- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper estimates rare-event probabilities p[E] under a pretrained diffusion model and samples from p( x |E) by running SMC along the reverse chain. Intermediate targets are reward-tilted, γ_k = p_k e^{r_k}, with a guided proposal and importance weights in closed form for one-step Gaussian integrators. The normalising constant of the SMC gives \hat{p}[E]. It is unbiased for the discretised law when rejuvenation is exactly invariant. A chi squared bound for the no-resampling case identifies the Doob h-transform as the optimal proposal . The practicall reward is a sigmoid function threshold indicator evaluated at a Tweedie Gaussian look-ahead, with schedules \lambda_k and \tau_k . Experiments use a 2D Gaussian mixture and a climate emulator (Pacific Northwest hot and dry extremes). They report \hat{p}/p near 1 down to p ≈ 1e-5, lower CV than Manshausen et al. (2026) on the GMM, and net speed-ups of 6×–651× over crude Monte Carlo.
Critical strengths
The paper is very well written and nicely structured and outlines the sequential Monte Carlo approach very nicely. The theory is well developed. The ablations are done rigorously and this is generally a very nice paper.
Critical weaknesses
- I can't shake the feeling that the approach is essentially standard sequential Monte Carlo applied to diffusion models as first pioneered for steering in Boltz (https://www.biorxiv.org/content/10.1101/2024.11.19.624167v3.full.pdf) in Section 4: Boltz Steering.
- The authors draw the comparison to Xie et al and there the similarities become even stronger as Xie et al did use MBAR, but also used Delta G diffusion where the potential is a a slope as well. So the comparison comes down to potential design whether one uses the authors sigmoid or the Delta G potential. In the case of Xie et al, one can recover the normalization constant from the weights as well as the expectation over unnormalized weights
E_proposal[ unnormalized weights ]. Similarly, MBAR is just method to combine multiple tilts together and trivially reduces to reweighting when only one potential is used. So in my understanding MBAR then is a more general case.
Questions for authors
Regarding 2: Can the authors juxtaposition their work more detailed on a theoretical basis to Xie et al (https://arxiv.org/pdf/2602.16634) and Boltz 1 Steering (https://www.biorxiv.org/content/10.1101/2024.11.19.624167v3.full.pdf) and Twisted SMC (https://arxiv.org/pdf/2404.17546)? On the experimental side all three approaches yield algorithms to which the authors approach should be compared to. A comparison between DireSMC, FKC with a suitable potential and Twisted SMC should be done.
7 comments
W.2/Q.1 The authors draw the comparison to Xie et al. and there the similarities become even stronger as Xie et al did use MBAR, but also used Delta G diffusion where the potential is a a slope as well. So [..]
As noted above, we view the two works as complementary. Xie et al. (2026) target free energies of metastable states, focusing on how to adaptively construct bias potentials to estimate them. To do this, they use Feynman–Kac correctors (FKC; Skreta et al., 2025) to generate particles under each bias potential and combine these using MBAR. Our focus is the guidance step itself: for a single, fixed event (i.e. a single tilt), how to design the reward, schedule and weights so that the probability estimate is unbiased and has low variance (Theorems 1 and 2, Lemma 1). Nothing prevents the two from being combined: DireSMC could serve as the steering component within the framework of Xie et al., and their adaptive biasing and MBAR could be layered on top of our estimator. We agree that single-tilt MBAR reduces to importance reweighting and that MBAR is the more general tool for pooling several tilts; for a single rare event, its analogue is the splitting estimator (App. C.4).
DireSMC and FKC. As requested, we compare DireSMC against FKC as used in Xie et al. (2026), under the same look-ahead potential to keep the comparison fair. Under a learned score, FKC weights systematically underestimate the probability by about 20% (Table R3.1), an error that does not vanish as (Table R3.2). In contrast, DireSMC's weights remain on target. We will add the detailed discussion and additional experiments to the camera-ready version.
FKC vs. exact weights. Both methods simulate a guided reverse SDE, , with , , and (ours) or (FKC default). Let be the marginal of the learned sampler and its true score. The Feynman–Kac weight rate that makes the weighted process target is
At (FKC) the Laplacian drops out, but remains and is unknown, so FKC substitutes . This omits the term
which we denote as the self-consistency error or the network's score versus the score of the discretised sampler's marginals, projected onto the reward gradient. It vanishes only for an exact score and is present for a learned network. With a larger reward gradient, i.e. for increasing rarity, this error grows with .
At the term vanishes, but the rate needs ( extra second-derivative passes per step).
In both cases, integrating the rate along the chain with Euler steps adds an quadrature error.
Our weights are instead the exact likelihood ratio of the Gaussian transitions we simulate (base , guided , the step's noise, ):
Since enters and identically, it cancels: the weight is exact for any network and any , and needs neither nor . At it recovers path by path as .
References
Skreta, M., et al. (2025). Feynman-kac correctors in diffusion: Annealing, guidance, and product of experts. arXiv:2503.02819.
Xie, Y., et al. (2026). Enhanced diffusion sampling: Efficient rare event sampling and free energy calculation with diffusion models. The Journal of Chemical Physics, 165.16. arXiv:2602.16634.
Experiment. We ran additional experiments to compare to the FKC weights on the 2D GMM model (with , , adaptive resampling, no rejuvenation, 96 runs per cell; same SEEDS-1 integrator and look-ahead twist for every arm). FKC's original reward, evaluated on the noisy state, diverges at this rarity (), so we give FKC our look-ahead twist. To isolate the weight rule, we also accumulate the FK weight on the exact-weight sampler's own particles () and report FK/exact.
Overall, we find:
- DireSMC weights are on target in this setting, while FK weights are under-estimates (Table R3.1). We also found in additional experiments that with the learned score, the gap grows with rarity (0.94 at to 0.77 at , same paths, ).
- With the analytic score, FKC's error is dominated by the discretisation error alone, while with the learned score, an error appears to remain as (Table R3.2). For the analytic score, and the omitted term is zero, whereas for the learned score the omitted term does not vanish with . It also agrees with our MADM (Lam et al., 2026) analysis (Fig. 12, App. G.3.3): the learned score has a non-zero antisymmetric Jacobian, increasingly so as (Vuong et al., 2025), so it is not the gradient of any potential and cannot equal . The limit here is an extrapolation from , and since is unknown for a network, we identify the size of this term by elimination rather than measuring it directly.
- Cost. For c = 1, FK weight requires the Laplacian , whereas DireSMC weights need no evaluations beyond the sampler's own.
Table R3.1. 2D GMM, , , 96 runs per cell. Own runs: each method runs with and resamples on its own weights; s.e. (CV), where is the exact probability for the analytic score and, for the learned score, a crude Monte Carlo estimate of the event probability under its discretised sampler at the same , with a relative Monte Carlo error of . Same paths: we run DireSMC (exact weights, Eq. 12) with the same push as the FK arm, i.e. DireSMC itself for and DireSMC with a half push for FKC (), and, along each particle's path, also accumulate the FK log-weight. Both estimates are computed from the same particles, so their ratio isolates the weight rule. Note that for , the FK weights are an Euler discretisation of the continuous-time weight and are exact only as ; ours are exact for the simulated chain at every .
\text{Score} & \text{Arm} & \text{Own runs: } \hat p/p^*\\ \text{(CV)} & \text{Same paths: FK} \div \text{DireSMC weights} \\\\ \hline \text{analytic} & \textbf{DireSMC } (c=1) & 0.998 \pm 0.032\\ (0.31) & - \\\\ \text{analytic} & \text{FKC } (c=\tfrac12,\\ \text{FK}) & 0.881 \pm 0.069\\ (0.76) & 0.897 \pm 0.020 \\\\ \text{analytic} & c=1,\\ \text{FK (needs } \Delta R) & 0.848 \pm 0.025\\ (0.28) & 0.859 \pm 0.001 \\\\ \hline \text{learned} & \textbf{DireSMC } (c=1) & 1.024 \pm 0.027\\ (0.26) & - \\\\ \text{learned} & \text{FKC } (c=\tfrac12,\\ \text{FK}) & 0.802 \pm 0.062\\ (0.75) & 0.765 \pm 0.015 \\\\ \text{learned} & c=1,\\ \text{FK (needs } \Delta R) & 0.856 \pm 0.025\\ (0.28) & 0.843 \pm 0.001 \end{array}$$ **References** Lam, K. H., et al. (2026). Metropolis-adjusted diffusion models. arXiv:2605.09654. Vuong, A. B., et al. (2025). Are we really learning the score function? Reinterpreting diffusion models through Wasserstein gradient flow matching. arXiv:2509.00336. ```
We thank the reviewer for highlighting where our contributions and novelty can be made clearer. Firstly, we see DireSMC as a specific instantiation of Sequential Monte Carlo within a diffusion model, in particular of Twisted Diffusion Sampling (TDS; Wu et al., 2023), which is a special case of the Feynman–Kac steering of Singhal et al. (2025) used by Boltz-1. These frameworks provide the general machinery but do not prescribe how to build the reward path (Section 3.2, Eqs. 16 and 18), the guidance (Eq. 17, App. E) or the weight computation (Lemma 1, Theorem 1), or how these interact with the numerical integrator (App. D.1). Our contribution is to elucidate these choices for the rare-event probability estimation problem, where the normalisation constant, not only the samples, is required. Secondly, we see our work as complementary to Xie et al. (2026). They focus on adaptively constructing bias potentials and combining them with MBAR, with Feynman–Kac correctors (FKC; Skreta et al., 2025) generating the particles under each bias; we instead focus on that guidance step itself. These design choices measurably matter: DireSMC's weights stay on target where FKC weights underestimate by about 20% under a learned score (Table R3.1), and the difference potential, as in TDS, remains stable where the max and sum potentials of Singhal et al. (2025) collapse to a single lineage (Q1). Additionally, Lemma 1 extends TDS and DireSMC beyond Euler–Maruyama to any first-order stochastic integrator, where an exponential integrator reduces the discretisation bias (Table 6, App. G.2.2). Hence, DireSMC could serve as the steering component within the framework of Xie et al. (2026). We make this positioning precise below and report the requested comparisons, which we will add to the revised manuscript.
We agree that DireSMC is SMC applied to a diffusion model. It builds upon TDS (Wu et al., 2023), which the Feynman–Kac steering used in Boltz-1 (Singhal et al., 2025; Wohlwend et al., 2025) generalises (see Q1 below). Our contribution is not the framework but how to instantiate it when the goal is a rare-event probability, and this goal is the key difference from Boltz-1: like Boltz-1, we use SMC to improve the quality of guided samples, but we also use it to estimate the normalisation constant itself, which places stricter demands on each component. Specifically, we elucidate:
References
Gonzalez, M., et al. (2023). Seeds: Exponential sde solvers for fast high-quality sampling from diffusion models. Advances in Neural Information Processing Systems, 36, 68061-68120.
Singhal, R., et al. (2025). A general framework for inference-time scaling and steering of diffusion models. In Forty-second International Conference on Machine Learning.
Skreta, M., et al. (2025). Feynman-kac correctors in diffusion: Annealing, guidance, and product of experts. arXiv:2503.02819.
Wohlwend, J., et al. (2025). Boltz-1 Democratizing Biomolecular Interaction Modeling. bioRxiv 2024.11.19.624167.
Wu, L., et al. (2023). Practical and asymptotically exact conditional sampling in diffusion models. Advances in Neural Information Processing Systems, 36, 31372-31403.
Xie, Y., et al. (2026). Enhanced diffusion sampling: Efficient rare event sampling and free energy calculation with diffusion models. The Journal of Chemical Physics, 165.16. arXiv:2602.16634.