- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes F2S-DLLM, a fast-to-slow thinking framework for multimodal diffusion language models. The method first generates a complete response by unmasking multiple tokens in parallel, then selectively remasks low-confidence tokens for further refinement. The authors also introduce EdgeDrop, which applies noise to regions with complex edge information during the fast stage, while restoring the original image during the slow stage.
The method is evaluated on three multimodal diffusion models—LaViDa, MMaDA, and LLaDA-V—across four multimodal benchmarks. The authors report performance improvements over standard decoding.
Critical strengths
- A practical training-free approach with a fixed denoising budget.
The proposed method redistributes the existing denoising budget between initial generation and selective refinement without additional training or external modules. The ability to refine generated responses without increasing the number of denoising steps is a potentially useful direction for efficient inference-time decoding.
- An interesting perspective on visual conditioning across decoding stages.
Through EdgeDrop, the paper explores the idea that different types of visual information may be beneficial during initial generation and subsequent refinement. Considering the role of visual complexity at different decoding stages, rather than merely modifying the decoding schedule, is an interesting research direction. However, the validity of this hypothesis requires more convincing experimental evidence.
Critical weaknesses
- Insufficient comparisons with existing decoding and refinement methods make it difficult to assess the advantages of the proposed approach.
My primary concern is the very limited comparison with existing methods. Table 1, which presents the main results, compares F2S-DLLM only against standard decoding and its own variant without EdgeDrop. Although Figure 4 includes a comparison with ReMDM, this evaluation is restricted to a single backbone, LaViDa. No direct comparisons with existing decoding or refinement methods are provided for the other two backbones.
In particular, the proposed approach closely resembles existing confidence-based remasking and draft-then-refine strategies. The paper discusses relevant methods, including Speculative Correction, but does not experimentally compare against these directly related approaches. Consequently, it is difficult to determine what meaningful advantages F2S-DLLM provides over existing methods.
Furthermore, the performance improvements on MMaDA and LLaDA-V are relatively modest. EdgeDrop also fails to consistently improve performance across all backbones; on LLaDA-V, the variant without EdgeDrop achieves a higher micro-average score than the complete method.
For a paper proposing a new decoding strategy, relying primarily on comparisons with standard decoding, without sufficient evaluation against strong and directly relevant baselines, is a significant experimental weakness. The current results demonstrate improvements over standard decoding in certain settings but do not convincingly establish the superiority or distinct contribution of the proposed approach over existing methods.
- The claimed fast-to-slow thinking mechanism is not sufficiently distinguished from conventional token refinement, and its effectiveness is not convincingly established.
The authors claim to introduce fast-to-slow thinking, but the proposed method essentially generates a complete response quickly and then remasks low-confidence tokens for refinement. It is unclear how this process fundamentally differs from existing uncertainty-based refinement methods. Moreover, the method applies the same fixed fast/slow schedule to every input, without adaptively adjusting the thinking mode or computational budget according to problem difficulty.
The experiments are also limited to multiple-choice tasks with a maximum generation length of 64 tokens. Many qualitative examples primarily demonstrate corrections to final answer tokens rather than improvements in the underlying reasoning process. Thus, while the results suggest that selective refinement can improve answer accuracy, they do not sufficiently support the stronger claim that the method enables fast-to-slow thinking or improves reasoning capabilities.
There is also a concern regarding a key implementation detail. The authors compute token confidence using the logits from the final fast step. However, at this point, most tokens have already been committed and are included in the model input. It is unclear whether confidence scores for already committed tokens are directly comparable to those for positions that remain masked. This issue could directly affect the validity of the uncertainty-based remasking strategy, which is central to the proposed method.
The motivation behind EdgeDrop is also insufficiently validated. The authors argue that complex visual information can distract fast thinking while benefiting slow thinking. However, the experiments primarily demonstrate differences in final accuracy rather than directly establishing this mechanism. Furthermore, in Figure 2, increasing the remasking budget K also increases the number of denoising steps, making it difficult to distinguish the benefits of selective refinement from those of additional computation.
As a minor presentation issue, the terminology is somewhat inconsistent. Although the paper focuses on multimodal diffusion language models, the proposed method is named F2S-DLLM, and Figure 1 also uses the term DLLM. While DLLM can broadly encompass multimodal models, the distinction between general DLLMs and multimodal DLLMs (dMLLMs) should be made clearer and more consistent, especially since visual conditioning is a central contribution. This is not a major technical flaw, but it makes the scope of the proposed method less precise.
Questions for authors
1.What fundamentally distinguishes F2S-DLLM from existing confidence-based remasking and draft-then-refine approaches? Can the authors provide comparisons with directly related methods, particularly Speculative Correction, under identical model configurations and inference budgets?
2.Why is the comparison with ReMDM restricted to LaViDa? Can the authors provide direct comparisons with established decoding and refinement methods on MMaDA and LLaDA-V as well?
3.How do the authors justify describing the proposed method as fast-to-slow thinking rather than conventional token refinement? Can they provide evidence demonstrating improvements in the actual reasoning process?
4.Are confidence scores for already committed tokens and still-masked tokens directly comparable when computed using the logits from the final fast step? Please clarify how token uncertainty is measured and used for remasking.
5.Why does EdgeDrop provide only limited improvements or even degrade performance on certain backbones? Additionally, can the authors analyze the effect of the remasking budget K under a fixed denoising-step budget?
4 comments
W2/Q4:Confidence Comparability and Remasking Procedure
We compute token uncertainty directly from the logits of the final fast step. For each position , we obtain the predictive distribution and define confidence as . Uncertainty is then ; positions with lower confidence are prioritized for remasking.
To assess whether confidence scores for committed and still-masked positions are directly comparable, we analyzed 100 LaViDA samples and grouped token positions by their state at the start of the final fast step. Of the 64 positions per sample, 60 had been committed and four remained masked. Results are as follows.
| State at last fast step | # positions | Median final-step confidence | Bottom-32 entry rate |
|---|---|---|---|
| Committed | 6,000 | 0.9995 | 46.88% |
| Still masked | 400 | 0.6781 | 96.75% |
| All | 6,400 | 0.9993 | 50.00% |
In the current method, we compute the confidence of each position from the predictive distribution of the last fast step and re-mask the lowest-confidence positions. The results above show that the score distributions of the two kinds of positions indeed differ: still-masked positions enter the slow stage more readily.
To further examine the validity of the current confidence ranking, we compare three selection strategies on the same set of LaViDA samples. Leave-one-out (LOO) masks one position at a time within the complete draft and runs a forward pass to recompute that position's confidence; "re-forward once" performs one additional forward pass after the complete draft is obtained and recomputes the confidence of all positions. All three strategies select the 32 lowest positions for slow refinement.
| Selection strategy | Accuracy | Overlap w/ LOO | Overlap w/ re-forward | Overlap w/ Final-fast | NFE |
|---|---|---|---|---|---|
| LOO | 40.0% | — | 76.81% | 69.56% | 32+64 |
| Re-forward once | 39.0% | 76.81% | — | 78.63% | 33 |
| Final-fast (ours) | 42.0% | 69.56% | 78.63% | — | 32 |
The bottom-32 positions selected by the three methods overlap by 69.56%–78.63%. On these 100 samples, the Final-fast strategy requires no additional forward pass and reaches 42.0% accuracy, whereas LOO and re-forward once reach 40.0% and 39.0%, respectively. This indicates that although the confidences of committed and still-masked positions at the last step are not strictly scores from the same condition, the current ranking still selects useful refinement positions at lower computational cost.
We further examine the four positions that remain masked at the last fast step. Under the current Final-fast logits, 387 of the 400 such positions enter the bottom-32 (96.75%); after the draft is complete, an additional forward pass that recomputes confidence under the full-text condition still selects 316 of them (79.00%).
| How bottom-32 is computed | Entering bottom-32 | Token entry probability | Mean entries per sample | All four entering |
|---|---|---|---|---|
| Final-fast logits | 387/400 | 96.75% | 3.87/4 | 90% |
| Full-draft re-forward | 316/400 | 79.00% | 3.16/4 | 49% |
This shows that the masked state at the last step does raise the probability that these positions enter the bottom-32; yet even when they are re-evaluated uniformly on the complete draft, 79.00% are still selected, so their high entry rate cannot be explained by the masked state alone. We also tabulate the entry rate under the Final-fast strategy by commit time: positions committed at steps 1–4, 5–8, 9–12, and 13–15 enter at 37.50%, 45.44%, 49.69%, and 57.58%, respectively, showing a trend in which later-committed positions are more likely to be re-evaluated. Together with the strategy comparison above, we regard Final-fast confidence as an effective but state-heterogeneous practical ranking signal.
We emphasize that how token uncertainty is computed is not the core contribution of this paper. The current method uses confidence to select re-masked positions; in principle, margin, entropy, and other measures could also serve as candidate uncertainty metrics, but we have not yet compared these selection strategies systematically.
W2/Q3:Reasoning Process
Regarding improvement in the actual reasoning process, Appendix Table 9 shows the complete change from the Fast Thinking draft to the Slow Thinking output on the same samples. These cases change not only the final answer token but also correct the reasoning content preceding the answer. In the tow-truck example, for instance, the fast draft gives contradictory explanations of the direction of force and selects the wrong answer, whereas the slow stage re-assesses the towing relationship and corrects both the reasoning statement and the final answer; other cases similarly show corrections to judgments about vehicle distance, object orientation, and visual attributes. The improvement therefore does not occur only at the answer option, but manifests in the visual judgments and reasoning statements that support the answer.
Table 7 provides quantitative evidence: even under the Original Image condition without EdgeDrop, the slow stage corrects 475 erroneous fast predictions across the four benchmarks while introducing only 161 regressions, a net correction of +314. This indicates that the slow stage brings a substantially positive correction to the fast draft overall. Together, these results show that fast-to-slow decoding changes not only the generated text but also the reasoning performance on the multimodal tasks we evaluate.
To directly test whether slow refinement improves the reasoning text, we sampled 100 examples stratified by domain from the 2,318 M³CoT samples and used GPT-6 Sol to score, along six dimensions, the fast draft and the slow output produced for the same example.
| Stage | Reasoning | Coherence | Grounding | Completeness | Format | Language |
|---|---|---|---|---|---|---|
| Fast draft | 3.17 | 3.34 | 3.08 | 4.11 | 3.51 | 2.59 |
| Refined output | 3.68 | 4.07 | 3.37 | 4.32 | 4.14 | 4.12 |
| Δ | +0.51 | +0.73 | +0.29 | +0.21 | +0.63 | +1.53 |
After slow refinement, the reasoning-correctness score rises from 3.17 to 3.68, logical coherence from 3.34 to 4.07, and evidence grounding from 3.08 to 3.37, while the six-dimension total increases from 19.80 to 23.70. Among the 100 paired comparisons, the refined output is judged overall better in 78 cases and the draft in only 9, with the remaining 13 tied; the gain is significant in all six dimensions under a paired sign test (p<0.001). Together with the case study in Table 9, these results indicate that the benefit of the slow stage is reflected not only in the final answer but also in the quality of the reasoning text.
W2/Q5: EdgeDrop Robustness
To test the robustness of the EdgeDrop increment relative to this ablation variant, we run three independent runs on each of the three backbones.
| Backbone | F2S (w/o ED) | Complete F2S-DLLM | Mean (Δ) | 95% CI of (Δ) |
|---|---|---|---|---|
| LaViDA | 59.67 | 60.10 ± 0.06 | +0.43 | [+0.29, +0.56] |
| MMaDA | 37.40 | 38.65 ± 0.26 | +1.25 | [+0.60, +1.89] |
| LLaDA-V | 66.19 | 65.94 ± 0.14 | −0.25 | [−0.59, +0.09] |
For LaViDA and MMaDA the confidence intervals lie strictly above zero, showing that EdgeDrop, as the visual scheduling component of the complete F2S-DLLM, delivers a stable incremental gain on these two backbones. For LLaDA-V the interval contains zero, so the result indicates that the incremental effect of EdgeDrop is not significant on this backbone; it does not establish a stable degradation.
Existing ablations also show that the effect of EdgeDrop is not caused by generic visual noise. On LaViDA, Table 3 indicates that the gain of the complete F2S-DLLM depends on which visual region is perturbed in the fast stage, and does not merely come from adding noise. Table 7 further shows that the visual condition affects how refinable the draft is. The effect of EdgeDrop therefore need not appear as higher fast-draft accuracy; rather, it makes the state produced by the fast stage more amenable to subsequent slow refinement.
In some samples, temporarily suppressing high-detail regions can reduce the premature influence of local evidence on aggressive parallel decoding, so that the affected content can be re-judged in the slow stage once the original image is restored; if, however, a suppressed region contains evidence needed for the current question, EdgeDrop can also lower the quality of the fast draft. Since different backbones use different visual encoders while we apply the same pixel-level EdgeDrop parameters to all models, the balance between this benefit and the information loss may vary across models. We will expand the discussion of this point in a revised version.
W2/Q5:Fixed-Budget Ablation
We further add an ablation on under a fixed denoising-step budget. The experiment uses LaViDA and evaluates on M³CoT, V*, ScienceQA, and MMBench; the output length is fixed at 64 tokens and EdgeDrop is disabled. All settings share the same 16-step fast draft and perform the same 16-step slow refinement, so the total budget is exactly NFE. The only difference across settings is the number of re-masked positions, .
| M3CoT | V* | SQA-IMG | MMBench | Micro Avg. | |
|---|---|---|---|---|---|
| 8 | 34.51 | 43.46 | 63.66 | 65.93 | 56.70 |
| 16 | 35.29 | 43.46 | 64.85 | 68.38 | 58.37 |
| 24 | 36.54 | 42.93 | 65.69 | 69.62 | 59.49 |
| 32 | 36.32 | 47.12 | 66.14 | 69.72 | 59.67 |
Relative to the shared fast draft, bring micro-average gains of +0.68, +2.36, +3.47, and +3.65 points, respectively. Although individual benchmarks are not strictly monotonic, both Macro and Micro Averages rise consistently with , and performs best within the range evaluated.
Increasing does not increase the number of model forward passes: all settings use exactly 32 NFE, and the average per-sample runtime is comparable (1.83–1.91 s). The performance difference therefore cannot be attributed to more denoising steps. The results show that, under the same forward budget, widening the set of positions re-evaluated in the slow stage improves final performance.
W2:Input-Adaptive
We agree that the current experiments validate a fixed, within-sample fast-to-slow decoding strategy rather than input-adaptive compute allocation. The contribution of this paper is that even without dynamic routing by input difficulty, this within-sample reallocation from rapid parallel generation to selective slow refinement already outperforms standard decoding under the same budget. The current experiments nevertheless cannot show that the model adaptively decides whether to enter the slow stage, or dynamically allocates the slow-stage budget, according to question difficulty. We will therefore state this boundary explicitly in the abstract and introduction. At the same time, deciding dynamically, based on input difficulty or uncertainty, whether to trigger slow refinement and how much refinement budget to allocate is a valuable direction for follow-up work, which we will discuss as future work.
W2: Terminology
We thank the reviewer for pointing out this terminology inconsistency. We fully agree, and will unify the wording of Figure 1 and the main text in the revision, clearly distinguishing general DLLMs from the multimodal dMLLMs studied in this paper.
W1/Q1/Q2:Insufficient comparisons
We thank the reviewer for pointing out the insufficient baseline comparisons and method distinctions. We add comparisons against ReMDM and Speculative Correction (SC) on three backbones and four benchmarks; results are shown in the table above. Under identical evaluation settings, the full F2S achieves Micro Averages of 60.15, 38.36, and 66.06 on LaViDA, MMaDA, and LLaDA-V, respectively, in each case above ReMDM (59.07, 37.19, 65.62) and SC (56.57, 37.21, 64.75). We also report F2S w/o EdgeDrop so that the contributions of the fast-to-slow decoding schedule and of the visual perturbation can be separated.
W2/Q3:Special Contrubition
We call the process "fast-to-slow thinking" because it is inspired by the human cognitive pattern of shifting from rapid judgment to deliberate reasoning: the model first forms a complete preliminary answer quickly and keeps the high-confidence, relatively easy portions, then allocates more fine-grained decoding to the low-confidence portions that may require further reasoning. Our method thus performs a transition from rapid drafting to slow deliberation within a single sample, rather than applying the same decoding granularity throughout generation. Naturally, slow thinking, at the operational level, uses uncertainty-based token refinement, but this is merely a technical means of connecting the fast and slow decoding modes; it is not the entirety of what we propose as fast-to-slow thinking.
Even though all three methods use uncertainty-based token refinement, we differ from ReMDM and SC in both the research problem and the solution.