- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This is a paper develops an inference time methods for generating DNA/RNA/proteins using doob h-transform where the doob transition kernel is estimated using monte carlo samples. To speed-up monte carlo sample generation, the author took the denoiser in one step as a surrogate.
Critical strengths
- well written with nice illustrations.
- results in table 1 and 2 appear to have improved upon baseline methods.
Critical weaknesses
-
Insufficient benchmarking and missing literature, the author should explain the relation/difference between their methodologies and TFG-Flow.
Haowei Lin, Shanda Li, Haotian Ye, Yiming Yang, Stefano Ermon, Yitao Liang, and Jianzhu Ma. TFG-Flow: Training-free guidance in multimodal generative flow. In International Conference on Learning Representations, 2025. URL https://arxiv.org/abs/2501.14216
Doob-h transform has been used to training time finetuning of masked diffusion models for example in this paper which the authors should discuss relations with. Both papers appears to target the same tilted target distribution but from different sides.
Yuyuan Chen, Shiyi Wang, Peter Potaptchik, Jaeyeon Kim, and Michael S. Albergo. Discrete tilt matching. In Proceedings of the 43rd International Conference on Machine Learning, volume 306 of Proceedings of Machine Learning Research, pp. 17141–17164.
There is also the concurrent work of D-DOIT which the author should explain connections:
Jieke Wu, Qijie Zhu, Weimin Wu, Zeqi Ye, Minshuo Chen, and Han Liu. D-DOIT: Training-free adaptation of discrete diffusion via Doob’s h-transform. arXiv preprint arXiv:2610.04938, 2026. URL https://arxiv.org/abs/2610.04938
PMLR, 2026.2. I don't remember the original SVDD paper did experiments for table 1 and 2. The authors should sweep parameters when adapting SVDD to these new settings to make comparisons fair.
-
Inference methods always have reward hacking concerns. In table 1 did the authors score ATAC with the oracle that guides the model? If so how does the authors mitigate for reward hacking.
Questions for authors
Per Weakness 1,2,3 above.
3 comments
Response to M24Q [2/2]
W2 and Q2. SVDD Adaptation and Hyperparameter Analysis
We appreciate the request for parameter sweeps when adapting SVDD. We rerun SVDD on the DNA and protein tasks with the same frozen priors, task rewards and output counts as DiMOS. Appendix O adds a candidate-width and selection-rule comparison, together with proposal-temperature alignment on DNA. Appendix R further sweeps the selection temperature.
Candidate Width, Selection and Temperature Controls (new). We sweep on DNA and on protein under both gates. Each width is tested with greedy and stochastic selection, and the stochastic arm uses , equal to on DNA and on protein on the paper's reward scale. DNA additionally uses both the original proposal temperature and DiMOS's proposal temperature. The table below reports three-seed means for greedy SVDD, which is stronger than its stochastic variant at every tested width at the matched reward temperature. Table 20 includes both DNA proposal temperatures. Both DNA SVDD rows below use the DiMOS-matched temperature, . Time is in milliseconds per design.
| Domain | Method | M | Soft SR (%) | Hard SR (%) | Time (ms) |
|---|---|---|---|---|---|
| DNA | SVDD | 12 | 60.36 | 49.01 | 246 |
| DNA | SVDD | 20 | 64.74 | 57.29 | 435 |
| DNA | DiMOS | 4 | 98.39 | 87.55 | 235 |
| Protein | SVDD | 12 | 40.36 | 35.26 | 247 |
| Protein | DiMOS | 4 | 70.64 | 58.38 | 158 |
Increasing the candidate width improves SVDD but also increases its generation cost. Even the wider settings above remain below DiMOS in both domains and both modes while using more time. Appendix O, Table 20 gives the full width and selection comparison.
Selection-Temperature Sweep (new). We further vary the stochastic selection temperature in the rule over three seeds, including the matched value and values both above and below it. All SVDD settings below take approximately 246--247 ms per design.
SVDD selection-temperature sweep on protein + SeqRec. Joint SR is mean standard deviation over three seeds, following Appendix R.
| Selection | Soft SR (%) | Hard SR (%) |
|---|---|---|
| Argmax | ||
As , stochastic selection concentrates on reward-maximizing candidates. The sweep yields similar soft-gate performance for low-temperature stochastic selection and argmax, while argmax exceeds the best tested stochastic setting by 2.32 percentage points under the hard gate. Neither closes the gap to DiMOS. Appendix N further isolates the local transition by transferring DiMOS's search layer to SVDD. Together, these comparisons test the adapted baseline beyond its original operating point.
W3 and Q3. Independent ATAC Evaluation
We thank the reviewer for raising this concern. Yes, the original experiments use a fixed pretrained ATAC predictor to define the accessibility objective and score the generated designs. Applying this predictor consistently across methods provides a common criterion for comparing their ability to satisfy the specified objective.
Cross-Predictor Evaluation (new). To examine whether the gains extend beyond this predictor, we trained a new ATAC evaluator on a separate ATAC-seq experiment and rescored the same generated sequences from every method. The new evaluator never participates in guidance. Appendix M, Table 17 reports the full comparison, with three-seed means for SVDD and DiMOS reproduced below. Retention is the fraction of originally accepted designs that remain accepted under the new evaluator.
| Method | Gate | Original SR (%) | New evaluator SR (%) | Retention (%) |
|---|---|---|---|---|
| SVDD | Soft | 55.16 | 48.39 | 82.77 |
| DiMOS | Soft | 98.39 | 92.19 | 93.70 |
| SVDD | Hard | 45.05 | 42.50 | 88.77 |
| DiMOS | Hard | 87.55 | 84.58 | 96.61 |
DiMOS retains the highest joint SR and acceptance retention among all methods in both gate modes. These results show that its performance advantage transfers beyond the predictor used for optimization.
Dear Authors,
Thank you for the answers, which have addressed my concerns. I continue to recommend accept.
Response to M24Q [1/2]
We sincerely thank the reviewer for recognizing the clear presentation, illustrations and improvements in Tables 1 and 2. We also appreciate the suggestions on related work, baseline adaptation and independent evaluation. We address these three concerns below. New experiments are marked (new), and manuscript revisions are shown in blue.
W1 and Q1. Relation to TFG-Flow, Discrete Tilt Matching and D-DOIT
We thank the reviewer for highlighting these related works. We have incorporated all three into the revised Related Work section. DiMOS focuses on joint feasibility across multiple biological objectives, combining a coordinate-wise enumerated transition with trajectory search to generate sequences that satisfy several property requirements simultaneously.
TFG-Flow. Lin et al. [1] estimate guided discrete transition rates by weighting clean samples with a target predictor. DiMOS holds a proposed context fixed, enumerates distinct token alternatives at one newly revealed position, and selects using explicit prior-and-value weights. Each candidate is evaluated against the combined multi-objective reward, concentrating candidate evaluations on different choices for the same local decision.
Discrete Tilt Matching. Chen et al. [2] learn the reward-tilted unmasking posterior through a cross-entropy training objective. DiMOS constructs an approximate guided transition at inference time while keeping the pretrained model frozen. New combinations of objectives and feasibility thresholds can therefore be supplied through the reward without retraining the generator.
D-DOIT. The concurrent work of Wu et al. [3] samples candidate next states from a reverse-transition proposal and selects among them using completion-based values. Its optional search branches into independent continuations and selects the best terminal output. DiMOS changes both candidate construction and search allocation. It enumerates distinct tokens within a shared context and repeatedly selects and replicates promising partial trajectories during denoising. This directs subsequent computation toward trajectories with higher estimated joint feasibility.
Controlled Evidence. Appendices N and O examine these contributions through controlled SVDD comparisons. Replacing DiMOS's enumerated candidates with i.i.d. draws reduces joint success by 47.61 and 38.28 percentage points under the soft and hard gates. Transferring DiMOS's search to SVDD improves that baseline, while DiMOS retains a further 35.37- and 35.21-point advantage at comparable generation time. These results support the enumerated local transition and its combination with trajectory search as the algorithmic contributions to multi-objective sequence design.
References
[1] Haowei Lin et al. TFG-Flow: Training-Free Guidance in Multimodal Generative Flow. ICLR, 2025.
[2] Yuyuan Chen et al. Discrete Tilt Matching. ICML, 2026.
[3] Jieke Wu et al. D-DOIT: Training-Free Adaptation of Discrete Diffusion via Doob's h-Transform. arXiv:2610.04938, 2026.