- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper brings Kuramoto-style synchronization from KODM (Song et al., NeurIPS 2025) into diffusion models for decision making, used as planners, policies and trajectory synthesizers. Trajectory chunks are treated as phases of coupled oscillators. Instead of running stochastic Kuramoto dynamics, KDDM computes a deterministic mean-field coupling term from the clean chunk only (self-synchronization) and defines the forward kernel so that this term enters as a time-dependent mean shift, removed and re-added at every step (telescoping update). This gives closed-form Gaussian marginals and posteriors, a standard Gaussian prior and a clean-sample prediction loss. On top of this the paper derives an ODE sampler (KDIM), classifier and classifier-free guidance, replacement and posterior-sampling guidance, SMC, and a small network that approximates the coupling term. KDDM and KDIM are plugged into many existing pipelines: unconditional trajectory generation on MuJoCo and Adroit, D4RL planners built on Diffusion Veteran, Diffusion Policy, Diffusion BC and DSRL on Robomimic, PushT and Relay Kitchen, and four tasks on a real SO-ARM arm. Improvements are reported in temporal and spatial correlation of generated data, in D4RL averages, and most clearly for Diffusion BC.
KODM: Yue Song, T. Anderson Keller, Sevan Brodjian, Takeru Miyato, Yisong Yue, Pietro Perona, Max Welling; NeurIPS 2025, arXiv 2509.15328
Critical strengths
- The empirical scope is broad. KDDM is dropped into about ten existing methods across three roles (synthesizer, planner, policy) with small changes, and the guidance suite makes it usable in standard pipelines.
- The reformulation removes the practical problems of KODM in this setting (no closed-form marginal, no ODE sampler, no guidance), and as far as I could find this is the first use of Kuramoto dynamics in diffusion-based decision making. Training stays single-step like DDPM, apart from computing the coupling term.
- Results are consistent in direction: better temporal and spatial fidelity than DDPM-family baselines (Fig. 7), higher D4RL averages than the DV base (Table 1), and large gains for Diffusion BC, e.g. on PushT-Image (Fig. 9). The "w/o Syn." ablation on Adroit (Table 4) shows the shift helps over plain DDPM in the same code base.
- The paper is well-written and easy to follow.
Critical weaknesses
- The reviewer believes the technical novelty is overstated. Eqs. 4-6, the x0 objective and the DDIM version (Eq. 10) match ContextDiff (Yang et al., ICLR 2024) term for term, with its learned bias replaced by the Kuramoto term. ContextDiff is cited only in the appendix, while the intro says "We design" this kernel. ShiftDDPMs (Zhang et al., AAAI 2023) uses the same telescoping construction and Neural Diffusion Models (Bartosh et al., ICML 2024) covers it as a fixed-transform case; neither is cited. The only new parts are the Kuramoto coupling as the shift term and its use in decision making.
- It is unclear what the Kuramoto term encodes. KDDM is DDPM on the shifted variable, the prior is N(0, I), and the shift fades as synchronization completes. The coupling is global over all entries of the chunk, so it is blind to temporal adjacency and joint structure, against the spatio-temporal motivation. The phase mapping is not described, and a circular topology is odd for positions and velocities.
- The gains are not attributed. No ablation swaps the Kuramoto shift for another shift, and the DDPM baselines' parameterization is not stated while KDDM predicts x0. Diffusion Policy and DSRL gains are about one point, KDDM is within one or two points of PG on D4RL (PG is better on AntMaze), and Fig. 22 claims consistent planner gains though KDDM is below the original on several bars (its MuJoCo panels look transposed). The §5.2 numbers do not match Table 1, and the real-robot result is compared with 2/10 from another paper.
• Yang, L., Zhang, Z., Yu, Z., Liu, J., Xu, M., Ermon, S., and Cui, B. Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing. ICLR 2024. arXiv:2402.16627. (ContextDiff) • Zhang, Z., Zhao, Z., Yu, J., and Tian, Q. ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories. AAAI 2023. arXiv:2302.02373. • Bartosh, G., Vetrov, D., and Naesseth, C. A. Neural Diffusion Models. ICML 2024, PMLR 235. arXiv:2310.08337. (NDM)
Questions for authors
- What is technically new beyond the choice of coupling term? Eqs. 4-6 and 10 match ContextDiff's forward kernel, marginal, posterior and DDIM update with its learned bias replaced by κK, ShiftDDPMs has the same telescoping construction, and NDM contains KDDM as a fixed-transform case. Please cite these where Eq. 4 is introduced and restate the contribution relative to them.
- Can the gains be credited to Kuramoto dynamics? Please replace the Kuramoto shift with (a) a learned shift trained end to end as in ContextDiff, (b) a simple pull toward the chunk mean or a temporal smoothing operator, and (c) DDPM with an SNR-matched schedule, all with the same x0 parameterization and network. If (a) or (b) match KDDM on ACF/CC and on the planner and policy benchmarks, the gain comes from the shifted-diffusion construction rather than from synchronization.
7 comments
Official Response to Reviewer Yq6a (Part II)
C3: Attribution of empirical improvements.
Response: In response to the reviewer's request, in Section 5.5 we have conducted additional experiments (Data Synthesizer) comparing KDDM with alternative mechanisms under the same experimental setting. Specifically, we consider the following variants: (a) Learned shift: replacing the Kuramoto-based shift with a learnable shift mechanism using Ts2vec [6], a contrasive representation learning alogorithm. (b) Simple synchronization alternatives: using a mean-pulling mechanism to investigate whether the improvements can be explained by simpler forms of coordination. (c) Standard DDPM: using a comparable noise schedule and prediction parameterization to control for differences in diffusion configurations. All comparisons are designed to maintain consistent network architectures and prediction parameterizations wherever applicable.
It can be seen in Figure 11, trajectories generated by (a) and (b) exhibit large performance degradation in modeling spatio-temporal dependencies (ACF and CC), with CC scores nearly collapsing, which we attribute to their numerical stochasticity. And (c) still underperforms KDDM. Moreover, as reported in the table below, for Diffusion
BC in Relay Kitchen, we observe a similar trend that KDDM outperforms both shift alternatives on all four tasks and achieves the best overall performance.
These results help distinguish the contribution of the general shifted-diffusion formulation from that of the specific synchronization mechanism.
| Method | Task 1 | Task 2 | Task 3 | Task 4 |
|---|---|---|---|---|
| KDDM | 100.0 | 92.7 | 77.7 | 45.4 |
| (a) Learned shift | 28.67 | 0.67 | 0.0 | 0.0 |
| (b) Mean Shift | 40.67 | 25.0 | 5.33 | 0.0 |
| (c) DDPM (x0) | 98.0 | 86.0 | 72.33 | 48.33 |
C4: Numerical consistency and real-world validation.
Response: We thank the reviewer for identifying several issues in the experimental presentation. First, we have also revised Figure 22 and corrected the disorder of the corresponding MuJoCo results. We apologize for these errors in the original manuscript. Second, regarding the real-world experiments, we have added direct comparisons against the baseline Diffusion Policy across all four real-world robotic manipulation tasks in Appendix D.6. We have also added some new demos of the baseline to https://kuramoto-decision-diffusion.github.io/#exp-robot. We believe these additional experiments provide stronger evidence for the practical effectiveness of KDDM.
| Task | Baseline Success Rate | Our Success Rate |
|---|---|---|
| put-the-knife | 0.11 | 0.87 |
| pick-the-bottle | 0.2 | 0.7 |
| place-the-duck | 0.18 | 0.48 |
| put-the-egg | 0.22 | 0.58 |
References:
[1] Zhang, Zijian, et al. "Shiftddpms: Exploring conditional diffusion models by shifting diffusion trajectories." AAAI' 2023.
[2] Yang, Ling, et al. "Cross-modal contextualized diffusion models for text-guided visual generation and editing." ICLR' 2024.
[3] Nielsen, Beatrix MG, et al. "Diffenc: Variational diffusion with a learned encoder." ICLR' 2024.
[4] Bartosh, Grigory, et al. "Neural diffusion models." ICML' 2024.
[5] Miyato, Takeru, et al. "Artificial kuramoto oscillatory neurons." ICLR' 2025.
[6] Yue, Zhihan, et al. "Ts2vec: Towards universal representation of time series." AAAI' 2022.
Dear Reviewer Yq6a,
We have incorporated the additional experiments and clarifications into our updated rebuttal. Whenever you have a moment to review it, we would greatly appreciate any further feedback. Thank you again for your time and consideration.
Best regards,
The Authors
Official Response to Reviewer Yq6a (Part I)
Many thanks to you for providing thorough very thoughtful feedback. We have carefully reviewed all your comments and revised our manuscript. Due to space limits, the new and revised contents (marked in blue) have been integrated not only into the relevant sections of the main body, but also extensively into the appendix. We offer detailed responses to your comments below.
C1: Contributions over existing techniques.
Response: We thank the reviewer for highlighting the connections to prior works, which have helped us better position our contributions. We have added citations to related works [1–4] at the appropriate places in the main text (e.g.,
Section 4.1). We acknowledge that the mathematical formulation of shifted diffusion itself is not entirely new. However, we would like to clarify three key distinctions:Abstract) to address specific technical challenges. To avoid misunderstanding, we have revised the text inIntroductionto emphasize our contributions.Lemma 7), KDDM is fully self-contained and starts sampling directly from a standard Gaussian prior without requiring additional inputs. Second, KDDM offers greater interpretability and stability. The shift predictors in prior methods rely heavily on learned representations (e.g., CLIP), introducing substantial pretraining costs and potential numerical instability that may complicate the reconstruction of x0 or ϵ. In contrast, our Kuramoto system exhibits predictable synchronization dynamics with monotonically decreasing drift. Furthermore, while prior methods require assumptions about black-box model properties, such as Lipschitz continuity (lemma 4 in [2]), our framework naturally guarantees this property (seeLemma 6). To clarify these distinctions, we have added a subsection titled "In Comparison with ShiftDDPMs" inAppendix B.6. Regarding NDMs [3,4], which provide a general perspective on transformed diffusion processes, their target marginal distributions q(zt∣x)=N(αtF(x,t),σ2I) differ clearly from ours, so here we omit further discussion.C2: Interpretation of Kuramoto coupling.
Response: We would like to clarify that the purpose of Kuramoto coupling in KDDM is to model the collective coordination of trajectory elements rather than conventional smoothing. It is well-known that the Kuramoto model naturally incorporates spatio-temporal representations (e.g., see [5]). Following KODM, we treat the elements (both time and spatial axes) within a chunk, as coupled oscillators with the phase mapping θ=π×τ. A footnote has been added on
Page 4to describe the above. The circular geometry (also adopted from KODM) used here is standard in Kuramoto models. Their interactions are governed by relative phase differences, enabling the physics-inspired mechanism to capture collective synchronization patterns across the entire chunk, which can provide a useful inductive bias for trajectory generation. This allows trajectory elements to influence one another even when they are not adjacent; note that it is not blind to temporal adjacency and joint structure, because the ordering of all oscillators in the data vector (tensor) keeps intact. See demos in https://kuramoto-decision-diffusion.github.io/#background, in which the Phase Velocity is the encoding information we refer to. The underlying model in KDDM must perform denoising and desynchronization simultaneously upon receiving each θt, therefore considering the spatiotemporal information.