- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Online Meta Flow Matching (OMFM) for control under unknown and varying dynamics. Environments are presented sequentially, and each environment is characterized by unobserved dynamics parameters. The proposed methodology uses a Transition-Aware Context Encoder (TACE) to map the observed trajectories from an environment into a latent context vector. This context vector conditions both 1) a flow-matching model that generates complete candidate control sequences and 2) a learned neural surrogate of the dynamics.
The control actions generator is trained on a Gibbs-weighted empirical distribution of observed trajectories, in order to assign a larger training weight to lower-cost control sequences. An autoregressive neural surrogate of the dynamics is trained with one-step and recursive multi-step prediction objectives. At inference time the model parameters are frozen and a single context trajectory is encoded. Multiple candidate controls are then generated and their outcomes are recursively predicted by the learned dynamics surrogate and, among those many candidate control, only the candidate with the lowest predicted objective is selected and executed.
This methodology is evaluated on a variety of benchmarks: Pendulum, CartPole, KS1D, 2D Kolmogorov flow, and Smoke2D, including parameter-shifted OOD environments and the paper reports lower control costs than the considered baselines across all main experimental settings.
Critical strengths
First, the empirical analysis is broad and nontrivial since the method is evaluated across both low-dimensional systems and high-dimensional PDE and transport control problems, and the reported improvements are consistent across the main benchmark settings rather than being limited to a single task. Furthermore, the paper also includes useful ablations of the context encoder, replay, Gibbs weighting, and predictor-based candidate ranking. The experimental details are reported with attention to details.
Also, the proposed system is operationally coherent. In particular, adaptation to a new environment requires only a context trajectory and a forward pass through the encoder rather than test-time parameter optimization, while candidate generation and model-based ranking avoid additional physical interactions. It is also a strength that the authors explicitly train the dynamics predictor with recursive multi-step losses rather than only one-step teacher-forced prediction to mitigate autoregressive rollout error accumulation.
Critical weaknesses
- The conceptual novelty appears limited, and the current experimental setup does not sufficiently isolate what is new in OMFM
All the main ingredients of this method have close precedents: online/meta-adaptive control across varying environment-dependent dynamics and shared representations (e.g. [1, 2]), latent context inference followed by context-conditioned dynamics prediction (e.g. [3]), generative trajectory/control modeling (e.g. [4] and related diffusion/flow policies), and amortization of finite-horizon predictive control using learned models or policies (e.g. [6], as well as subsequent amortized-MPC work). Reward-/cost-weighted supervised policy fitting is also an established mechanism (see [5]).
The identifiable novelty therefore appears primarily to be the particular composition of these ideas: transition-based context encoding + Gibbs-weighted flow matching + a context-conditioned dynamics surrogate + candidate ranking under sequential replay. I do not currently see sufficient evidence that this composition constitutes a substantial methodological advance rather than a useful engineering synthesis of pre-existing ideas.
Relatedly, I think the paper should position OMFM more explicitly with respect to the amortized predictive-control literature. A substantial line of work replaces or accelerates repeated finite-horizon optimization with learned policies or models. OMFM similarly learns a mapping from system/task information to finite-horizon control sequences in order to avoid iterative optimization at deployment. The paper should therefore clarify what is fundamentally gained by conditional flow matching relative to these approaches, beyond providing a different amortized parameterization of finite-horizon control.
More importantly, the baselines do not cleanly isolate the contribution of flow matching. For example, this work would benefit from ablations with a context-conditioned sequence behavior-cloning model and/or CVAE, or another non-flow sequence generator, given the same cost weighting, the same context representation, the same number of candidate samples, and the same learned-dynamics ranking procedure. A context-conditioned amortized-MPC or differentiable-predictive-control baseline would also be highly informative. Without such controls, it is difficult to determine whether the reported gains come specifically from the proposed flow-matching formulation or primarily from environment conditioning plus model-based candidate selection. This concern is reinforced by the Pendulum ablation, where removing the encoder or candidate ranking is substantially more damaging than removing Gibbs weighting. It would also be helpful to characterize the distribution of generated action candidates.
- The paper's central claim of adaptation/generalization to unknown dynamics is supported mainly by relatively local parameter shifts within unchanged dynamics families, while both the empirical and theoretical characterization of adaptation remain limited.
The OOD environments preserve the governing equations, geometry, and qualitative task structure, and generally extend one or a small number of physical parameters only slightly beyond the training support. For example, the Pendulum natural-frequency support is extended from [0.75, 1.25] to adjacent intervals reaching 0.65 and 1.35; KS1D extends κ from [0.15, 0.45] to [0.10, 0.15) ∪ (0.45, 0.50]; and Smoke2D explicitly shifts one hidden parameter by 15% of the width of its training range. These experiments demonstrate local parametric extrapolation, but in my view they do not yet substantiate a broader claim of adaptation to OOD dynamics.
This concern is especially important because control selection relies on recursively rolling out a learned dynamics surrogate over the entire horizon. The authors appropriately include recursive multi-step prediction losses during training, so the issue is not that compounding error is ignored. However, I did not find direct diagnostics of the quantities that matter for control selection under OOD dynamics, such as recursive rollout error versus horizon, predicted-versus-true candidate cost, or candidate-ranking accuracy. Since only the surrogate-selected candidate is executed, ranking fidelity is particularly important.
A further concern is the limited theoretical characterization of the central adaptation problem. This is particularly noticeable relative to related work on online meta-learning and meta-adaptive control. For example, Online Meta-Learning [7] provides regret guarantees under appropriate assumptions, while Shi et al. [1] study Online Meta-Adaptive Control in sequential environments with unknown environment-dependent nonlinear dynamics and develop both learning- and control-theoretic guarantees. Related control-oriented meta-learning work also explicitly considers closed-loop tracking performance [2].
In contrast, the theoretical material in this submission mainly characterizes the conditional flow-matching regression target and the finite-sample loss construction. In particular, the analysis states that the desired environment-conditioned field is recovered when the learned context c preserves the relevant environment-dependent information, but it does not establish when or why the proposed trajectory encoder should satisfy this property, especially when c is inferred from a single trajectory in an unseen environment.
Thus, the analysis effectively assumes the difficult part of the proposed adaptation mechanism: that c is a sufficiently informative representation of the unknown dynamics. I did not find a result relating context quality to dynamics-prediction error, candidate-ranking error, control suboptimality, regret, robustness, or generalization beyond the training dynamics distribution. Given both the paper's framing as an online meta-control method and the stronger theoretical characterization available in some closely related antecedents, I view this as a meaningful weakness rather than merely an optional extension.
[1] Shi, Guanya, et al. "Meta-adaptive nonlinear control: Theory and algorithms." Advances in Neural Information Processing Systems 34 (2021): 10013-10025. [2] Richards, Spencer M., et al. "Control-oriented meta-learning." The International Journal of Robotics Research 42.10 (2023): 777-797. [3] Lee, Kimin, et al. "Context-aware dynamics model for generalization in model-based reinforcement learning." International Conference on Machine Learning. PMLR, 2020. [4] Wei, Long, et al. "Diffphycon: A generative approach to control complex physical systems." Advances in Neural Information Processing Systems 37 (2024): 4090-4147. [5] Peters, Jan, and Stefan Schaal. "Reinforcement learning by reward-weighted regression for operational space control." Proceedings of the 24th international conference on Machine learning. 2007. [6] Drgoňa, Ján, et al. "Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems." Journal of Process Control 116 (2022): 80-92. [7] Finn, Chelsea, et al. "Online meta-learning." International conference on machine learning. PMLR, 2019.
Questions for authors
- Novelty and controlled baseline: Can the authors compare OMFM against a non-flow, context-conditioned sequence generator trained using the same context trajectories and cost weighting, with exactly the same number of sampled candidates and exactly the same learned-dynamics ranking procedure? This would help determine whether flow matching itself contributes materially beyond context conditioning + sampling + model-based ranking. A context-conditioned amortized-MPC or differentiable predictive-control baseline would also strengthen the paper.
- Surrogate reliability: Can the authors report recursive dynamics-prediction error as a function of rollout horizon, separately for ID and OOD environments, particularly for KS1D/K2D/Smoke2D? More importantly, can they report metrics between predicted and true candidate costs or top-k/ranking accuracy of the surrogate? Since only the surrogate-selected candidate is physically evaluated, prediction accuracy alone is less informative than ranking fidelity.
- OOD severity: Can the authors evaluate materially larger or structurally different dynamics shifts, rather than only adjacent parameter-range extensions within the same governing system? Examples could include simultaneous multi-parameter shifts, changed actuator effectiveness/layout, changed forcing/boundary conditions, or substantially farther parameter extrapolation. If performance degrades, a quantitative curve versus distance from the training support would be much more informative than a binary ID/OOD split.
- K2D clarification: Appendix C states that OOD environments are divided into viscosity-shift and forcing-amplitude-shift groups and describes these as single-parameter shifts, but it also states that is in {3,4} for ID and {2.5,4.5} for OOD. Does every OOD environment therefore also have an OOD ? If so, these are not single-parameter shifts. Please clarify the construction and report results broken down by the actual shifted parameters.
- Theoretical characterization: Several closely related online/meta-adaptive control methods provide regret, convergence, stability, or tracking guarantees, whereas the present analysis appears to characterize flow matching conditional on an already-informative environment representation. Can the authors provide a result that addresses the central adaptation step itself? In particular, under what assumptions does the finite trajectory context yield a sufficient or approximately sufficient representation of the unknown dynamics for control? Can error in c be related to dynamics-prediction error, candidate-ranking error, and/or final control suboptimality? A result of this form, even under a simplified dynamics class, would strengthen the paper.
- Role of the formalism: What technical result or capability of OMFM requires the empirical-measure / measure-conditioned formulation of the context in Sec. 3.1? As currently written, it seems that the implemented method could be described equivalently as a finite-set trajectory encoder conditioning a flow model. If the measure-theoretic formulation is important beyond interpretation, could the authors clarify what result depends on it? Otherwise, simplifying this part may make the actual methodology more straightforward.
7 comments
Official Response to Reviewer FFmj (2)
Q2: Compare OMFM with matched non-flow generators and predictive-control baselines.
A2: Thank you for this suggestion. We added controlled comparisons with non-flow generators, sequence baselines, and differentiable predictive control in the revised Appendix D.3 (Tables 14, 17, and 26). These experiments evaluate the contributions of conditional flow matching and amortized control generation under matched context and evaluation protocols.
1. Matched non-flow generators (Table 17). We replace OMFM's conditional flow matching (CFM) generator with a conditional variational autoencoder (CVAE) or diffusion model (50 DDIM steps), while keeping the same context encoder, Gibbs cost weighting, dynamics predictor, and 16-candidate ranking procedure.
| Generator | Pendulum J | Time (s) | KS1D(Dissipation) J | Time (s) | K2D J | Time (s) |
|---|---|---|---|---|---|---|
| CVAE | 0.1420 | 0.013 | 0.1294 | 0.022 | 0.1911 | 0.905 |
| Diffusion (50 DDIM) | 0.1504 | 0.1452 | 0.2739 | 0.1632 | 0.4110 | 3.544 |
| OMFM (Ours) | 0.1358 | 0.024 | 0.1217 | 0.040 | 0.1879 | 1.206 |
OMFM achieves the lowest control cost on all three systems, outperforming both non-flow alternatives under identical conditioning, weighting, and selection mechanisms. It also provides substantially faster inference than diffusion, while CVAE offers a faster but less accurate alternative. These results isolate the contribution of the flow-matching generator beyond context conditioning and model-based ranking.
2. Matched sequence-generation baselines (Table 14). We additionally equip OFM, FMPhyCon, and Sequence BC with the same one-trajectory test context and 16-candidate budget. Under this matched setting, OFM is equivalent to OMFM without Gibbs weighting, directly isolating the contribution of cost-weighted learning. OFM and Sequence BC use predictor-based ranking, whereas FMPhyCon ranks jointly generated state–control trajectories.
| Method | Pendulum | KS1D(Dissipation) | K2D |
|---|---|---|---|
| OFM | 0.1402 | 0.1581 | 0.2113 |
| FMPhyCon† | 0.1694 | 0.2644 | 0.3263 |
| Sequence BC | 0.1791 | 0.1496 | 0.2117 |
| OMFM (Ours) | 0.1358 | 0.1217 | 0.1879 |
OMFM achieves the lowest control cost across all three systems, outperforming both non-flow alternatives under identical conditioning, weighting, and selection mechanisms. It offers a favorable accuracy–efficiency trade-off: CFM achieves higher control accuracy with substantially faster inference than diffusion, while outperforming the faster but less accurate CVAE. These results isolate the contribution of flow matching beyond context conditioning and model-based ranking.
3. Context-conditioned differentiable predictive control (Table 26). We introduce CC-DPC, which shares OMFM's TACE encoder, dynamics predictor, and control objective, but directly optimizes 16 independently initialized control sequences through gradients. We evaluate optimization budgets of 1–100 steps.
| Method | Pendulum J | Time (s) | KS1D(Dissipation) J | Time (s) | K2D J | Time (s) |
|---|---|---|---|---|---|---|
| CC-DPC-1 | 0.3418 | 0.074 | 2.0459 | 0.223 | 0.5966 | 6.940 |
| CC-DPC-10 | 0.2909 | 0.630 | 1.8501 | 1.955 | 0.5578 | 60.672 |
| CC-DPC-50 | 0.2128 | 2.948 | 1.1508 | 10.582 | 0.4266 | 449.280 |
| CC-DPC-100 | 0.1846 | 5.851 | 0.5166 | 19.397 | 0.3296 | 592.246 |
| OMFM (Ours) | 0.1358 | 0.024 | 0.1217 | 0.040 | 0.1879 | 1.206 |
OMFM achieves lower control costs and faster inference across all three systems, even compared with 100-step CC-DPC. On KS1D, OMFM achieves in 0.040 s, versus in 19.397 s for CC-DPC-100. The higher costs of CC-DPC may reflect the risk of over-optimizing controls against an imperfect learned dynamics model. By avoiding test-time gradient optimization, OMFM reduces computational overhead and exposure to surrogate-model exploitation, demonstrating the accuracy and efficiency of amortized, context-conditioned control generation.
Official Response to Reviewer FFmj (3)
Q3: How reliable are recursive dynamics predictions and candidate rankings under ID/OOD shifts?
A3: Thank you for this question. We added recursive prediction and candidate-ranking diagnostics in the revised Appendix D.3 (Figure 11 and Table 18).
1. Recursive prediction error (Figure 11). We measure relative errors over the full rollout horizon on KS1D(Dissipation) and K2D () and Smoke2D Domain (), separately for ID/OOD environments. Predictions recursively use estimated states without ground-truth feedback.
| Horizon (KS1D/K2D/Smoke2D) | KS1D ID / OOD | K2D ID / OOD | Smoke2D ID / OOD |
|---|---|---|---|
| 5 / 5 / 16 (25%) | 0.024 / 0.021 | 0.035 / 0.038 | 0.079 / 0.093 |
| 10 / 10 / 32 (50%) | 0.049 / 0.050 | 0.070 / 0.087 | 0.114 / 0.137 |
| 15 / 15 / 48 (75%) | 0.095 / 0.108 | 0.104 / 0.132 | 0.155 / 0.194 |
| 20 / 20 / 64 (100%) | 0.182 / 0.229 | 0.130 / 0.164 | 0.190 / 0.247 |
Errors accumulate with horizon, with larger OOD errors at longer horizons. The predictor uses both one-step and multi-horizon training losses (Section 3.2; Appendix B.3). Importantly, its role in OMFM is to rank candidate controls rather than provide exact state predictions for execution. Since selection depends on relative predicted costs rather than absolute prediction accuracy, reliable candidate rankings can mitigate the impact of OOD prediction errors on control performance, as further supported by Table 18.
2. Candidate-ranking fidelity (Table 18). For the same 16 candidates, we compare predicted and true simulator costs using Spearman correlation and Recall@3. We also report true costs of predictor selection (), oracle selection (), and random selection ().
| System | Split | Recall@3 | ||||
|---|---|---|---|---|---|---|
| Pendulum | ID | 0.859 | 0.840 | 0.1296 | 0.1205 | 0.1649 |
| OOD | 0.775 | 0.760 | 0.1421 | 0.1306 | 0.1775 | |
| KS1D | ID | 0.952 | 0.960 | 0.0785 | 0.0768 | 0.1020 |
| OOD | 0.910 | 0.920 | 0.1650 | 0.1643 | 0.1857 | |
| K2D | ID | 0.854 | 0.880 | 0.1864 | 0.1620 | 0.2463 |
| OOD | 0.764 | 0.840 | 0.1895 | 0.1659 | 0.2526 | |
| Smoke2D | ID | 0.715 | 0.800 | 0.0922 | 0.0873 | 0.2257 |
| OOD | 0.699 | 0.660 | 0.1145 | 0.1059 | 0.3380 |
Despite increased OOD prediction errors, candidate ranking remains effective, consistently outperforming random selection and approaching oracle performance in several settings. True costs of all candidates are computed only for this diagnostic; deployment selects controls using predicted costs and executes a single physical rollout.
Q4: K2D problem setting clarification.
A4: Thank you for identifying this inconsistency. The original statement for standard OOD environments was a reporting error that conflated two separate K2D experiments. We have corrected and clarified both settings in the revised Appendix C.4.
1. Standard ID/OOD evaluation (Tables 1 and 9). The relevant parameter space is , with for both training and testing. ID environments use and . OOD environments are equally divided into two groups:
- Viscosity shift: , with within its training range.
- Forcing-amplitude shift: , with within its training range.
Therefore, no standard OOD environment has an out-of-distribution . The OOD evaluation extends one parameter at a time beyond the training region in the space, while retaining the same admissible wavenumbers. Table 9 reports aggregate K2D control costs of 0.1864 (ID) and 0.1895 (OOD) for OMFM.
2. Separate parameter-space evaluation (Figure 4(b)). This experiment uses independently trained models with continuous training distributions and , fixing . Evaluation covers a 31×31 grid over and , including joint extrapolation in forcing amplitude and wavenumber.
Thus, applies exclusively to the separate parameter-space evaluation, not the standard ID/OOD tests. The revised Appendix C.4 now explicitly distinguishes these experimental protocols.
Official Response to Reviewer FFmj (1)
Thank you for your careful reading of the paper and your constructive comments. We address each point below.
A1: Thank you for this assessment. We acknowledge precedents in online/meta-adaptive control, context-conditioned dynamics modeling, generative planning, cost-weighted learning, and amortized predictive control. OMFM's methodological contribution lies in coupling environment-conditioned control distribution learning with independent dynamics-based candidate evaluation under sequentially arriving unknown dynamics. The trajectory context jointly conditions generation and evaluation; Gibbs weighting shapes candidate quality, while dynamics-based ranking selects controls suitable for the inferred environment.
1. Conditional distribution learning beyond deterministic amortization. Unlike deterministic regression (s0,c)→u1:H, OMFM learns pθ(u1:H∣s0,c). For the same initial condition and context, multiple near-optimal strategies Uϵ=U:Jξ(U;g)≤J∗+ϵ may exist. Regressing distinct modes to one sequence risks mode averaging; furthermore, identical tasks may require different controls under different dynamics. Context conditioning preserves environment-dependent strategies, while within-initial-condition Gibbs weighting favors low-cost solutions without over-weighting easier initial states. Flow matching thus models alternative control strategies rather than only amortizing a single optimizer output. In revised Appendix D.3 (Table 13), OMFM achieves J=0.1358/0.1217/0.1879 on Pendulum/KS1D(Dissipation)/K2D, compared with 0.1651/0.1436/0.2435 for Context+FM and 0.1785/0.2102/0.4351 for Context+FNO under the same one-trajectory context, demonstrating the benefits of OMFM's integrated formulation beyond context conditioning alone.
2. Decoupled generation and dynamics-based evaluation. A context inferred from limited observations need not fully identify unknown dynamics; a single proposal U∗=Gθ(c,s0,ϵ) can therefore be sensitive to context uncertainty, OOD shifts, approximation errors, or sampling variability. OMFM samples multiple candidates and uses a separately trained, context-conditioned predictor to estimate trajectories X^(m) and costs J^(m), selecting the lowest predicted cost. Generation explores alternative strategies without gradients from the predictor; independent evaluation ranks their suitability under the inferred dynamics. Since selection requires relative cost ordering, not exact absolute predictions, it can remain reliable under increased OOD prediction error when rankings are preserved. This differs from directly optimizing one control sequence through a learned model.
3. Sequential online meta-learning and gradient-free adaptation. As environments arrive, OMFM updates its shared encoder, generator, and predictor with bounded replay and no access to future environments. At deployment, one observed trajectory conditions both generation and ranking through forward inference, without gradient-based parameter updates. The framework thereby links cumulative knowledge acquisition to low-overhead adaptation to unseen dynamics.
4. Evidence for complementary components. The revised Appendix D.3 reports:
Together, these controlled analyses support the complementary roles of context-conditioned distribution learning, cost-weighted generation, and predictor-based selection—not novelty claims for their individual ingredients.