- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposed the travel-optimal sampler for few-step generation by seeking probability flux with minimal total travel cost. The theoretical error analysis is presented, and the experimental results show that the proposed method is effective and competitive.
Critical strengths
- The proposed sampler is novel and can be obtained by optimizing the generating flux. The flux can be freely designed under the detailed balance condition (Lemma 1).
- The theoretical error analysis of the proposed sampler is derived.
- The experimental results are promising, demonstrating that the proposed sampler is effective.
Critical weaknesses
- There are some quantities appearing for the first time without definition or sufficient explanation, such as in line 262. Additionally, the sentence in line 309 is incomplete; Proposition 1 just appears in the main paper without discussion.
- There are no comparison results with other samplers (beyond AVE and corrected samplers proposed by Wan et al. ), such as higher-order samplers proposed by Ren et al. (2026). The results with other models like FUDOKI seem to be limited.
Questions for authors
- Could the authors explain the relationship between the results in Section 4.2 and the results in Shaul et al. (2025)?
- How should we analyze the theoretical results in the paper compared to existing works, such as Wan et al. (2026) mentioned in the paper? Is the proposed sampler better than other samplers theoretically (some discussion is welcome)?
- In experiments, I noticed that the proposed method achieves the best performance among the selected competing samplers for image generation with URSA. I am also curious about the experimental results of the proposed method compared with higher-order discrete samplers proposed by Ren et al. (2026). Also, more results (for comparison between the proposed method and competing samplers beyond AVE) for other models like FUDOKI could strengthen the evidence for the effectiveness of the proposed method. I think some metric (e.g., GenEval) vs. sampling time figures would be helpful for readers to identify the performance of the method.
3 comments
Thank you for your additional discussion and results, which addresses my main concerns. I will raise my score to 4.
Thanks !
Thank you for the follow-up. We are glad the additional results were helpful, and appreciate your thoughtful feedback throughout the discussion. Please feel free to let us know if there is anything further.
Response to Reviewer hQjF
We thank the reviewer for the positive evaluation and constructive feedback, and for recognizing the novelty of the sampler, the error analysis, and the experimental results. We address the comments below.
[W1] Notation and presentation. We thank the reviewer for the careful reading. In the revision, we refer back to the definition of â (Section 2.2) where it is used in Section 4.3, and complete the sentence introducing Proposition 1. We have also checked the remaining notation throughout the paper.
[W2,Q3] Comparison with other samplers and results on FUDOKI. Please see G1 for the comparison with the high-order sampler of Ren et al. and G2 for the extended FUDOKI comparison against AVE, Corr-T, Corr-L, and RK-2.
[Q1] Relation to the kinetic-optimal (KO) flux of Shaul et al. (2025). We thank the reviewer for this question. The difference from KO is central to our contribution, so we explain it in detail. Both KO and TO choose a flux among the many that generate the same probability path, but they optimize different objectives, and this leads to different behavior. For a current token b and target a, with dˉt(a)=∑b′pt(b′∣a)d(b′,a), the two compare as follows.
Objective. KO minimizes a quadratic (kinetic) cost. Under a quadratic cost it is cheaper to spread the flux thinly over many transitions, so mass is often routed through intermediate tokens, which creates jumps that are not needed to realize the path. TO minimizes a linear transport cost. Since c is a metric, a detour can never reduce the cost, and sending mass directly to its destination is optimal. We also note that the weight wt in KO serves mainly to make the objective symmetric, rather than to encode a semantic distance between tokens, whereas c in TO is the distance itself.
Jump intensity. In KO the expectation over b′ sits outside the ReLU, while in TO it sits inside. As a result, under TO only tokens whose probability is decreasing emit mass, and mass flows only to tokens whose probability is increasing. Under KO, a token can emit mass even when its own probability is not decreasing, as long as some b′ is closer to the target.
Destination. In KO, the current token b affects the destination only through the scalar d(b,a), so a jump goes to any token near the target regardless of where b is. TO multiplies in a locality kernel e−c(b,b′)/ε, so mass moves toward tokens that are close to the target and also not far from the current token. This is the locality-aware property that Reviewer 2gYT also highlighted.
We have added this comparison to Appendix E.
[Q2] Theoretical comparison with prior work. We would like to highlight two differences.
Comparison with Wan et al. (2026). Prior analyses, including Wan et al., mostly consider the uniform and masked paths common in discrete diffusion. As discussed in our response to Reviewer BUms (W2), in these paths the flux either leaves or arrives at a single state, so the OT coupling is unique and the default rate is already travel-optimal. Since there is no room to improve the rate itself, these works naturally focus on improving the integrator for a fixed rate. In contrast, we show that for more general paths, where both the source and the destination of the flux are spread over many states (the metric path being the main example), the choice of rate becomes a substantial degree of freedom, and that optimizing it further reduces the finite-step error. The two directions are complementary, as the combination with RK-2 in G1 also shows.
Comparison with KO (Shaul et al., 2025). Our bound on the finite-step error (Theorem 2) is quite loose, but its constants Hk and ℓk do not depend on the choice of rate. The rate enters only through the jump intensity and the travel cost. Our rate attains the minimal jump intensity in closed form and approximately minimizes the travel cost, so both rate-dependent terms are no larger than those of KO. Since these terms do not depend on the integrator, the comparison is not tied to AVE and carries over when our rate is combined with other integrators.
We have added this discussion to Appendix A.
[Q3] Higher-order samplers, FUDOKI, and sampling time. Please see G1, G2, and G3. The plot of GenEval against wall-clock time is in Figure 7 (Appendix F.4).