step WM, as you note, is an important exception that performs stochastic generation in a single step.
Second, repeated sampling can introduce extra cost. Stochastic world models can represent multiple plausible future states, but a single forward pass produces only one sample from that distribution. The resulting trajectory score can therefore be sensitive to which future happens to be sampled. The official NWM paper addresses this issue by running NWM three times for each action sequence and averaging the three LPIPS scores between the predicted final state and the goal. This existing strategy shows that repeated sampling is an established practical approach to stabilizing trajectory scoring. As stated in our Introduction: “Stochastic models can capture diverse plausible futures, but determining whether the goal belongs to this distribution requires sufficient samples to approximate it, incurring high computational cost.”
We further explore the issue of sampling sensitivity using One-Step WM. In the main experiment, each candidate trajectory receives one predicted future (N=1), which is compared with the goal image to score the trajectory. We additionally evaluate N=3. For every candidate, we perform three forward passes and score it using the sampled future most similar to the goal image.
Increasing the number of samples consistently improves ATE, while RPE remains tied at the reported precision. This experiment shows that additional sampling can partly reduce the sampling sensitivity of the same stochastic world model at the cost of additional computation.
We nevertheless agree that “high computational cost” is too absolute as a description of the entire category. Even with N=3, One-Step WM remains among the faster evaluated world models. We have therefore revised the manuscript to describe the general drawback as extra computational cost, which may arise from iterative generation, repeated sampling, or both. We have also added Appendix A.9.1, which formally defines the multi-sample scoring strategy, reports the complete One-Step WM N=1 versus N=3 results, and discusses the trade-off between reduced sampling sensitivity and additional world-model evaluations.
2. What trade-offs and components explain the strong deterministic baseline? (W1&Q1)
Thank you for asking us to examine both the expected trade-offs and the components underlying the strong deterministic baseline.
Expected trade-offs
You note that the efficiency of our deterministic baseline would normally be expected to come with a trade-off. Our results reveal two relevant trade-offs, which should be distinguished from a universal trade-off between inference cost and navigation performance.