- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies inference-time sampling when a pretrained diffusion model is imperfect and an external reference energy specifies the desired target distribution. It distinguishes two sources of error: endpoint mismatch, where the learned terminal density differs from the reference target, and path-tracking error, where sampling dynamics fail to follow the prescribed intermediate densities. The authors introduce the Energy-based Feynman–Kac Corrector (EBFKC), a framework for energy-based diffusion models that corrects these errors on the fly given a reference energy. Experiments cover Gaussian mixtures, interacting particle systems, and molecular sampling and free-energy estimation.
Critical strengths
- The paper correctly distinguishes the density defined by a learned energy from the marginal distribution generated by the corresponding reverse SDE. These need not coincide. This distinction explains why increasing the particle count alone cannot repair every source of sampling error, and provides a useful framework for interpreting inference-time correction methods. 2.The reported improvements are substantial across several relevant benchmarks.The experiments extend beyond analytical examples to learned molecular energy models. For ALDP annealing, Table 2 reports a reduction in Ramachandran TVD from for EBFKC on MIT to for EBFKC on EAT, and a reduction in basin-population error from to . The free-energy results in Figure 5 are also encouraging.
Critical weaknesses
The experiments diagnose the proposed failure modes more convincingly than they establish a practical advantage over competing correction strategies. The geometric tempering baseline on LJ-13 is useful, but its comparison uses the same particle count rather than a demonstrated comparable computational budget. Its runtime is also absent from Table 8. Across the paper, runtime tables report individual operating points rather than accuracy as a function of computational budget, despite the inference-time scaling motivation. The derivative overhead is material: Table 9 reports approximately seconds for EBFKC on EAT versus seconds for EBFKC on MIT.
Questions for authors
Given the unconstrained architecture with sampling-time endpoint replacement in Grenioux and Noble, what precise capability or guarantee distinguishes EBFKC beyond the progressive correction schedule and its integration with VCG?
3 comments
Response to Reviewer idu7 [2/3]
(b) Accuracy as a function of compute budget, and derivative overhead (ALDP)
"Across the paper, runtime tables report individual operating points rather than accuracy as a function of computational budget, despite the inference-time scaling motivation. The derivative overhead is material: Table 9 reports approximately (508) seconds for EBFKC on EAT versus (143) seconds for EBFKC on MIT."
For ALDP annealing, we compare particle-count scaling for EBFKC on EAT and EBFKC on MIT. To approximately match compute budgets, EBFKC on MIT uses four times as many particles per batch as EBFKC on EAT. Results are evaluated on samples accumulated over 25 batches:
| Method | Batch-wise particles | Wall Clock (s) | Energy TVD ↓ | Distance TVD ↓ |
|---|---|---|---|---|
| EBFKC on EAT | 100 | 100.95 ± 2.45 | 0.077180 | 0.009166 |
| 200 | 140.68 ± 2.24 | 0.047207 | 0.007234 | |
| 500 | 308.38 ± 2.50 | 0.035113 | 0.004006 | |
| 1,000 | 613.05 ± 5.04 | 0.023555 | 0.002973 | |
| EBFKC on MIT | 400 | 76.38 ± 0.60 | 0.442142 | 0.038203 |
| 800 | 147.05 ± 0.82 | 0.437852 | 0.035386 | |
| 2,000 | 349.93 ± 1.57 | 0.435523 | 0.037053 | |
| 4,000 | 695.40 ± 2.33 | 0.455924 | 0.037037 |
We have also included the inference-time scaling curve in Fig. 5 of the revised paper. Scaling the number of particles clearly improves EBFKC on EAT. EBFKC on MIT does not benefit from more particles because of the endpoint mismatch error. The overhead you note in Table 9 of the paper (508 s vs. 143 s) comes mainly from the OpenMM finite differences for the reference-energy terms, which are not parallelized across particles (App. B.4; see also our complexity analysis in the response to Reviewer aQ3B); even so, at a matched wall-clock time EBFKC on EAT is far more accurate than EBFKC on MIT with more particles.
Response to Reviewer idu7 [3/3]
Comparison with DABG
"Given the unconstrained architecture with sampling-time endpoint replacement in Grenioux and Noble, what precise capability or guarantee distinguishes EBFKC beyond the progressive correction schedule and its integration with VCG?"
We thank the reviewer for this insightful question, which lets us clarify how EBFKC differs from DABG [1]. The main differences are:
- Setting and generality. We target inference-time scaling, i.e., sampling under arbitrary annealing and reward tilting, rather than the equilibrium distribution alone. DABG is therefore a particular case of EBFKC:
- its pinned architecture corresponds to EBFKC on the model-induced path with and (Sec. 3.3);
- its unconstrained architecture with sampling-time endpoint replacement corresponds to an EAT path whose correction schedule jumps from 0 to 1 at .
- General prescribed paths, purely post-training. Theorem 2 guarantees exact tracking of any prescribed path in the continuous-time population limit, not only the raw energy-based marginals. We exploit this freedom with a look-ahead map that avoids evaluating noisy samples directly on and ; without it, our ALDP runs become numerically unstable (App. D.4). DABG instead uses either the raw energy path or a pinned architecture, which can be seen as a look-ahead built into training. Our construction requires no change to training.
- Progressive correction schedule and VCG. As you note, we additionally integrate a progressive correction schedule with VCG, and both proved essential in our experiments. On the hardest molecular problems, an appropriate schedule is needed for accurate sampling, and VCG is key to weight stability when the pretrained model is imperfect. Neither is explored in DABG.
- Complementary tools in DABG. DABG also explores a replica-exchange-based correction, which does not directly transfer to our framework. It also uses integration schemes beyond Euler–Maruyama, which could readily be combined with EBFKC.
We thank you again for your constructive feedback. We hope our responses and additional experimental results have addressed your concerns, and we would be very grateful if you could consider raising your score.
Reference
[1] Grenioux, Louis, and Maxence Noble. "Diffusion-based Annealed Boltzmann Generators: benefits, pitfalls and hopes." arXiv preprint arXiv:2601.21026 (2026).
Response to Reviewer idu7 [1/3]
We sincerely thank you for highlighting the strengths and novelty of our work, and for your insightful suggestions! We are glad that you find that our paper "correctly distinguishes the density defined by a learned energy from the marginal distribution generated by the corresponding reverse SDE." As you note, this distinction "explains why increasing the particle count alone cannot repair every source of sampling error, and provides a useful framework for interpreting inference-time correction methods." We also appreciate your observation that "the reported improvements are substantial across several relevant benchmarks" and that "the experiments extend beyond analytical examples to learned molecular energy models." Thank you as well for noting that "the free-energy results in Figure 5 are also encouraging." We address your suggestions below.
Practical advantage over competing strategies under matched computational budgets
We find this suggestion really helpful. We have added matched-budget comparisons to clarify that EBFKC has a practical advantage over competing strategies.
(a) Tempering SMC on LJ-13
For tempering-path SMC on LJ-13, we scale the number of particles and report wall-clock times:
Tempering SMC is much faster per particle, but its error barely changes over a 100-fold increase in particles (∣ΔNLL∣ from 17.3 to 15.5 for annealing and from 13.8 to 14.2 for reward tilting) and remains more than an order of magnitude above that of EBFKC on EAT even at 1,000,000 particles.