Parallel Decoding for Diffusion Language Models

Follow this topic Ask about this topic

Latest papers

37 papers11 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Oct 19, 2026

ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting

Block diffusion drafters accelerate speculative decoding by generating multiple draft tokens in a single forward pass. However, each pass produces only a fixed-length block from a single target-generated anchor, limiting how far the draft can extend. Meanwhile, target verification computes hidden states even at positions beyond the first rejection, but these states are typically discarded rather than reused. We propose ReAnchor, a training-free method that reanchors a pretrained drafter at shifted positions using discarded verifier states to generate parallel draft blocks. These blocks improve predictions within the original block and extend coverage beyond its endpoint. At sampling temperature of T=0, ReAnchor achieves its largest average gains on Gemma 4-12B, improving acceptance length by 19.4% and decoding speed by 17.9% across eight benchmarks. Averaged equally over four target models and eight benchmarks, it improves acceptance length by 15.2% and decoding speed by 13.4% with pretrained DFlash drafters.

Sanghyun Lee, Wonjin Nam, Seungho Jang +4

KAIST · Seoul National University

Speculative Decoding Speculative Decoding for Diffusion Language Models Parallel Decoding for Diffusion Language Models Diffusion Language Model Inference Blockwise Diffusion Language Models

Oct 19, 2026

Balance-Aware Pivot Selection for Parallel Diffusion LLM Decoding

Diffusion language models enable parallel token generation, offering a promising alternative to sequential autoregressive decoding. Existing acceleration methods use predictive confidence to enable parallel token commitment while preserving generation quality. However, confidence-based selection prioritizes reliable token predictions without explicitly considering how token positions shape the remaining decoding schedule. Moreover, such ordering does not always reflect inter-token dependencies, suggesting that confidence need not be the sole criterion for token selection. Motivated by this limitation, we propose Balance-Aware Pivot Decoding (BPD), which favors central pivots within contiguous masked intervals and decodes the selected positions in parallel. Balanced pivots yield logarithmic decoding depth in the interval length. Our practical method accounts for model uncertainty by combining confidence-based prefilling with confidence-thresholded center selection. We evaluate the resulting quality-efficiency tradeoff on LLaDA and Dream across five mathematical reasoning, code generation, and instruction-following benchmarks. Our implementation is available at: https://anonymous.4open.science/r/DLM_random_pivot-EE62/

Yejin Lee, Hyundong Jin, Yo-Sub Han

Yonsei University, Seoul, Republic of Korea

Diffusion Language Model Inference Parallel Decoding for Diffusion Language Models Parallel Decoding

Oct 19, 2026

Learning to Couple: Context-Adaptive Joint Denoising for Diffusion Language Models

Diffusion language models accelerate generation by predicting multiple tokens in parallel, but factorized denoisers treat simultaneous predictions as conditionally independent. Decoding heuristics reduce the resulting errors by controlling which tokens are committed, but leave the underlying distribution factorized. Joint modeling addresses the source of the problem, yet existing methods attach separately learned layers to frozen denoisers, leaving the backbone unadapted to the joint objective and the coupling parameters fixed across contexts. We propose Codpula, a context-parameterized denoiser combining a Transformer with a tractable probabilistic inference layer. Given a partially masked input, the Transformer produces token potentials that shape per-position predictions and compact gates that modulate the layer's coupling parameters, yielding a context-dependent joint distribution while retaining exact conditional inference. We jointly optimize both components under a conditional denoising objective using a dual-flow multiplicative update that preserves valid probabilistic parameters. At inference, Codpula supports standard heuristics and uses conditional queries to adapt commitments to dependencies among proposed tokens without extra Transformer evaluations within a step. Codpula sets new state-of-the-art results across a broad suite of reasoning benchmarks while advancing the accuracy-latency Pareto frontier in mathematical reasoning and code generation.

Zilei Shao, Ian Li, Heng Zhao +4

University of California, Los Angeles · University of California, San Diego · University of Virginia +1

Diffusion Language Model Inference Diffusion Language Models Parallel Decoding for Diffusion Language Models

Oct 16, 2026

LED: Improving Masked Diffusion Language Models by Lookahead Editing

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive language models, enabling non-autoregressive text generation through parallel decoding. Existing dLLMs can be broadly categorized into two families: masked diffusion models (MDMs) and uniform diffusion models (UDMs) In this work, we theoretically show that MDMs are easier to optimize due to their mask-based transition schedule but have lower computational expressivity, whereas UDMs enable iterative state revision and greater expressivity but are substantially harder to train. This trade-off raises a natural question: can we obtain the expressivity of iterative revision without giving up the simple, easy-to-optimize transition schedule of MDMs? Motivated by this analysis, we propose Lookahead Editing (\ours{}), which augments masked diffusion decoding with a rewritable proposal state. At each decoding step, the model performs several lookahead updates to iteratively refine future predictions in this proposal state before committing tokens to the masked sequence. This design introduces a rewritable proposal that uses additional compute to improve expressivity while keeping the simple mask-based transition schedule of MDMs. We fine-tune Qwen2.5-7B and Qwen3-8B to obtain LED-7B and LED-8B, respectively. Across eight benchmarks, LED SFT yields average gains of

+11.4

and

+7.7

points over standard MDM SFT. Moreover, using SFT alone, LED-8B outperforms LLaDA2.1-16B Q-mode, which is trained with continued pre-training, supervised fine-tuning, and reinforcement learning.

Yuyan Zhou, Zeyuan Yang, Yuxuan Song +5

Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University +1

Diffusion Language Model Decoding Masked Diffusion Models Parallel Decoding for Diffusion Language Models Diffusion Model Fine-Tuning

Oct 15, 2026

Query-Efficient Rejection Sampling for Parallel Masked Diffusion

Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their correlations and biases the output. Anari et al. (2026) corrected this bias with rejection sampling, decomposing the log acceptance probability into a sum of token-level terms, but the evaluation requires one score query per unmasked token. We propose the Single-Increment Rejection Sampler (SIRS), which provides an estimate of the log acceptance probability from a single randomly sampled increment at the cost of one query. SIRS then converts a Poisson number of clipped estimates into accept/reject decisions through a Bernoulli factory adapted from Chen et al. (2026). Since each query returns the conditionals of all remaining tokens in the block, we further Rao-Blackwellize each increment by averaging over these tokens at no extra cost, thereby reducing clipping. We show that the KL-divergence between the data distribution and the SIRS output is bounded by a clipping term plus the model's training error. With exact scores, parallel decoding pays the full within-block dependence, whereas SIRS pays only the part beyond the clipping range.

Shiyuan Zhang, Xuheng Li, Qiwei Di +1

Department of Computer Science, University of California, Los Angeles, CA 90095, USA

Parallel Decoding for Diffusion Language Models Diffusion Sampling Diffusion Language Model Decoding Masked Diffusion Models

Oct 14, 2026

One Block Ahead: Promoting Sampler State in Diffusion Language Models

Block-diffusion language models denoise a whole block of token positions in parallel so each forward pass can emit many tokens. However, blocks are still denoised in strict sequence, a cost that within-block acceleration leaves untouched. Here, we investigate decoding blocks concurrently and propose One Block Ahead (OBA), a training-free decoding algorithm that denoises the next block alongside the current one. We demonstrate that for uniform-state diffusion LMs, where a block's denoising progress is not visible in its intermediate tokens, concurrent decoding is advantageous if the next block's tokens are promoted together with the corresponding sampler state, including the self-conditioning signal and the denoising time. We also derive a break-even criterion that relates the benefit of OBA to the relative cost of a paired-block forward pass. On DiffusionGemma, a state-of-the-art diffusion LM, OBA increases the tokens per forward pass by 42.3% (from 15.64 to 22.25) and the single-request denoising throughput by 16.3%, averaged over ten benchmarks, with a small accuracy regression.

Yangyi Shen, Pin-Jui Ku, Nicolai Oswald +6

Stanford University · NVIDIA

Parallel Decoding for Diffusion Language Models Diffusion Language Model Decoding Diffusion Model Inference Acceleration Blockwise Diffusion Language Models

Oct 13, 2026

A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs

Parallel generation is widely regarded as an inherent advantage of diffusion large language models. Yet our fixed-quota evaluation of four representative models reveals severe degradation across mathematics and code, with all scores below 15% at 16 tokens per step. Token-level probes identify local predictive potential near the observed prefix, especially in mathematical text. We propose RePara, which reinforces short consecutive token blocks through group-relative policy optimization and reduces rollout and log-probability recomputation costs. On LLaDA and SDAR, \ours improves GSM8K and MATH-500 accuracy over JustGRPO under reduced denoising budgets, with a 1.96x training-step speedup in our LLaDA/MATH setup.

Jiahao Kuang, Yangfan Gao, Tao Gui +4

East China Normal University · Fudan University

Parallel Decoding for Diffusion Language Models Parallel Decoding RL for Diffusion Models Blockwise Diffusion Language Models

Oct 13, 2026

Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models

As generative language models become more capable and widely used, inference demand grows, making efficient serving increasingly important. Discrete diffusion language models (dLLMs) offer a promising path to more efficient inference through parallel token generation. Prior dLLM decoding methods, however, focus on improving inference efficiency for individual sequences. We formulate fixed-budget dLLM batch decoding and introduce Batch-Paced, a training-free method that jointly optimizes the allocation of decoding compute across requests to improve overall batch quality. Across two dLLM backbones, five benchmarks and their representative mixtures, Batch-Paced improves batch performance under matched budgets; gains generally grow with batch size and largely persist across decoding configurations. Analysis of requests' decoding trajectories suggests that these gains arise largely by raising the committed-token confidence of lower-confidence requests. We further show that Batch-Paced's batch decode time remains competitive and that adding a decoding-depth allowance during Batch-Paced decoding can shorten it further at a modest performance cost.

Shuai Zhang, Zhanchao Zhou, Huachuan Qiu +2

Zhejiang University · Westlake University

Diffusion Language Model Decoding Inference-Time Compute Allocation LLM Inference Scheduling Parallel Decoding for Diffusion Language Models

Oct 12, 2026

PIG: Parallel Inconsistency Guidance for Accelerating Diffusion Language Models

Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequential counterparts, which are slow and expensive "oracles" that adhere to the joint distribution of language. In this paper, we propose Parallel Inconsistency Guidance (PIG), a new paradigm that uses a trained auxiliary model to directly estimate the inconsistency between parallel and sequential generation from a single model forward pass. During inference, masked positions are traversed by decreasing confidence, and tokens are added to the parallel decode set one-at-a-time until the total estimated inconsistency between the parallel and sequential generation exceeds a threshold. Surprisingly, it suffices to train a lightweight ~2M parameter auxiliary model on a small mixture drawn from OpenCoder, GSM8K-train, MATH-train, and MBPP-train. For LLaDA-8B Instruct and NemotronDiffusion-3B Instruct, PIG extends the accuracy-TPF frontier on GSM8K, MATH500, MBPP, HumanEval, and MMLU, when compared to the industry standard Fast-dLLM and measures favorably on LLaDA-8B Instruct against DAPD, KLASS, EB-sampler, and other learned unmasking policies.

Quentin Fruytier, Anton Xue, Sanjay Shakkottai +1

The University of Texas at Austin

Parallel Decoding for Diffusion Language Models Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Language Models

Oct 12, 2026

Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models

In parallel decoding, diffusion language models commit several tokens per forward pass, so co-committed tokens cannot see each other, breaking multi-token format units that parsers need. On ECHO, an open-weight one-step chest X-ray (CXR) report generator, 32.7-36.7% of evaluation reports lack a parseable Impression heading and score as empty. We propose intent-triggered anchoring, a training-free decoding rule that completes a format unit once the model commits its first token, inserting only units with a unique, content-free completion; fallbacks write the unit when the model stops or loops without starting it. On three CXR evaluation sets, the rule raises readable rates from 63.3-67.3% to 100.0% with no regressions and a 95th-percentile latency ratio of 0.68-1.28 against official decoding. Broken headings state findings absent from the reference; adding the heading at the end leaves them in 15.5-31.0% of reports, our rule in at most 0.6%. For math answer markers, the rule raises accuracy in the most parallel setting of five diffusion language models by 5.8-20.8 points on GSM8K and 5.1-17.1 on GSM-Symbolic, held out from tuning. With lenient answer extraction, gains are 3.3-12.5 and 2.7-6.3 points; the rule adds 1.4-8.6 points over a stop-only fallback for four of the five models.

Junhyeok Lee, Kyu Sung Choi

Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine · Department of Radiology, Seoul National University Hospital · Department of Radiology, Seoul National University College of Medicine +1

Parallel Decoding for Diffusion Language Models Language Model Decoding Diffusion Language Model Decoding Structured Output Generation

Oct 3, 2026

ALoDLM: Adaptively Looped Diffusion Language Models

Diffusion language models (DLMs) enable fast generation by predicting multiple tokens in parallel, but their practical adoption remains limited by a persistent quality gap relative to comparably sized autoregressive (AR) models. We attribute this gap to a computation-difficulty mismatch: within a partially observed sequence, some unknown tokens are easy to predict, while others require substantially more computation. Existing DLMs nevertheless apply uniform computational depth to all unknown positions at each denoising step. We introduce ALoDLM, which replaces uniform computation with token-adaptive latent recurrence. At each denoising step, ALoDLM iteratively refines latent representations and allocates computation according to token difficulty. Tokens ready to commit are fed back as discrete context, while unresolved tokens retain and further refine their latent states through additional recurrent passes. To learn token prediction and computation allocation jointly, we formulate token-wise computation schedules as latent variables and derive a conditional negative evidence lower bound (NELBO). We train ALoDLM at 1.7B and 8B parameter scales. Across eleven benchmarks, ALoDLM outperforms all evaluated DLMs and the corresponding AR baselines in average benchmark score at both scales. ALoDLM also retains fast parallel decoding, yielding a strong quality-efficiency trade-off among evaluated autoregressive and diffusion models under optimized inference engines.

Liancheng Fang, Zhuowei Li, Youngeun Kim +10

University of Illinois Chicago · Amazon AGI · Korea University

Adaptive Computation for Diffusion Models Diffusion Language Models Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Language Model Training Parallel Decoding for Diffusion Language Models

Sep 29, 2026

Alpha Diffusion Language Models: Factorization Alone Is Not the Problem

Discrete diffusion language models can generate multiple tokens in parallel, but reducing the number of denoising steps can lead to inconsistent predictions. Standard cross-entropy training fits conditional token marginals, whereas parallel generation requires consistent joint predictions. We introduce Alpha Diffusion Language Models (AlphaDLM), trained with a sequence-level alpha loss that recovers cross-entropy in the limit of vanishing alpha and has a joint-mode optimum at alpha one. Our analysis characterizes how the objective and factorization jointly determine the fitted distribution. We identify conditions under which intermediate alpha preserves multiple valid completions while excluding invalid token combinations. Trained on TinyGSM, our method achieves 34.6% accuracy on GSM8K with only four model evaluations. We further scale the method to SDAR-1.7B and evaluate it on code and mathematics benchmarks. These results show that changing the training objective can improve the accuracy-computation trade-off of factorized diffusion language models.

Nikita Gushchin, Dmitry Baranchuk, Alexander Korotin

Applied AI Institute, Moscow, Russia · AXXX, Russia · Yandex Research

Diffusion Language Models Diffusion Language Model Training Diffusion Language Model Decoding Diffusion Language Model Inference Parallel Decoding for Diffusion Language Models LLM Training

Sep 29, 2026

Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models

Diffusion language models (DLMs) enable parallel generation by predicting and committing multiple tokens at each denoising step, yet they can generate individually plausible but mutually inconsistent tokens. Recent work shows that soft tokens can mitigate this issue by representing uncertain positions with continuous embeddings built from the model's predictive distribution at the previous decoding step. However, although soft tokens are commonly understood as preserving predictive uncertainty, how soft-token feedback improves parallel decoding has not been systematically examined. In this paper, we investigate this question in frozen pretrained DLMs to examine soft-token feedback without the effects of additional training. To construct soft-token inputs in a training-free setting, we identify a geometric mismatch between conventional soft-token construction and the pretrained embedding space. Based on this observation, we propose a training-free, geometry-aware construction of soft tokens. Our analysis of soft-token feedback suggests that uncertainty preservation alone does not fully explain how it reshapes subsequent predictions. To better explain how soft-token feedback improves parallel decoding, we provide empirical evidence that it favors coherent token sequences. Across four pretrained DLMs and four math and code benchmarks, our method outperforms standard parallel decoding and a training-free Euclidean soft-token baseline. Code: https://github.com/kodaikawamura/rethinking-soft-tokens

Kodai Kawamura, Kenji Kawaguchi, Anji Liu

National University of Singapore

Language Model Decoding Diffusion Language Model Decoding Diffusion Language Models Parallel Decoding for Diffusion Language Models Parallel Decoding

Sep 29, 2026

Reliable Parallel Decoding in Masked Diffusion Language Models

Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same forward pass are not necessarily reliable when committed together. We study when parallel commitment is reliable. Our diagnostics show that confidence alone does not determine a reliable commitment order: confident predictions near the end of the sequence can fix an answer before its supporting computations are established, and downstream predictions become less reliable as the uncertainty of their upstream context grows. At the same time, a single forward pass can already resolve several masked tokens, and predictions that remain stable across the final layers are more likely to be correct. Based on these findings, we propose Reliable Parallel Decoding (RPD), a training-free method that selects candidates by layerwise prediction stability and final confidence, and commits them under a cumulative entropy budget over their preceding masked positions. RPD defers predictions with uncertain upstream context while committing the remaining candidates in parallel, without relying on a fixed block schedule. Across mathematical reasoning and code generation benchmarks on LLaDA and Dream, RPD achieves the highest decoding throughput among the evaluated methods while maintaining or improving accuracy.

Zhenghao He, Bohan Liu, Guangzhi Xiong +1

Department of Computer Science, University of Virginia

Masked Diffusion Models Diffusion Language Model Decoding Parallel Decoding for Diffusion Language Models

Sep 17, 2026

Parallelism, critical windows, and separations among diffusion language models

A popular selling point of diffusion large language models (dLLMs) is their capacity for parallelism: the ability to generate sequences of text far more efficiently than autoregressive models, which require one forward pass per token. Yet among the many competing paradigms for dLLMs, from masked to uniform to Gaussian diffusion, principled understanding of how these different proposals compare in parallelism remains limited. In this work, we initiate a fine-grained comparison of the capacity for parallelism among these three leading approaches and prove the following: - Uniform and Gaussian diffusion can sample in a number of forward passes which scales with the dual total correlation of the underlying distribution, a measure of intrinsic complexity which can be much smaller than the context length. Previously, it was only known how to achieve this using masked diffusion. - For a certain family of random empirical measures, we show that

\widetildeΘ(\sqrt{d})

forward passes are necessary and sufficient to sample using uniform or Gaussian diffusion, yet there exist approximate score oracles for which

\widetildeΩ(d)

forward passes are needed for masked diffusion. This establishes the first provable separation in parallelism between the three prevailing dLLM paradigms. Contrary to popular intuition that masked diffusions are harder to parallelize because they must commit to token values, the latter separation instead comes from the fact that the critical windows in masked diffusion sampling are asymptotically narrower than those in uniform and Gaussian diffusion sampling.

Sitan Chen, Liye Wang

SEAS, Harvard University · Tsinghua University

Masked Diffusion Models Diffusion Sampling Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Language Models Continuous Diffusion Language Models+1

Aug 14, 2026

CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass. However, existing dLLMs can suffer from unreliable predictions in early denoising stages under aggressive parallelism strategies, leading to errors that can propagate to later stages. To tackle this issue, we present Consistency Forcing (CForce) for dLLMs, a distillation method to force the mask predictions of early stages to align with those of later stages. CForce trains the model on pre-collected self-rollout trajectories, thereby improving training-inference alignment. We introduce Confidence Adaptive KL Divergence as a distillation objective to conjoin the merits of forward and reverse KL. We further provide a theoretical analysis for the consistency objective to explain why CForce can approximately minimize the prediction error of early stages. Critically, the same formulation applies to both mask-to-token decoding and edit-capable decoding; in the edit-capable case, later token-to-token refinements provide additional supervision for earlier masked-state predictions. Experiments on non-edit and edit-capable LLaDA models show improved speed-quality trade-offs, especially under high-parallelism decoding budgets. Code is available at: https://github.com/inclusionAI/dFactory.

Yuji Ren, Chenkai Xu, Zhuocheng Gong +2

Shanghai Jiao Tong University · Ant Group

Parallel Decoding for Diffusion Language Models Diffusion Language Model Decoding Diffusion Language Models Consistency Distillation Diffusion Language Model Distillation

Jul 31, 2026

DiffusionGemma Technical Report

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional autoregressive (AR) large language models. Instead of training from scratch, we obtain DiffusionGemma by fine-tuning the mixture-of-experts Gemma 4 model with 3.8B activated and 25.2B total parameters. Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget. The first stage uses supervised fine-tuning to teach bidirectional denoising, while the second stage combines reinforcement learning with sampler distillation to jointly improve generation quality and inference efficiency. DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. Averaged across our full evaluation suite, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU, which is substantially faster than AR models even with state-of-the-art speculative decoding. DiffusionGemma also retains the starting model's support for thinking mode, multimodal inputs, and long contexts. Despite diffusion fine-tuning, it remains capable of AR generation with only minor performance degradation, suggesting a path toward hybrid diffusion-AR decoding.

DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41

Diffusion Language Model Decoding Blockwise Diffusion Language Models Diffusion Model Fine-Tuning Diffusion Language Models Diffusion Model Inference Acceleration Diffusion Language Model Training+1

Jul 27, 2026

Rethinking the Generation Order of Block Diffusion Language Models

Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs). We show empirically and analytically that these models are naturally more aligned with left-to-right decoding than MDMs. Based on this observation, we propose Parallel Autoregressive Decoding (PARD), a simple training-free sampling method that preserves left-to-right unmasking structure while allowing parallel token commitment. Extensive experiments show that PARD consistently outperforms existing parallel samplers in generation quality, while achieving substantial speedups over pure AR decoding with only a small quality gap.

Kai Syun Hou, James Kwok

Department of Computer Science and Engineering The Hong Kong University of Science and Technology

Diffusion Model Sampling Blockwise Diffusion Language Models Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Parallel Decoding for Diffusion Language Models

Jun 28, 2026

Multi-Block Diffusion Language Models

Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation. A natural next step is to extend them from Single-Block Diffusion (SingleBD) to Multi-Block Diffusion (MultiBD), where a running-set of consecutive blocks is decoded concurrently for inter-block parallelism. However, existing BD-LMs are mostly trained under teacher forcing, where the model observes only one noisy block conditioned on a clean prefix. While the recent diffusion forcing strategy introduces visibility among multiple noisy blocks, its training states still differ from MultiBD inference, where decoding operates on a bounded running-set with heterogeneous slot-wise noise patterns. To bridge this gap, we propose Multi-Block Diffusion Language Models (MBD-LMs), obtained by post-training BD-LMs with Multi-block Teacher Forcing (MultiTF). MultiTF integrates teacher forcing and diffusion forcing by training on bounded noise-groups conditioned on clean prefixes, with randomized noise-schedulers that better match MultiBD inference states. To make MultiBD practically executable, we further introduce an optimized decoding algorithm based on the Block Buffer mechanism that preserves prefix-cache reuse, keeps input shapes static, and translates increased decoding parallelism into wall-clock acceleration. Empirically, MBD-LLaDA2-Mini increases average Tokens Per Forward pass (TPF) from 3.47 to 6.19 and improves average accuracy from 79.95% to 81.03%; when combined with DMax, MBD-LLaDA2-Mini-DMax reaches an average TPF of 9.34 with only a 1.02% accuracy drop on math and code benchmarks.

Yijie Jin, Jiajun Xu, Yuxuan Liu +8

Shanghai Jiao Tong University · Xi’an Jiao Tong University · Huawei

Blockwise Diffusion Language Models Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

Jun 14, 2026

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limits effective parallelism: tokens that appear reliable in isolation can form incompatible configurations when several positions are updated at once. We introduce a training-free decoding framework that coordinates these parallel updates. At each forward pass, the method assigns a commit score to each masked position and refines these scores using pairwise interactions derived from the model's predictive distributions. A variational relaxation yields a simple fixed-point update that suppresses conflicting simultaneous commitments within a single forward pass. This mechanism allows the decoder to commit more tokens in parallel while maintaining competitive generation quality. The method is lightweight, requires no auxiliary model or retraining, and drops into existing diffusion decoding pipelines without modification. Experiments on reasoning and code-generation benchmarks show consistent improvements in the quality-latency trade-off.

Tamim Zoabi, Ameen Ali, Liran Ringel +1

School of Electrical & Computer Engineering Tel Aviv University, Israel · School of Computer Science and AI Tel Aviv University, Israel · Department of Computer Science Technion, Israel Institute of Technology, Israel

Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

Jun 12, 2026

Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens

Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measured. We instrument DiffusionGemma 26B, a masked discrete-diffusion mixture-of-experts model built on Gemma 4, hooking its sampler's accept step to record which canvas positions commit, when, and at what confidence. Across a 686-prompt, six-regime probe suite we find that its decoding is neither parallel nor block-autoregressive: it follows a partial left-to-right commit bias whose apparent strength depends almost entirely on the granularity at which you look. Order is weak token by token and strengthens smoothly as the analysis is coarsened, so the model's "block size" turns out to be an artifact of the measuring ruler rather than the architecture. The model commits in large simultaneous batches, leaving much of the within-batch order genuinely undefined rather than merely unobserved. The behaviour is regime-dependent: structured JSON is committed in essentially arbitrary order, and a position's commit confidence tracks correctness on mathematical reasoning but carries no signal on factual recall. Commitment is aggressive, finishing in a short late burst well inside the step budget, while task accuracy matches the model's autoregressive Gemma-4 sibling. Beyond these findings, our central contribution is methodological: measuring decoding order honestly demands handling trailing-EOS padding, within-regime confounding, commit non-monotonicity, block-size sensitivity, and large commit-batch ties, each of which can otherwise manufacture a decoding-order result that is not really there.

Ali Asaria, Tony Salomone, Deep Gandhi

Transformer Lab

Masked Diffusion Models Diffusion Sampling Diffusion Language Model Decoding Diffusion Language Models Parallel Decoding for Diffusion Language Models

Jun 6, 2026

Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge

Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation quality compared to autoregressive (AR) models. Recent progress attempts to bridge the gap via importance sampling, with DLM being the proposal and AR being the target. However, due to the huge gap between their distributions, the sampling requires a large number of particles and is thus expensive to compute. In this paper, we introduce PoE-Bridge, a novel decoding framework that drastically improves generation speed and accuracy by introducing an intermediate distribution to bridge the gap. The distribution is constructed as a Product-of-Experts (PoE) of the DLM proposal and the AR target. With the intermediate distribution, we first use the DLM to draft multiple continuations in parallel, then apply rejection sampling to verify the drafted tokens and move the resulting candidates toward the PoE. We then use importance sampling to further correct the PoE-aligned candidates toward the AR target. We further propose several improved techniques, including mixed-temperature sampling for enhanced diversity and elastic rejection windows for reducing wasted verification. Empirically, PoE-Bridge achieves significantly improved accuracy with

5\times

speedup over the standard DLM decoding approach, and recovers at least 95% of the target AR model's performance, efficiently advancing most of the quality gap on challenging mathematical reasoning and coding tasks. Our code is available at https://github.com/juntongshi48/poe-bridge.

Juntong Shi, Brian L. Trippe, Jure Leskovec +2

Stanford University

Importance Sampling Product of Experts Speculative Decoding Diffusion Language Model Decoding Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

Jun 2, 2026

Supportive Token Revealing for Fast Diffusion Language Model Decoding

Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Aggressive decoding may commit mutually dependent tokens too early, while conservative decoding requires many denoising steps. Existing methods address this tension by deciding which tokens are safe to reveal using confidence or dependency criteria. However, avoiding unsafe commits does not necessarily make the remaining masked sequence easy to decode, since uncertain tokens may depend on masked tokens, creating a bottleneck for denoising steps. We propose AXON, a training-free module that can be added on top of existing parallel decoding strategies for diffusion language models. Rather than replacing the base decoder, AXON monitors the remaining uncertain masked tokens and intervenes only when their current state suggests that additional context is needed. It then shifts the criterion from which tokens are safest to reveal to which confident reveals would best support later denoising. AXON selects anchors, confident masked tokens that uncertain positions attend to, using attention, uncertainty, and confidence signals. Experiments on reasoning and code-generation benchmarks across multiple diffusion language models show that AXON improves the quality-latency trade-off of existing parallel decoders, often reducing the number of function evaluations while maintaining or improving accuracy.

Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez +4

Department of Computer Science, University of Haifa · Institute for AI, University of Stuttgart · IMPRS-IS

Masked Diffusion Models Diffusion Language Model Decoding Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

Jun 1, 2026

Fast-dLLM++: Fréchet Profile Decoding for Faster Diffusion LLM Inference

Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together. Fast-dLLM addressed this with KV caching and confidence-guided parallel decoding, but its decoding theory uses a homogeneous high-confidence assumption that effectively reduces each candidate set to its weakest selected token. We argue that this leaves speed on the table because real decoding steps exhibit heterogeneous confidence profiles. We propose Fast-dLLM++, a training-free extension that introduces Fréchet profile decoding: selecting parallel commit sets from the full sorted confidence profile rather than a single worst-case confidence. The resulting rule is a heterogeneous-confidence generalization of Fast-dLLM's factor selector and it recovers the previous rule exactly in the equal-confidence case and adds a provable heterogeneity bonus when the selected tokens have uneven confidences. Fast-dLLM++ leaves the model, diffusion process, and cache implementation entirely unchanged, making it a drop-in replacement for existing Fast-dLLM decoding. Experiments on GSM8K, MATH, HumanEval, and MBPP with the LLaDA-8B model show that the theoretical improvement translates directly into empirical gains: profile-aware selection improves the accuracy--throughput frontier by exploiting safe parallelism that weakest-token rules miss, achieving up to 37% higher throughput at comparable accuracy. Our code release is at https://github.com/Ringo-Star/FastdLLM_plusplus.

Siva Rajesh Kasa, Yasong Dai, Sumit Negi +1

Amazon Inc. · School of Computing, Australian National University.

Language Model Decoding Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

May 28, 2026

Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models

Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit this granularity and observe that reliable predictions often emerge as contiguous high-confidence spans, suggesting that the unit of parallel commitment can be larger than a single token. We first group adjacent high-confidence candidates into confidence-induced clusters (CICs) as span-level update units. We then use self-attention maps from the same forward pass to estimate inter-cluster dependencies, enabling conflict-aware selection of mutually compatible CICs for parallel commitment. This yields CLAD (Cluster-Level Attention-Guided Decoding), a training-free cluster-level decoder for MDLMs. Experiments on LLaDA and Dream model families across four reasoning and code-generation benchmarks show that CLAD achieves 1.77x--8.47x speedups over Vanilla decoding while maintaining broadly comparable task accuracy in most settings.

Heqiang Qi, Wei Huang, Mingyuan Bai +1

Zhejiang University · RIKEN Center for Advanced Intelligence Project · The Institute of Statistical Mathematics +1

Masked Diffusion Models Diffusion Language Model Inference Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration+1

May 28, 2026

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding. In practice, however, block-wise dLLM inference exposes a difficult granularity trade-off: small blocks preserve local conditioning but require many denoising steps, whereas large blocks expose more parallelism but can make premature commitments and accumulate cache error. Existing acceleration methods typically choose a single block size per request, leaving the complementarity among block sizes unused. We show that block size itself is a useful branching dimension. Different block sizes induce related but non-identical KV-cache trajectories: branches often share an initial prefix, bifurcate at semantically decisive positions, and later agree on syntactically lightweight tokens. Motivated by this structure, we propose BlockBatch, a training-free online inference framework that executes multiple block-size branches for the same request inside a batched forward pass. BlockBatch coordinates these branches through confidence-gated token merging, leader-based synchronization, and periodic full-sequence refreshes that re-anchor local block updates to a globally consistent KV state. Across 3 representative dLLMs and 4 datasets, BlockBatch reduces denoising NFEs by 26.6% on average and achieves a 1.33

\times

average end-to-end speedup over Fast-dLLM while preserving accuracy. These results identify block-size diversity as a practical and previously underexplored axis for branch-parallel dLLM inference.

Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji +2

Georgia Institute of Technology

Blockwise Diffusion Language Models Diffusion Language Model Inference Diffusion Language Model Decoding Parallel Decoding for Diffusion Language Models Parallel LLM Inference

May 27, 2026

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM

Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms. However, their computational complexity scales on the order of L cubed with the sequence length L. This poses significant challenges for long-sequence and real-time applications, primarily due to the lack of compatibility with key-value caching and the non-autoregressive nature of denoising steps. Existing acceleration methods rely on static caching or parallel decoding strategies, which fail to account for the dynamic behavior of token properties across layers and decoding steps. We propose Dynamic-dLLM, a training-free framework that enhances dLLM inference efficiency through two components: Dynamic Cache Updating (DCU), which adaptively allocates cache-update budgets based on layer-wise token dynamics, and Adaptive Parallel Decoding (APD), which dynamically calibrates decoding thresholds to balance generation quality and efficiency. Extensive experiments on models like LLaDA-8B-Instruct, LLaDA-1.5, and Dream-v0-7B-Instruct across benchmarks such as MMLU, GSM8K, and HumanEval demonstrate that Dynamic-dLLM significantly improves inference speed. It attains an average speedup exceeding 3 times while maintaining performance. Dynamic-dLLM outperforms state-of-the-art acceleration methods and provides a plug-and-play solution for efficient dLLM deployment without compromising performance. The code is available at https://github.com/TianyiWu233/DYNAMIC-DLLM.

Tianyi Wu, Xiaoxi Sun, Yanhua Jiao +5

*Equal contribution. The work is done during Tianyi’s internship at CBG Celia DeviceAI Team, Huawei. · 1Harbin Institute of Technology, Shenzhen · 2Huawei +1

Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Model Inference Acceleration Parallel Decoding for Diffusion Language Models

May 15, 2026

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding

Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes inference expensive. This cost can be reduced spatially by unmasking multiple tokens per step, or temporally by collapsing multiple denoising steps into one verification call. We propose Parallel Speculative Decoding (PSD), a training-free framework that jointly improves inference along both axes. Using the confidence scores from a single forward pass, PSD selects positions to unmask via a configurable, adaptive unmasking policy and constructs multi-depth speculative drafts without extra model calls. A final batched verification pass then applies hierarchical acceptance, keeping the deepest draft that remains consistent with the updated predictions. Experiments on three dLLMs across reasoning and code generation tasks show that PSD achieves favorable trade-offs between inference efficiency and generation quality, reaching up to

5.5\times

tokens per forward pass with accuracy comparable to greedy decoding.

Shengyin Sun, Yiming Li, Renxi Liu +7

Department of Computer Science City University of Hong Kong · Huawei Technologies · City University of Hong Kong

Parallel Speculative Decoding Masked Diffusion Models Speculative Decoding for Diffusion Language Models Speculative Decoding Diffusion Language Model Inference Diffusion Language Model Decoding+3

May 12, 2026

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequential nature of standard autoregressive decoding represents a fundamental bottleneck for high-throughput inference. While diffusion language models attempt to break this barrier via parallel generation, they suffer from significant performance degradation, high training costs, and a lack of rigorous convergence guarantees. Orthrus resolves this dichotomy natively. Designed to seamlessly integrate into existing Transformers, the framework augments a frozen LLM with a lightweight, trainable module to create a parallel diffusion view alongside the standard autoregressive view. In this unified system, both views attend to the exact same high-fidelity Key-Value (KV) cache; the autoregressive head executes context pre-filling to construct accurate KV representations, while the diffusion head executes parallel generation. By employing an exact consensus mechanism between the two views, Orthrus guarantees lossless inference, delivering up to a 7.8x speedup with only an O(1) memory cache overhead and minimal parameter additions.

Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham +3

University of Oregon · Google DeepMind · Adobe Research

Language Model Decoding Diffusion Language Model Inference LLM Inference Acceleration Diffusion Language Model Decoding Parallel Decoding for Diffusion Language Models

May 10, 2026

Edit-Based Refinement for Parallel Masked Diffusion Language Models

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a mismatch between token-level training objectives and joint sequence consistency. In this paper, we propose ME-DLM, an edit-based refinement framework that augments diffusion generation with lightweight post-editing steps. After producing an initial complete response, the model refines it through minimal edit operations, including replacement, deletion, and insertion, conditioned on the full sequence. Training supervision is derived from edit distance, providing a deterministic signal under a fixed canonicalization scheme for learning minimal corrections. This approach encourages sequence-level consistency through globally conditioned edits while preserving the efficiency benefits of parallel diffusion decoding. Extensive experiments demonstrate that ME-DLM improves the quality and robustness of multi-token parallel generation. In particular, when built upon LLaDA, our method achieves consistent gains of 11.6 points on HumanEval and 33.6 points on GSM8K while using one-eighth of the total diffusion steps. Code is available at https://github.com/renhouxing/ME-DLM.

Houxing Ren, Mingjie Zhan, Zimu Lu +5

CUHK MMLab · SenseTime Research · Shenzhen Loop Area Institute +1

Masked Diffusion Models Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Text Generation+1