- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This work proposes the method PIG. It decides which masked positions a diffusion LM commits in parallel by predicting sequential–parallel inconsistency: whether a parallel commit would differ from one-at-a-time greedy decoding. An approx 2M-parameter adapter on the frozen backbone predicts pairwise entropy finite differences from one forward pass.
Offline tables, fitted by sequential replay on GSM8K-train and OpenCoder, turn confidence plus aggregate coupling into a mismatch probability. PIG.INT commits the confidence-ordered prefix whose summed risk stays less than . PIG.EXT widens the round until the predicted benefit of waiting exceeds . On LLaDA-8B-Instruct and Nemotron-Diffusion-3B (GSM8K, MATH-500, MBPP, HumanEval; MMLU on Nemotron), PIG improves the accuracy vs tokens-per-forward (TPF) frontier over confidence thresholding, most at high parallelism.
Critical strengths
-
Large gains over confidence thresholding at high parallelism, under a paired, fully tabulated protocol. For example, at 10 TPF on LLaDA PIG.INT gains +19.1 points on GSM8K and +11.4 on MATH-500, and on Nemotron PIG.EXT gains +27.8 on MBPP at 5 TPF (Table 2). These gaps are well outside the reported Wilson intervals.
-
The mismatch estimate is validated during live decoding. Realized/predicted mismatch is 0.83–0.92, and realized per-round regret never exceeds 0.91φ (App. D.4).
Critical weaknesses
-
In my understanding, the gains are not shown or cant be attributed to come from the learned predictor.
- The coupling (Eq. 5) sums non-negative terms over every admitted token, so the table's coupling axis partly just tracks how many tokens are already in the round.
- The only adapter ablation measures estimator quality (Fig. 6), not decoding. No confidence-only cumulative budget is tested, and EB-Sampler is not swept on the same setup.
- So the improvement over Fast-dLLM may come from the cumulative-budget rule rather than the adapter. The other baselines don't settle this:
- EB-Sampler and KLASS are single cells copied from a setup whose Fast-dLLM is 4-14 points weaker (App. D.7).
- DAPD is a single-schedule re-implementation about 12 points below its published HumanEval accuracy (App. D.5).
- DEMASK is not compared.
-
"Acceleration" is measured only in TPF, and the headline claims exceed the paper's own tables.
- There are no wall-clock results, although the adapter adds 12.8 ms per round (App. B). LLaDA TPF also counts EOS padding.
- "PIG helps globally on the whole frontier" (Sec. 5) is contradicted by Nemotron GSM8K. There, Fast-dLLM's 0.896 at 2.56 TPF beats PIG.INT's 0.854 at 2.52 (Table 8).
- The headline drops to if the MBPP reference moves by one problem (0.396 vs 0.394, Table 6). Some "matched-accuracy" ratios are taken at lower accuracy (HumanEval at points).
Questions for authors
I have the following questions for the authors.
- What is the decoding frontier for PIG.INT with a confidence-only table (refitted), and for EB-Sampler/KLASS swept on your setup? If these match PIG.INT, then i think that the adapter cannnot be the source of the gains.
- I am curious what is the end-to-end wall-clock time at matched accuracy vs Fast-dLLM, including adapter, attention-map extraction and selection? What is LLaDA TPF excluding padding?
- If i understnad correctly, Prop. A.8 is no tighter than the trivial bound for , which covers most of the LLaDA sweep. Its non-negativity premise also fails for the deployed (Fig. 10: 0.138 vs 0.287). Can you give a non-vacuous version, or scope the guarantee claims?
- Algorithm 2 returns when the top candidate's risk exceeds (e.g. , Fig. 8). Is the first token force-committed, and does Prop. A.4 still hold?
Minor:
- Nemotron BL=64 results (Table 2, Fig. 5) are not tabulated.
- App. B.1 says "nine" scalar inputs but lists eight, and "" is arithmetically wrong.
- is Sec. 3's ordering condition is reversed?
8 comments
[W2] Measure of acceleration
We next justify our metrics for acceleration and break W2 down into the following points:
[W2.1, Q2] Wall-clock.
Prompted by your review, we timed every operating point of every lane on LLaDA-8B-Instruct, with 64-token blocks, a 256-token canvas and batch size 1, on one H100 GPU with no other process (10 problems per point). Per round, PIG adds 4.0–4.3 ms for the adapter and 0.2–0.7 ms for the selection. That is a 9–10% wall-clock overhead against native selection. However, since the adapter's arithmetic is under 0.1% of a backbone forward (≈0.6 GMAC per round); the measured ~4 ms is dominated by kernel-launch latency in our unoptimised fp32, eager-mode implementation, so a fused implementation (e.g., CUDA graphs, bf16, selection on the GPU) should reduce the overhead further.
Therefore, further optimising PIG's feature extraction and selection code would reduce the overhead. In fact, preliminary experiment suggests that halving the adapter size would still maintain performance:
| adapter | parameters | per-edge correlation | aggregate coupling correlation |
|---|---|---|---|
| width 96 | 0.95M | 0.76–0.80 | 0.93–0.97 |
| width 192 (paper) | 2.17M | 0.76–0.81 | 0.92–0.97 |
We will include further discussion of this in the revision. We also provide an accuracy-TPF frontier plot without padding calculated as (256 - Number of Pads) / Number of Forwards (see Fig 24 App. F). Our findings suggests that excluding pads does not alter our claims, as the inclusion of pads would have affected every baseline anyways.
[W2.2] Contradictory claims.
Our statement is not contradictory because we do not claim best performance at every configuration. However, thank you for pointing out an opportunity to improve clarity, and we will update the wording accordingly: "PIG improves the frontier at medium and high parallelism, with the largest gains as decoding becomes more parallel."
[W2.3] The 1.7× headline and matched accuracy.
The reporting is due to the granularity of our hyperparameter sweeps, which either matches or is finer than existing baselines. In more detail, Table 1 reports the fastest measured PIG cell whose accuracy reaches the baseline's most accurate cell (App. D.7). This is the same matched-accuracy speed-up convention as Fast-dLLM, EB-Sampler, and KLASS. This is why we additionally report full accuracy–TPF frontiers (Fig. 5, App. E) rather than single operating points.
[Q1] confidence-only table, EB-Sampler and KLASS on our setup.
Prompted by your review, we ran on LLaDA-8B-Instruct with 64-token blocks (Fig. 16's setting), on all four benchmarks:
- PIG.INT with its table collapsed onto confidence;
- the training-free unconfidence budget;
- EB-Sampler and KLASS, both swept;
Results are in Fig 23 App. F for convenience.
We also provide an accuracy-TPF frontier plot without padding calculated as (256 - Number of Pads) / Number of Forwards (see Fig 24 App. F).
[Q3] Theoretical analysis.
We will scope the claim to clarify that the theorem is intended to be non-vacuous for . More broadly, Prop. A.8. is intended to provide coarse regret scaling laws over the decode trajectory, and so may not have interpretations at all thresholds. We'd also like to point that our depth of theoretical analysis is rare compared to related works, and regret-based dynamics are notoriously difficult to analyze even with significant assumptions.
[Q4] The first candidate.
Yes, the most confident candidate is always committed, to ensure progress. Prop. A.4 still holds because that token's inconsistency is exactly zero: the sequential reference's first step reads the same canvas, so and is unchanged. We will correct Algorithm 2 to initialise . Thank you for pointing out this opportunity to improve clarity.
Minor Fixes
Thank you for noticing these, all fixed in the revision:
- Nemotron BL=64 frontier tables are added.
- App. B.1: nine scalars is correct, but the structural class is four-way (decoded, committable, outside the active block, canvas boundary), and the list now says so.
- "≈232×24" becomes "≈136×24 ≈ 3,300", since there are 136 eligible receivers per state on average.
- The ordering condition in Sec. 3 now reads .
References
[1] Wu et al., “Fast-dllm: Training-free acceleration of diffusion llm by enabling kv cache and parallel decoding” (ICLR 2026).
[2] Ben-Hamu et al., “Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking”, NeurIPS 2026. (Notes: EB-Sampler)
[3] Kim et al., “KLASS: KL-Guided Fast Inference in Masked Diffusion Models”, NeurIPS 2025.
[4] Kim et al., “DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs”, ICML 2026.
[5] Jazbec et al. “Learning unmasking policies for diffusion language models”, ICML 2026.
Thank you for the detailed rebuttal and for the considerable effort behind the new experiments. I appreciate that Fig. 23 now includes the ablation I asked for, along with EB-Sampler and KLASS run in your own harness. It answers my main question: the adapter does contribute on GSM8K and MATH-500 at high parallelism. Fig. 24 also settles my concern about padding, and the clarification on the first candidate in Algorithm 2 is correct.
Also at this stage (closer to deadline), I am not asking for any new experiments. I would only appreciate it if you could clarify the remaining concerns below, which are about the existing results, the claims in the text, and the theory.
-
First, Fig. 23 also shows that a large share of the improvement comes from the training-free budget itself. On GSM8K at 10 TPF, the confidence-only table already recovers roughly 70% of PIG.INT's gain over Fast-dLLM, and on HumanEval it matches PIG.INT. I think the paper's framing should reflect this. I was also unsure about the "knapsack refinement" label on the PIG.INT cells in Fig. 23/24, since Sec. 4.1, Algorithm 2, App. D.4 and
pig/rules.pyall describe a prefix walk that stops at the first candidate exceeding . Could you confirm whether this is a labelling error? -
On acceleration, if i undertand correctly, the reported 9-10% per-round overhead means the matched-accuracy ratios in Table 1 translate to only about - in wall-clock time on GSM8K and MATH-500. The headline rests on a one-problem difference in the reference (198 vs 197 of 500). The revised wording is still contradicted by Nemotron GSM8K (Tables 2 and 8), and Table 1 and the abstract still rely on the copied EB-Sampler and KLASS numbers. I would really appreciate your view on how these claims will be stated in the revision.
-
For theory, restricting Prop. A.8 to does not quite resolve the issue. The bound is still no better than at , and its non-negativity premise does not hold for the deployed (Fig. 10). The revised D.4 also says both quantities exceed at every point, while reporting 0.99-2.00 at . Could you kindlyy clarify how the guarantee should be read for the deployed decoder? Finally, the Nemotron BL=64 tables mentioned in the rebuttal do not yet appear in the revision.
We sincerely appreciate the reviewer's careful evaluation and constructive feedback.
In response, we conducted the following additional experiments:
We would be happy to clarify any remaining questions and make every effort to conduct additional experiments if needed. The code is also provided to ensure reproducibility of our results and overall soundness of the paper.
To ground discussion, we first note references to Fast-dLLM [1], EB-Sampler [2], KLASS [3], and DAPD [4].
[W1] Effect of learned predictor
We justify that the gains can be attributed to the learned predictor in the following points.
[W1.1] Does the coupling just count tokens?
We wish to clarify that the table's coupling axis does not track how many tokens are already in the round. μ^i(S) aggregates the estimated first-order effect of each member of S on token i. At most, the total number of tokens in a round can only track this in expectation. In Section 4.1 of the paper, we explain that inconsistency is governed by the slack in the top-1 vs top-2 predicted probabilities and by the size of the perturbation S applies to it. Our feature μ^i(S) approximates this total perturbation up to first order and is therefore relevant to the regret estimation.
[W1.2] No confidence-only cumulative budget, estimator-only ablations.
There are many ablations that are highly relevant to decoding, including Fig 6. Specifically:
These give fine-grained analyses of decoding performance beyond surface-level accuracy or TPF metrics.
For this rebuttal, we have also added comparisons against EB-Sampler and KLASS sweeps, and a training-free PIG that runs the PIG.INT walk with inconsistency estimated as one minus confidence, and we have also run experiments with inconsistency measured from confidence alone.
We have updated the manuscript to show these in Fig 23 App. F. Notably, the training free PIG matches or slightly edges out against EB-Sampler (runs under our harness, code cloned from DAPD’s repo).
[W1.3] Baselines.
Our results in [W1.1] and [W1.2] show that the gains come from both the adapter and the cumulative budget rule: both components contribute.
Moreover, our implementation is sound: our harness matches Fast-dLLM's and our numbers are consistent with Jazbec et al. (ICML 2026 oral), and our EB-Sampler, KLASS, and DAPD evaluations used DAPD's released codebase. We suspect the gap in DAPD's reported HumanEval numbers is attributable to sensitivity to attention patterns, possibly due to different prompt setups. Finally, DEMASK does not have a public implementation.
References
[1] Wu et al., “Fast-dllm: Training-free acceleration of diffusion llm by enabling kv cache and parallel decoding” (ICLR 2026).
[2] Ben-Hamu et al., “Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking”, NeurIPS 2026. (Notes: EB-Sampler)
[3] Kim et al., “KLASS: KL-Guided Fast Inference in Masked Diffusion Models”, NeurIPS 2025.
[4] Kim et al., “DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs”, ICML 2026.
[5] Jazbec et al. “Learning unmasking policies for diffusion language models”, ICML 2026.