- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
AIM is a framework for world-model-based planning, providing the goal-conditioned initial point for efficient searching, rather than goal-agnostic start. It trains an intent predictor on frozen world model features, which predicts compact action blocks connecting the current and goal images. To summarize action blocks to intent, AIM uses discrete cosine transform (DCT), and also reweighting layers to focus on important components of features for planning. AIM shows improvement compared to default CEM, across three types of world models, various budget ranges, and two planners.
Critical strengths
None
Critical weaknesses
-
I am not convinced why DCT and reweighting layers should be used. DCT and reweighting do not show any clear gain in terms of the planning success rates, compared to Direct-H5 in Table 7 and compared to no reweighting in Table 8, respectively. I also think that there might be no cost advantage of DCT for planning. Also, without DCT and reweighting layers in the proposed method, it seems that it lacks novelty, since there are several similar approaches providing better initial points for planning (e.g., INTACT [1], PRISM [2]).
-
The proposed experiments are limited to somewhat simple environments and tasks. I am not sure that the proposed intent prediction module will also work on complex, long-horizon, and real-world scenarios.
[1] Sun et al., INTACT: Isomorphic intent-to-action learning for search-free world models.
[2] Wang et al., PRISM: PRior-guided imagination sampling in world Models.
Questions for authors
-
Can the authors clearly show why DCT and reweighting layers should be used? What advantages does it bring to world-model-based planning?
-
Can the authors clarify the novelty and practical gain of the proposed methods compared to similar approaches providing better initial points (e.g., INTACT [1], PRISM [2]) or policy-guided planning?
-
Can the authors show some evidence that the proposed method will also work in more complex, long-horizon, or real-world scenarios?
-
Also, considering 300 trajectories with planning only improves 3.67pp compared to prior-only, I think additional computational cost for planning is diffcult to justify. Can the authors show more convincing scenarios where prior-only is not sufficient?
4 comments
Novelty, longer horizons, and the role of planning (2/2)
W1 & Q2: Novelty and practical benefit over INTACT, PRISM, and policy-guided planning.
A2: AIM is not a variant of these methods.
- INTACT [1] trains the world model jointly with the prior, so the model itself must be trained for it. AIM attaches to hosts that are already trained and frozen: three in the paper.
- PRISM [2] also uses frozen features but fuses a predicted mean and variance into the planner's sampling distribution (MPPI in the original; our Gaussian-PoG control applies the same fusion to CEM). AIM writes only the mean.
- The plain form of policy-guided planning, a network that predicts the action block and seeds the planner, is our Direct-H5 control.
- Beyond the interface, AIM contributes the exact decomposition of W&A1, which states before any planning run what a prior should predict.
All three heads were newly trained on the same host with the same training pairs and update count, and evaluated on the same start/goal pairs:
| Success (%) | No search | CEM@300, offset 25 | CEM@300, offset 50 | Parameters |
|---|---|---|---|---|
| Direct-H5 | 86.73 ± 0.83 | 93.67 ± 0.81 | 64.60 ± 0.20 | 0.26–0.28M |
| Gaussian prior, PoG | 81.93 ± 0.64 | 94.87 ± 0.12 | 63.93 ± 1.22 | 0.51–0.59M |
| AIM (Ours) | 89.20 ± 0.60 | 92.87 ± 0.64 | 65.47 ± 1.22 | 0.25–0.26M |
All columns average the five tasks. Offset 25 is the standard setting; offset 50 doubles the largest training offset (W&A3). AIM is thus stronger without search and at twice the goal offset, and within 2 points of a prior twice its size after search on the standard tasks, through an interface that touches only the mean and with no host retraining.
W2 & Q3: More complex, long-horizon, or real-world scenarios.
A3: Thank you for raising this concern. We answer it on two levels.
Scope already in the paper. The evaluation covers three frozen hosts (ours, SMWM, and a DINO-WM-style host on DINOv2 features), five tasks that include single- and two-object manipulation (Cube, Cube-Double), two planners (CEM and MPPI), and a thirtyfold range of search budgets. With one CEM iteration AIM raises mean success in 14 of the 15 task–host cells and ties the remaining one (Table 1).
New experiment on longer horizons. The heads are trained only on goals up to 25 environment steps away. With the heads frozen and evaluated on goals twice as distant (offset 50, 100 interaction steps, four planning calls) on all five tasks, without intermediate goals, AIM with search reaches 65.47%, above Direct-H5 (64.60%) and, in every seed, the Gaussian prior (63.93%). It is the best method on Cube (60.67% vs 57.67% for both others) and exceeds the Gaussian prior on Cube-Double (47.33% vs 43.00%). The advantage therefore carries over to goals beyond the training range.
Real-world scenarios. Our evaluation follows the benchmark protocol of the world-model baselines we build on and compare with (LeWM, SMWM and DINO-WM), all of which are evaluated in simulation, so that our results are directly comparable with theirs. Accordingly, this submission does not include real-robot experiments either. The rebuttal period is too short for real-robot experiments, so we will add these results in future work.
Q4: Scenarios where the prior alone is insufficient and planning is necessary.
A4: The prior fixes where sampling starts; only search can correct the cases where that start is wrong. The 3.67-point average understates this role, because the prior alone already succeeds on about 89% of episodes:
- Standard tasks: search removes one third of the remaining failures (10.80% → 7.13%). Failures fall from 28.00% to 16.67% on PushT and from 6.67% to 1.67% on TwoRoom, and PushT success keeps rising with budget: 72.00 → 83.33 → 93.67% at 0/300/9,000 candidates.
- Distant goals: at offset 50, search lifts AIM from 56.60% to 65.47% on the five-task average (+8.87 ± 0.61) and from 16.00% to 34.33% on PushT. On the four tasks other than Reacher it rescues 153 prior failures and breaks 14; on Reacher, discussed in W&A1, the prior alone already reaches 95.00% at this offset, above every search condition.
- Against search alone: one AIM iteration (300 candidates) beats thirty default iterations (9,000) on all three hosts, 92.93% vs 75.07% on ours, in 5–12× less evaluation time.
These discussions and experiments will be integrated into the revised version.
[1] INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models
[2] PRISM: PRior-Guided Imagination Sampling in World Models
While I appreciate the authors' efforts in this rebuttal, it is still very hard for me to find practical benefit to DCT for planning. Also, without the search, this method is closer to goal-conditioned policy learning than to planning. In this context, predicting low-frequency DCT coefficients for action chunks is similar to ideas already used in FAST [1] and there is no comparison to a policy learning baseline.
[1] Pertsch et al., FAST: Efficient Action Tokenization for Vision-Language-Action Models
We thank you for the follow-up and for engaging with our rebuttal. Your three points are connected, and one controlled comparison below speaks to all of them: AIM with search against a goal-conditioned policy trained on the same frozen features and the same data.
W1: Practical benefit of DCT for planning.
A1: All conditions below use the same frozen host, the same training pairs and the same number of updates. The first column is Direct-H5 executed without search, i.e., goal-conditioned behavior cloning with action chunking.
| Success (%) | GC policy (Direct-H5) | AIM prior alone | AIM + CEM@300 (Ours) |
|---|---|---|---|
| Standard tasks, five-task mean | 86.73 ± 0.83 | 89.20 ± 0.60 | 92.87 ± 0.64 |
| Twice the training goal offset, five-task mean | 53.40 ± 0.87 | 56.60 ± 1.06 | 65.47 ± 1.22 |
| Cube, p = 0 | 95.33 ± 1.53 | 95.67 ± 2.08 | 99.00 ± 1.00 |
| Cube, p = 0.25 | 81.00 ± 1.73 | 86.00 ± 0.00 | 87.33 ± 0.58 |
| Cube, p = 0.5 | 51.67 ± 1.53 | 57.00 ± 3.00 | 68.67 ± 0.58 |
| Cube, p = 0.75 | 44.00 ± 2.65 | 48.67 ± 2.08 | 54.00 ± 1.73 |
| Cube, p = 1 | 45.33 ± 4.04 | 45.67 ± 2.08 | 52.67 ± 2.08 |
Mean ± SD over three training seeds. The Cube rows are a new experiment: the heads are trained on 2,000 trajectories in which each step is a uniform random action with probability p, with the host, the update count and the evaluation fixed. All Cube rows use one frozen host and the standard Cube start/goal pairs, so their SD reflects head training only.
The practical benefit of DCT (first vs. second column) is a stronger starting point for the same search, at the same latency and with a more compact output. It shows wherever the planner's start is hard to learn from the data:
- Non-expert data. Offline data for world models are often collected by exploratory or noisy policies rather than experts. When the data mix purposeful and random actions (p = 0.25–0.75), the DCT prior is 4.67–5.33 points above Direct-H5; with half or more random steps (p = 0.5 and 0.75), the advantage remains after the same search (+7.67 and +5.00 points).
- Goals beyond the training range: 56.60% vs 53.40% at twice the training goal offset.
- Hard-to-predict actions: on Reacher, 90.00% vs 74.33% without search.
On the standard expert datasets, 300 candidates largely erase the difference between two good starts, so the benefit is clearest where the search still depends on where it starts. In addition, the number of coefficients is chosen from offline data before running the planner.
W2: Without search, the method is closer to goal-conditioned policy learning; no policy-learning baseline.
A2: The policy-learning baseline is the first column of the table in W&A1, and planning with AIM (last column) exceeds it in every row:
- Planning adds what the policy cannot: AIM with search is 6.13 ± 0.99 points above the policy on the standard tasks and 12.07 ± 1.92 points on distant goals.
- The gap is largest where imitation is weakest: on distant goals (+12.07) and on Cube data with half the steps random (+17.00). There search on the world model corrects starts that imitation alone cannot get right.
- Each column adds one component, and each raises success in every row: the DCT target improves the start, and search on the world model improves on it.
We agree that the prior executed alone is a goal-conditioned policy; we report it as a probe of the start the planner receives, as asked in Q4 of the original review. AIM itself is a planning method: in every main result the executed actions are selected by CEM rollouts of the frozen world model, and the head writes only the planner's initial mean.
W3: Similarity to FAST [1].
A3: Thank you for the pointer. Our paper already cites FAST for the energy compaction of the DCT (Section 1), and we will expand the comparison in Related Work. The transform is shared; its role and what is kept differ:
- Role. FAST tokenizes an action chunk so that an autoregressive VLA can predict it and then execute it. In AIM the coefficients are not executed: they set where CEM starts, and the search over the full action sequence on the world model refines them.
- What is kept. Because FAST's decoded chunk is executed, FAST keeps all coefficients up to quantization. AIM truncates to the leading K and ranks the choice of K with the exact decomposition of Section 4.3: a coefficient that the frozen latent predicts no better than zero cannot reduce the initialization error. FAST's rounding also zeroes small coefficients, but it selects them by magnitude, to preserve the reconstruction of the executed chunk; AIM selects them by how well the frozen latent predicts them (), which is what matters for a search prior.
AIM's contribution is therefore not the transform itself but a truncated intent target for the initial mean of a planner on a frozen world model, together with an offline analysis of how many coefficients are worth predicting.
[1] Pertsch et al., FAST: Efficient Action Tokenization for Vision-Language-Action Models
Why DCT and the reweighting layer are needed (1/2)
We thank you for the detailed comments and for pointing us to closely related work. We ran new controlled experiments for each concern; numbers are mean ± SD over three training seeds, 100 episodes per task and seed.
A1: We appreciate this comment, and we would like to clarify why DCT is needed: it is the choice an exact analysis prescribes, and its benefit is measurable.
Theory (Section 4.3). The DCT is orthonormal, so the initialization error splits exactly into the prediction error of the kept coefficients and the energy of the dropped ones: E(K+1)=E(K)−RK2eK, where eK is the share of the action energy in coefficient K and RK2 its validation R2 from the frozen latent. A coefficient is thus worth its share of the action energy times its predictability; one the latent predicts no better than zero only adds error. Direct-H5 predicts all five coefficients, including those. DCT with K=2 retains the first two low-frequency coefficients. Our analysis and empirical results support this compact representation as a robust default across the evaluated tasks.
The decomposition needs only offline data, and it predicts where the second coefficient pays off:
On TwoRoom and Reacher the first temporal mode still holds about one fifth of the action energy, but the frozen latent predicts it at a validation R2 of only 0.008 and 0.003, against 0.45–0.68 on the other three tasks, so predicting it brings almost nothing. Every further increment of K is ranked below the three large ones and changes success by at most 3 points. A target with more coefficients therefore adds outputs without improving control.
Why Table 7 does not show it. Table 7 compares the two targets after search, where an initial mean matters only while the search still depends on its starting point (Section 4.3); 300 candidates largely erase the difference between two good priors. Where search contributes less, DCT is clearly stronger:
The reweighting layer is an auxiliary design. Learned and uniform weighting both reach 92.93%, so we will present it as optional; no conclusion depends on it.