- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
INFun-WM represents observations with fitted SIREN weights and predicts their changes after an action using a permutation-equivariant NFT. It plans with CEM and, for navigation, A* waypoints. Models with similar image prediction quality show different planning success. The authors attribute this gap to equivariance and propose an action-response diagnostic.
Critical strengths
- The gap between prediction and control is a useful observation. At C=2, INFun-WM and FLAT achieve similar rollout PSNR, 15.21 and 15.11 dB, but success rates of 65% and 10%. The analysis of movement direction helps explain why similar image scores can hide errors that matter for planning.
Critical weaknesses
-
The experiments do not isolate equivariance as the cause of better control. Architecture and state representation also change. The comparison should match capacity, training and neuron alignment. Table 4 tests canonicalization for static safe-action prediction, but not dynamics and planning.
The NOVA-style MLP has -107.7/-113.7 dB PSNR (Table 3), so it cannot support the matched-prediction claim. It uses this paper's per-trajectory INR fitting, whereas NOVA uses a shared encoder and base weights. Its failure therefore does not establish that original NOVA is unsuitable for control. Also, networks representing the same image need not differ only by neuron order. Equivariance ensures consistency under reordering, but even a zero-update operator is equivariant. It does not guarantee correct action effects. -
The contribution relies on the control experiments, whose interpretation remains uncertain. NFN/NFT already learn equivariant INR edits [1,2]; NFT Section 5.2 predicts residual SIREN edits using image losses. NOVA evolves INR weights using inferred latent actions [3], and prediction/control mismatch is established in model-based RL [4]. The distinct step here is to condition an equivariant weight operator on environment actions and test closed-loop planning.
The action-response score is high for LATENT (0.77/0.79) despite poor control, and Figure 4 excludes clean PointMaze from the correlation fit. Figure 10 describes different inputs for the DINO-WM comparison: clean egocentric observations for INFun-WM and native allocentric RGB for DINO-WM. Sharing A* does not remove this difference. Success also falls to 23% with four objects, with failures under texture and contact. These limits leave practical value uncertain, especially given the cost of fitting each observation.
References:
[1] Permutation Equivariant Neural Functionals. NeurIPS 2023. https://arxiv.org/abs/2302.14040
[2] Neural Functional Transformers. NeurIPS 2023. https://arxiv.org/abs/2305.13546
[3] Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement. 2026. https://arxiv.org/abs/2605.06298
[4] Objective Mismatch in Model-based Reinforcement Learning. L4DC 2020. https://arxiv.org/abs/2002.04523
Questions for authors
- With matched capacity and training, does the control advantage remain over alternatives using aligned neurons or shared initialization? Please test dynamics and planning, beyond the static readout in Table 4.
- Do the gains over DINO-WM remain with matched observations, actions, goals and planning budgets? Figure 10 indicates that the observations differ.
- Why does action-response fail for LATENT, and why is clean PointMaze excluded from the correlation fit? Does the denominator use true or predicted transitions? Does this diagnostic predict success on held-out environments?
Thank you for all the reviewers' time and feedback. We are withdrawing this submission.