Diffusion Language Model Decoding

Follow this topic Ask about this topic

Momentum

26 papers in the last four weeks, up 271% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 164

Oct 8, 2026cs.AR

DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution

Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinement, alleviating the sequential decoding bottleneck of AR generation. However, their parallel iterative refinement mismatches AR accelerators optimized for sequential decoding and their discrete token generation differs from DiT accelerators designed for continuous denoising. Recent dLLM accelerators have explored workload-specific optimizations to reduce vocabulary processing overhead and redundant computation across denoising iterations. However, these approaches retain all tokens in parallel execution, despite varying token refinement utility and execution requirements. This paper presents DynaTE, a hardware--software co-design architecture that dynamically adapts accelerator execution to evolving token states during dLLM decoding. DynaTE first enables adaptive token execution by skipping low-utility token computation, while a dimension-reconfigurable PE array maintains high utilization under varying active-token patterns. Second, DynaTE exploits dynamic token dependencies through FLDD to refine a small number of locally dependent tokens within the current iteration, reducing the overall number of denoising iterations, while a Merge--Split--Merge dataflow hides the resulting serial overhead. Third, a streaming vocabulary engine interleaves multiple token streams from the LM head to accommodate irregular output variations caused by selective token computation and uneven vocabulary-selection demands. Evaluated on two representative dLLMs, DynaTE achieves 2.05--2.78

\times

speedup and 2.99--3.93

\times

higher energy efficiency over state-of-the-art dLLM accelerators, while delivering 2.55

\times

speedup and 6.07

\times

higher energy efficiency over Jetson AGX Orin.

Minghan Jiang, Jiayi Wang, Shuaiting Li +2

College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou 310027, China

AI Accelerator Inference Diffusion Language Model Inference Diffusion Language Model Decoding Hardware-Software Co-Design

Oct 6, 2026cs.IR

Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval

Generative retrieval trains a language model to generate the identifier of a relevant document. Recent work replaces the autoregressive decoder with diffusion, but changes identifiers, training recipe and decoding at once, so differences cannot be credited to the paradigm. On NQ320K and MS300K, we train autoregressive, masked-diffusion and block-diffusion models with residual-quantised, product-quantised and random identifiers. With identifier length and training budget fixed, we decode each model in several ways. Decoding alone moves a diffusion model's Hit@1 by 6.6 to 13.7 points. Our reference diffusion decoding, generate-and-match, generates an identifier, then retrieves the closest corpus identifiers. The generated identifier is right for 14-21% of NQ320K queries. We test one-pass scoring to decode diffusion retrievers: the model reads a fully masked identifier once, and each document is scored by its codes' probabilities. It matches or beats generate-and-match in 11 of 12 settings. Autoregressive models still lead in Hit@1; on NQ320K, the lead comes from the model, not beam search. Starting from one sampled identifier, one-pass scoring removes 46-83% of masked diffusion's deficit to beam search; from generate-and-match, at most a quarter. On NQ320K, every paradigm largely memorises which identifier answers which query: random identifiers keep 83-90% of the Hit@1 of residual-quantised ones. There, product-quantised identifiers lead residual-quantised ones by 3.4 points in the autoregressive model and by -0.7 to +3.6 in diffusion models; across decodings, AR's gap exceeds diffusion's by 1.5-2.3 points, around our 2-point threshold. Paradigm comparisons must report each paradigm at its own recipe and best decoding.

Hicham Randrianarivo, Logan Renaud, Alexia Allal

Artefact Research Center France

Generative Retrieval Memorization in Generative Models Diffusion Language Model Decoding

Oct 5, 2026cs.CL

D-Loop: Looped Diffusion Drafting for Speculative Decoding

Block diffusion accelerates speculative decoding by drafting multiple tokens in one forward pass. However, each position predicts a marginal distribution without observing earlier proposed tokens, limiting draft quality and acceptance length. We identify a concrete failure, the \emph{repetition trap}, in which neighboring positions produce redundant copies of the same token. We explain this tendency theoretically and empirically examine its association with shorter accepted drafts. Recent methods refine marginal predictions with an additional causal head or a separately trained drafter, increasing parameter storage and introducing separate training objectives. We instead propose D-Loop, which introduces \emph{intra-block causal conditioning} within the original diffusion drafter without additional model components. Inspired by semi-autoregressive generation and parameter sharing, D-Loop reuses the same backbone across looped passes. The first pass proposes a block, and the second conditions on a selected prefix to regenerate the suffix in parallel. A complementary prefix--suffix objective trains the shared drafter for both anchor-only prefix prediction and prefix-conditioned suffix prediction. Across eight math, code, and chat benchmarks, D-Loop can beat DFlash and DSpark on Qwen3-4B and Qwen3-8B with obvious gains.

Kecheng Chen, Yuyang He, Cheng Gong +8

City University of Hong Kong · The Chinese University of Hong Kong · Huawei Research

Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding Diffusion Language Models

Oct 4, 2026cs.LG

Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models

Masked Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked tokens with model predictions. At each denoising step, the decoder chooses which positions are sufficiently confident to commit. Existing decoding methods typically rely on softmax confidence, which can be miscalibrated. We introduce BayesER (BAYESian Entropy-based Reordering), a post-hoc Bayesian decoding framework that uses predictive uncertainty to guide token commitment. In BayesER, we construct a lightweight approximate posterior centered at the pretrained checkpoint, similar to Laplace-LoRA but without training LoRA adapters. We average predictions over posterior samples and use predictive entropy to prioritize reliable positions. We examine how posterior predictions affect position ordering and token selection across benchmarks spanning code generation, mathematical reasoning, planning, and molecular generation. We show that BayesER reduces sequence-level calibration error while preserving or improving accuracy relative to common decoding schemes, including confidence-threshold decoding. Additionally, a posterior fitted on one code-generation dataset reduces calibration error on another without refitting, suggesting that Bayesian uncertainty may provide a transferable signal for more reliable MDLM decoding.

Zhejun Jiang, Mijung Park

The University of British Columbia

Confidence Estimation in Language Models Bayesian Inference Language Model Calibration Diffusion Language Model Decoding

Oct 1, 2026cs.CL

Hierarchical Continuous Diffusion Language Models

Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global constraint satisfaction. Yet they share a structural bottleneck: when decoding in parallel, each token is sampled independently from its marginal, severing the statistical dependencies among the tokens decoded together. Continuous diffusion language models avoid this by denoising a shared continuous state, but their denoiser sees only that state, so nothing ties it to a valid token configuration until it is finally decoded. To address this, we propose Hierarchical Continuous Diffusion Language Models (HC-DLM), which couple discrete token generation with a continuous latent trajectory in a single, principled denoising process, whose training objective is derived from a variational bound on the token likelihood. In contrast to recent methods that attach continuous context to a self-contained discrete chain, HC-DLM makes the latent the only persistent generative state: tokens are read out from it at every step and feed back as a scaffold for the next latent update. On structured reasoning (Sudoku), mathematical planning (Countdown) and language modeling (LM1B), HC-DLM improves over discrete and continuous diffusion baselines at matched model size, in puzzle accuracy on Sudoku and Countdown and in generative perplexity on LM1B. Project page: https://hc-dlm.github.io/.

Hui Ren, Zihan Li, Chang Liu +2

University of Illinois Urbana-Champaign · Amazon.com, Inc.

Diffusion Language Model Decoding Diffusion Language Models Continuous Diffusion Language Models

Oct 1, 2026cs.CL

Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models

Uniform-state diffusion models (USDMs) can revise any token at any denoising step, which lets them correct their own mistakes, a key advantage over masked diffusion. Self-correction, however, requires both revising incorrect tokens and retaining correct ones, and we show that current USDMs lack the latter. Even under greedy-tail decoding, state-of-the-art USDMs (DUO, UDLM, and uniform-noise SEDD) keep revising 173--270 of 512 positions at every step, and these large, uncoordinated edits collapse sample diversity. A random-token corruption experiment traces this deficit to the models themselves: they reconstruct clean and corrupted tokens with nearly identical accuracy, even though clean tokens are easier targets. A decomposition of the validation NELBO shows that training barely rewards retention: incorrect predictions are heavily penalized at corrupted positions but almost free at clean ones. We propose Correct-Token Retention Regularization (CTR-Reg), a simple but effective auxiliary loss that trains the model to retain tokens left unperturbed by the forward process and requires no change to the sampler. CTR-Reg improves clean-token accuracy by 26.5 percentage points on average across six benchmarks, while leaving corrupted-token accuracy virtually unchanged, and its per-step revisions converge to only 3--11 positions. With just five greedy-tail steps, generative perplexity more than halves under CTR-Reg for all three models while diversity is preserved, and these gains hold across sampling budgets. Our results identify correct-token retention as a key missing ingredient for self-correcting diffusion language models, and demonstrate an effective fix.

Mojtaba Nafez, James Henderson

EPFL & Idiap Lausanne, Switzerland · Idiap Research Institute Martigny, Switzerland

Diffusion Language Model Decoding Diffusion Language Models Diffusion Models

Oct 1, 2026cs.CL

Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models

This work presents Diffusion Layer Integrated Gradients (DLIG), a token attribution method for diffusion language models (DLMs) that extends Integrated Gradients (IG~\cite{sundararajan2017axiomatic}) to arbitrary layers and denoising steps. DLIG attributes a DLM's progressive commitment to a self-generated or fixed completion for an input prompt. We establish direct correspondences between DLIG and the IG axioms of completeness, implementation invariance, linearity, and symmetry preservation. As a lightweight complement to interventional analysis, DLIG provides an inexpensive first check of mechanistic hypotheses across the denoising trajectory. We demonstrate this on word-sense disambiguation, multi-hop graph reasoning, and sentence infilling, revealing how DLMs draw on inputs across positions, layers, and denoising steps.

Darpan Aswal, Céline Hudelot

Université Grenoble Alpes · MICS, CentraleSupélec

Integrated Gradients LLM Interpretability Diffusion Language Model Decoding Diffusion Language Models

Sep 30, 2026cs.LG

Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models

Masked diffusion language models (dLLMs) have shown strong potential for faster inference through parallel token generation when combined with confidence-based samplers. However, recent work has shown that such methods can defer unmasking high-entropy fork positions at which multiple plausible continuations exist. This results in reduced generation diversity, as shown by worse pass@k scaling, and limits gains obtainable from RL post-training. To avoid this flexibility trap, prior work advocated for autoregressive (AR) sampling. Here, we show that discarding confidence-based sampling is unnecessary and, once inference cost is taken into account, wasteful. We first propose Fork-dLLM, a simple hybrid sampler that uses AR-style ordering only at uncertain fallback steps while retaining parallel generation otherwise. We then extend the same principle to post-training with ForkGRPO, which uses Fork-dLLM rollouts and applies the GRPO objective only at fallback steps, preserving exact policy-likelihood ratios while substantially reducing rollout and optimization cost. In our experiments, Fork-dLLM matches the strong pass@k scaling of AR sampling while being 2-3x more efficient, and ForkGRPO achieves downstream performance comparable to or better than AR-based GRPO baselines at a substantially lower training cost.

Stipe Frković, Metod Jazbec, Christian A. Naesseth

University of Amsterdam · UvA-Bosch Delta Lab, University of Amsterdam

Masked Diffusion Models Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding RL for Diffusion Models Diffusion Model Inference Acceleration

Sep 30, 2026cs.LG

Self-Repulsive Sampling for Diffusion Language Models

Sampling several responses and voting over their answers can improve a language model's accuracy, but repeated answers limit the benefit of additional samples. Raising temperature increases diversity at a potential cost to per-sample accuracy. We introduce Self-Repulsion (SR), a sampler for masked diffusion language models that uses peer commitments to diversify the pool. At each penalized denoising step, each path lowers a token's logit according to how many peers have committed that token at the same position. Paths share a batched forward pass and then commit in sequence, so later paths observe choices made earlier in the same step. This coupling requires no training or additional forward or backward pass and can produce distinct paths even at temperature zero. When all paths commit a position together from identical logits, the update exactly maximizes total logit minus a convex duplication cost. On LLaDA-8B-Instruct with ten paths and 128 denoising steps, deterministic SR reaches 80.38% plurality accuracy on GSM8K, compared with 70.17% for the unpenalized greedy decoder. At temperature 0.6 and matched model-evaluation budgets, the count penalty improves over self-consistency by 2.06 percentage points in blocks of 32 and 14.50 under pure diffusion. Experiments on GSM8K, MATH and TruthfulQA show that voting gains arise mainly from higher coverage of correct answers, with gains that vary by benchmark and decoding regime.

Michael Helcig, Martin Jaggi

ETH Zürich · EPFL

Diffusion Language Model Decoding Diverse Text Generation Diffusion Language Models Self-Consistency in Language Models LLM Reasoning

Sep 29, 2026cs.LG

Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents

Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, but recent evaluations show this efficiency does not transfer to embodied agentic competence: dLLM-backed agents repeatedly fall into retry loops, re-issuing an action long after it has failed. We give a mechanistic account of this failure and a training-free remedy. We trace the retry loop to the adaptivity of masked decoding: the sampler commits the positions it is most confident about and defers the uncertain ones, and at a failure state the context already offers a confident fill for the deferred decision, i.e. the failed action itself, so the retry is committed without the failure feedback ever being confronted. We model the resulting distortion of the action distribution as a task-blind corruption: contextually salient actions (e.g., the action just taken) receive inflated probability by a factor that depends on the state and the action but not on the task. Under this model, we analyse an invariance proposition: the task-blind factor cancels exactly from the reverse conditional, i.e. the likelihood of the task given the state and a candidate action, which coincides with the task posterior of an idealized uncorrupted model. Masked dLLMs evaluate the reverse conditional natively, unlike autoregressive models, by masking the task tokens and denoising, at the cost of a few parallel passes per candidate. We instantiate the rule as Reflect Reverse and evaluate it on four multi-turn embodied benchmarks, where it improves task success and progression rates over forward-scoring baselines.

Jiacheng Qiu, Christopher E. Mower, Jan Peters +2

Huawei Noah’s Ark Lab · Technical University of Darmstadt · UCL Centre for AI

Diffusion Language Model Decoding LLM Agents Diffusion Language Models

Sep 29, 2026cs.DC

DScale: Scaling Block-Diffusion Speculative Decoding with Adaptive Verification

Growing large language model applications demand efficient inference. At high concurrency, block-diffusion speculative decoding suffers from verification padding, rejected candidates, and incompatibility between variable prefixes and fixed-shape graphs. Uniform truncation sacrifices acceptable tokens. We present DScale, preserving drafter architecture, weights, and full draft length. A separate 112K-parameter predictor requires neither confidence calibration nor hardware speed-curve preparation. Path-aware tiles reduce padding. Dynamic verify-length (DVL) allocation packs scored prefixes into half the native verification capacity. Fixed-address workspaces propagate changing boundaries through verification and acceptance while reusing captured graphs. On A100-40GB with tensor parallelism 1, Qwen3-8B and Qwen3-4B cover four datasets and concurrency 8-32, reusing each target's frozen predictor. Geometric-mean throughput gains across these configurations are respectively 43.9% and 48.8% over DFlash, 22.2% and 37.7% over DSpark, and 24.4% and 32.0% over Domino, with lower request latency. Cumulative ablations show that adding the three mechanisms successively increases geometric-mean throughput, while budget adjustment improves accepted-token retention. GPU profiling shows that complete decode-step time on GSM8K decreases by 30.8-52.5% relative to DFlash

Rongjian Chen, Minxian Xu, Zhengxin Fang +2

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518052, China · University of Chinese Academy of Sciences, Beijing 100049, China · Victoria University of Wellington, Wellington, New Zealand +1

Speculative Decoding LLM Inference Acceleration Diffusion Language Model Decoding

Sep 29, 2026cs.LG

LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter

Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context grows, existing state-of-the-art drafters become increasingly expensive, eroding the very efficiency advantage they are designed to provide. We argue that this scaling is unnecessary. A standalone language model must grow with its prefix because it is solely responsible for every token it produces. A drafter, by contrast, only proposes candidates; the target catches and corrects every error before any token is committed. The drafter's decoding cost can therefore be made entirely independent of the prefix length. We introduce LongSpark, a block-diffusion drafter that achieves this by extracting fixed-size, multiscale views from the target's verification pass, thereby eliminating the need for a growing persistent state. Extensive evaluations demonstrate that LongSpark achieves state-of-the-art end-to-end efficiency across multiple model scales and realistic serving conditions. Notably, it delivers the lowest time-per-output-token on long-context tasks while reducing the drafter's context state by several orders of magnitude.

Hao-Yuan He, Peng-Fei Liu, Si Shen +1

Long-Context Language Model Inference Blockwise Diffusion Language Models Speculative Decoding LLM Inference Acceleration Diffusion Language Model Decoding

Sep 29, 2026cs.CL

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

Sep 28, 2026cs.LG

Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models

Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constraint. MDLMs generate outputs by repeatedly unmasking masked positions present in their current state. Recent strategies for constrained decoding constrain the model's per-step mean-field posterior (which factorizes over masked positions) by enforcing the desired constraint with an automaton. The resulting chain-structured factor graph allows exact constrained sampling via dynamic programming. However, despite each draw being exact and constraint-satisfying, we prove that their composition, in general, tilts away from the model's relative probabilities over valid trajectories, thus leading to trajectory bias. We derive an exact expression for this bias as a product of ratios measuring how valid continuation mass changes when the denoiser is reconditioned, and characterize when the bias vanishes. We then correct the bias by introducing TWISTER, the first automaton-twisted Sequential Monte Carlo decoder for MDLMs, using the step-exact decoder as the proposal. We show that for regular language constraints, the Feynman-Kac correction is exactly computable, with the twists obtained efficiently using quantities pre-computed for step-exact sampling. We prove that the resulting Feynman-Kac model targets the unbiased Doob h-transformed path law conditioned on constraint satisfaction.

Aditya Thimmaiah, Lara Marinov, Jayanth Srinivasa +3

The University of Texas at Austin · Cisco Research

Constrained Decoding Masked Diffusion Models Language Model Decoding Diffusion Language Model Decoding

Sep 28, 2026cs.AI

Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning

Discrete diffusion language models (dLLMs) expose a denoised solution at every step, which makes process reward model (PRM) guidance look like a way to spend compute at test time. We show that once denoising, PRM scoring, and outcome reward model (ORM) scoring are charged in the same budget of forward passes, its deterministic form loses to a much simpler baseline. Our PRMs score intermediate denoising states and are trained on the correctness of the final answer. On Dream-v0-Instruct-7B with 8 candidates per GSM8K problem, keeping the candidate with the highest PRM score at every scoring step reaches 65.18%, while independent sampling plus an ORM reranker trained for the task reaches 75.13%. The gap grows to 12.69 percentage points (pp) with 32 candidates, and is 9.85 pp on MATH and 12.16 pp on MBPP. We trace it to two separable failures. First, guidance prunes on a weak signal: on GSM8K, PRM ROC-AUC falls from 0.77 to 0.54 as the mask ratio rises, a decay that persists when states are relabeled with fresh rollouts, and pruning lowers the best accuracy reachable from the candidate pool from 81.05% for independent samples to 67.30%. Second, on GSM8K and MATH, the PRM is a poor final judge: a sequential Monte Carlo sampler at the same budget restores that ceiling to 77.89%, yet selecting with the PRM gives 65.48%, on par with deterministic guidance, while a PRM retrained on final states matches the ORM on identical candidates. MBPP separates the two: there the PRM reaches 65.47% when reranking finished programs, on par with the ORM, but 50.88% when it guides denoising. The results point to two targets for dLLM guidance: keep correct partial solutions alive through early denoising, and leave the final choice to a verifier trained on final states. We release the corpus of denoising states with outcome labels and evaluation toolkit for reproducible comparisons at matched compute.

Yan Zhan, Shaobo Liu, Zhijun Gao

Peking University · Shenzhen University

Process Reward Models Diffusion Language Model Decoding Diffusion Language Models

Sep 28, 2026cs.AI

BV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding

Diffusion drafters accelerate speculative decoding by proposing multiple tokens in parallel. Despite recent advances in speculative decoding through sequence-level drafting and verification, existing training objectives remain largely designed around token-level verification. To address this mismatch, we introduce Block Verification-aware loss (BV loss), a training objective designed to maximize the expected acceptance length of a drafted sequence. BV loss is directly derived from the block verification acceptance rule, providing a principled connection between the drafter training objective and the inference-time verification mechanism at the sequence level. Across math, code, and chat benchmarks, BV loss increases the mean number of tokens accepted per verification call under block verification by 13.0--21.0% over cross-entropy loss training for DFlash and DSpark with Qwen3-4B and Qwen3-8B without changing the inference procedure. BV loss also outperforms tokenwise acceptance objectives such as TV loss and LK loss, and its gains extend to token verification and greedy decoding. These results demonstrate the benefit of training block diffusion drafters with an objective aligned with sequence-level verification, rather than optimizing each token independently.

Suyoung Kim, Jahyun Koo, Hyeonjin Kim +5

a2sys (a2sys.ai) · Seoul National University (snu.ac.kr) · University of Wisconsin (wisc.edu)

Speculative Decoding Diffusion Language Model Decoding Diffusion Language Models

Sep 28, 2026cs.LG

Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs

Masked diffusion language models support arbitrary-order generation, suggesting a natural way to produce diverse outputs. However, recent work argues that this flexibility reduces diversity by delaying high-uncertainty tokens that can lead to different generation paths. We trace this diversity loss not to arbitrary-order generation itself, but largely to low-confidence remasking (LCR), a widely used decoding rule. At each step, LCR samples a token at every masked position but commits only the sampled token with the highest probability, filtering out the rest. We show that this mechanism can exponentially suppress lower-probability tokens as more positions compete, and observe the same suppression in LLaDA. In contrast, top-probability position selection (TPP), which has often been conflated with LCR under the shared label confidence-based decoding, avoids this diversity loss. TPP first selects the position whose most likely token has the highest probability, then samples directly from that position's distribution. Replacing LCR with TPP restores diversity and yields Pass@

k

comparable to left-to-right decoding, suggesting that the reported diversity loss stems largely from LCR's filtering rather than from generating high-confidence positions first. To further exploit order flexibility, we introduce Entropy-Guided Initialization (EGI), which samples the first token at the highest-entropy position and then follows TPP. This simple modification further improves rollout diversity and solution coverage beyond left-to-right decoding, with gains extending to downstream policy optimization, highlighting the potential of arbitrary-order generation for diverse rollouts.

Moongyu Jeon, Dongjae Jeon, Bumjun Kim +2

Yonsei University · KRAFTON AI · Kookmin University

Masked Diffusion Models Diffusion Language Model Decoding Diffusion Language Models

Sep 27, 2026cs.CL

From Position Risks to Block Survival: Faster Generation for Diffusion Language Models

Diffusion language models (DLMs) can accelerate generation by predicting multiple tokens in parallel, but there is a mismatch between how these tokens are predicted and how they ultimately contribute to generation. Parallel predictions can hardly condition on the tokens selected earlier within the same block, even though their validity depends on this realized prefix. Under the popular proposal-verification decoding, this mismatch makes errors highly asymmetric: an early rejection prevents all subsequent proposals from contributing decoding progress. We introduce BRISK-DLM, a framework that addresses both mismatches by optimizing proposal learning and selection for verified progress. BRISK-DLM trains on self-generated sequences, using risk-reward weighting to dynamically prioritize positions by their impact on verified progress and decoding cost. During inference, a lightweight prefix-conditioned corrector reranks existing candidates using previously selected tokens and preferences distilled from the model's own verifier. The corrector reuses the backbone's parallel representations and requires no additional backbone evaluation, while fused execution keeps its overhead small. BRISK-DLM improves end-to-end throughput by up to 37.4% while preserving task quality, establishing a new quality-throughput frontier for DLM generation.

Siwei Chen, Yuxiang Wan, Yifan Yu +1

University of Illinois Urbana-Champaign

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

Sep 27, 2026cs.AI

Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models

Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference decision. Existing methods vary in how they prioritize positions, control parallelism, restrict selection regions, revise predictions, or plan future denoising, yet it remains unclear when these choices should change during generation. We study this question through strategy reversals, where an alternative action becomes preferable to a fixed choice. We organize MDM inference into five axes--score, cardinality, region, commitment, and planning--and define adaptation opportunity as the one-step utility advantage of the best candidate action over a validation-selected fixed action. This view shows that adaptation value depends on both the frequency and magnitude of such reversals. Across three MDMs and ten tasks, adaptation opportunities are highly heterogeneous, with some regimes exhibiting concentrated and predictable one-step gains. This motivates selective adaptation: lightweight detectors calibrated on validation prompts identify high-opportunity states, capturing, for example, 56.9 percent of the candidate-set oracle opportunity by adapting only the top 10 percent of states on LLaDA-8B constrained JSON filling. Our transition-level results suggest that state adaptation is most useful when applied selectively rather than uniformly.

Injin Kong, Sunghwan Choi, Yohan Jo

Graduate School of Data Science, Seoul National University

Masked Diffusion Models Diffusion Language Model Inference Diffusion Language Model Decoding

Sep 27, 2026cs.CL

Hesitation-Aware On-Policy Distillation for Diffusion Language Models

Diffusion large language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a token at every masked position, but the decoder commits only a confident subset of these proposals. Trace-based on-policy distillation (TOPD) builds on this process by matching the student to a stronger teacher, yet only at the committed positions. We argue that this discards much of the useful signal, which resides in the uncommitted proposals, where the student has made a prediction but is not yet confident enough to commit it. We call these proposals hesitations. In our pilot study on an SDAR-4B student, hesitations make up only 24% of supervisable state-position pairs but carry 66% of the teacher-student divergence. To exploit this signal, we propose Hesitation-Aware On-Policy Distillation (HOPD), which extends teacher distribution matching to every masked position of each denoising step. Because hesitations are not equally informative, we further allocate supervision using hindsight from the completed trajectory, placing more weight on positions whose proposal was later disagreed with the final token and on blocks where first-step proposals rarely survive. Since both models already produce distributions at all masked positions, HOPD requires no additional forward passes over TOPD. The only extra cost is evaluating the loss at more positions. With SDAR-1.7B and SDAR-4B students distilled from TraDo-8B-Instruct, HOPD achieves the best average score among the evaluated methods on five math and coding benchmarks, under both static and dynamic decoding and at both scales. It also speeds up decoding. On SDAR-4B, the HOPD student hesitates less and commits 11% more tokens per denoising step than TOPD, while reaching higher accuracy.

Jianguo Huang, Lipeng Wan, Yanchen Deng +1

Nanyang Technological University, Singapore · Xi’an Jiaotong University, China

Diffusion Language Model Decoding Uncertainty-Aware Knowledge Distillation On-Policy Distillation Diffusion Language Models Knowledge Distillation Diffusion Language Model Distillation

Sep 23, 2026cs.CL

When Parallel Drafter Meets Parallel Speculative Decoding

DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong guess reverts the whole batch to serial drafting. We present DPara, a PSD framework that reuses effective parallel drafters yet guarantees backbone--verification overlap in every round, thereby eliminating this probabilistic fallback altogether. While the target verifies, DPara's diffusion backbone precomputes draft representations for every acceptance boundary with the bonus left unspecified; a lightweight autoregressive head then combines the revealed verification outcome with the matching precomputed representation to emit the next round's draft tokens almost instantly---fully parallelizing the dominant backbone forward with verification and leaving only the negligible head cost serial. Experiments on Qwen3-8B and Qwen3-14B across seven math, coding, and chat benchmarks show that DPara achieves average speedups of

3.21\times

and

3.52\times

over autoregressive decoding, surpassing the strongest serial and parallel speculative decoding baselines alike.

Fuliang Liu, Xue Li, Kun Qian +4

State Key Laboratory of Novel Software Technology, Nanjing University · Alibaba Group

Speculative Decoding LLM Inference Acceleration Parallel Decoding Diffusion Language Model Decoding

Sep 22, 2026cs.CL

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabling non-autoregressive text generation. However, their practical deployment remains limited by inefficient inference, largely due to the absence of effective Key-Value (KV) caching and scalable parallel decoding mechanisms. Existing acceleration methods typically study KV caching and parallel decoding in isolation, overlooking the I/O bottlenecks that arise when cache reuse and parallel token verification are jointly applied. In this work, we introduce

\textbf{Flash-dLLM}

, a training-free inference acceleration framework for fast and memory-efficient dLLMs. Flash-dLLM first identifies GPU memory I/O as a dominant bottleneck in KV-cache-enabled dLLM inference and addresses it with an I/O-aware fused KV-cache kernel that reduces redundant memory movement. Building on this optimized cache mechanism, Flash-dLLM further proposes an efficient KV-cache-driven draft-and-verify decoding strategy, where the dLLM itself serves as both drafter and verifier without requiring an auxiliary model. This unified design enables faster decoding while preserving generation quality and improving scalability to longer sequences and larger batch size. Extensive experiments on mathematical reasoning and code-generation benchmarks demonstrate that Flash-dLLM consistently outperforms existing state-of-the-art dLLM acceleration methods in both inference speed and memory efficiency. In particular, it achieves

5.1\times

and

11.0\times

speedups over prior strongest baseline Elastic-Cache on GSM8K and HumanEval, respectively.

Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen

VILA Lab, MBZUAI Abu Dhabi, UAE

Speculative Decoding Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Model Inference Acceleration

Sep 17, 2026cs.CL

dQwen3.5: Hybrid-Attention Diffusion Language Models

Adapting a pretrained autoregressive (AR) model is a cost-efficient route to a diffusion language model (DLM). While nearly all such adaptations start from a full-attention transformer, AR modeling has shifted toward hybrid architectures that interleave attention and RNN layers. This creates an obstacle for adaptation: unlike attention, RNNs are structurally causal and nontrivial to bidirectionalize. Despite this mismatch, we investigate whether such backbones can become effective DLMs by adapting Qwen3.5 at 0.8B, 2B, 4B, and 9B scales, yielding the dQwen3.5 family. We find that hybrid backbones can be efficient starting points for adaptation: against a full-attention control, the hybrid reaches a given training loss in about half the tokens. Across scales, dQwen3.5 resembles full-attention DLMs in any-order decoding behavior and performs strongly under parallel decoding.

Anton Xue, Litu Rout, Aditya Akella +3

University of Texas at Austin

Diffusion Language Model Decoding Diffusion Language Models

Sep 17, 2026cs.LG

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

Sep 17, 2026cs.CL

Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference

Autoregressive language models (ARMs) are constrained by sequential, left-to-right generation, while masked diffusion models (MDMs) enable parallel decoding but suffer from high computational overhead due to the inability to reuse Key-Value (KV) cache and from incoherent generation arising from learning dependencies over an intractable space of token combinations. We introduce Zarya, a family of hybrid language models that jointly optimizes an autoregressive (AR) objective and a masked-diffusion objective within a single architecture. Zarya structures training data into variable-size slots and employs a curriculum that gradually increases slot granularity, enabling a smooth transition from fine-grained AR learning to coarse-grained diffusion learning. At inference, Zarya provides two distinct decoding paradigms through a unified interface: (i) MDM sampling with first-hitting denoising, and (ii) slotted speculative decoding that interleaves inter-slot diffusion-based selection with intra-slot autoregressive infilling, achieving full KV cache reuse. The training and inference regimes are fully decoupled, allowing a model trained with any configuration to be deployed in either mode. Extensive configurability --- including grouped noise patterns (Prefix Completion, Fill-In-the-Prefix, Fill-In-the-Middle), ordered sampling schedules, and noise-level permutation strategies --- enables flexible research exploration. We release Zarya models publicly in sizes 0.6B, 1.7B, and 4B, demonstrating performance on standard benchmarks while offering a principled integration of autoregressive and diffusion paradigms.

Leonid Sinev, Ilya Koziev, Vladislav Leshchuk

Masked Diffusion Models Autoregressive Diffusion Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration

Sep 15, 2026cs.CL

Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling

Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation through iterative unmasking. However, dLLMs typically require many steps before token confidence reaches the decoding threshold, resulting in inefficient inference even with block-wise KV caching. To accelerate dLLM inference, we for the first time propose an "early-bird (EB)" decoding framework, motivated by the observation that tokens with similarly low entropy tend to cluster and can be jointly decoded earlier, before reaching the confidence threshold. In particular, our EB-Decode framework integrates two key enablers: (1) a learnable network that adaptively groups tokens with similar uncertainty into variable-length blocks, rather than relying on fixed block sizes; (2) a position-aware sampler that learns to unmask tokens in parallel using fewer decoding steps within predicted variable-length blocks. Both components are developed without modifying pretrained dLLM weights and can therefore be directly deployed as plug-ins during serving, with negligible training and inference overhead. Extensive experiments across three models and four benchmarks consistently validate our observation and the effectiveness of EB-Decode, achieving 3.53-18.76

\times

higher throughput than the vanilla decoding method and up to 1.58

\times

higher throughput over the strongest baseline, Fast-dLLM, with comparable accuracy.

Lixuan Wei, Wei Zhou, Jianwen Wu +3

Harvard University · Georgia Institute of Technology · Purdue University

Diffusion Language Model Inference Parallel Decoding Diffusion Language Model Decoding

Sep 14, 2026cs.LG

Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models

Diffusion language models (dLLMs) promise fast inference by generating multiple tokens in parallel, but suffer severe performance degradation when parallel decoding is pushed too aggressively. We introduce Temporal Self-Distillation (TSD), a simple on-policy method that trains dLLMs for fast inference by distilling predictions across time. Specifically, TSD distills the model's denoising distribution at earlier timesteps toward its distribution at the final timestep at which a token is committed. This encourages earlier predictions to better anticipate the model's eventual output, enabling much more aggressive parallel decoding. Because its teacher signal comes from the model itself, TSD requires no offline teacher generation and applies seamlessly to both base and post-trained policies. Across seven benchmarks in mathematics, planning, and code, TSD substantially shifts the speed--quality frontier toward the low-compute regime. TSD thus provides a simple, single-stage approach to accelerating dLLMs, achieving speedups competitive with offline distillation while avoiding a complex two-stage pipeline.

Shijian Xu, Andrea Miele, Metod Jazbec +3

University of Basel · University of Amsterdam · Johns Hopkins University

Diffusion Model Distillation Diffusion Language Model Inference Diffusion Language Model Decoding Self-Distillation Diffusion Language Models Diffusion Language Model Distillation

Sep 14, 2026cs.CL

DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models

Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, independently predicting multiple tokens at each step. This conditional independence discards inter-token dependencies and degrades coherence-an issue that parallels the multi-modality problem in Non-Autoregressive Translation (NAT). Drawing on the Directed Acyclic Transformer (DAT), which tackles this problem in NAT via a Directed Acyclic Graph (DAG), we propose DA-DLM, a model that adapts DAG-based dependency modeling to DLMs' iterative setting through a position-oriented DAG design. The position-oriented DAG binds node groups to fixed output positions so that tokens fixed in earlier steps anchor neighboring predictions via learned transitions, and evolves with denoising to focus on remaining uncertainty as anchors accumulate. On language modeling, open-ended generation, and summarization, DA-DLM consistently outperforms Block Diffusion, especially under fewer denoising steps, and matches autoregressive models while preserving the parallel generation advantage. Our code is publicly available at https://github.com/jipy0222/DA-DLM.

Pengyu Ji, Zichen Zhang, Xiang Hu +1

‡School of Information Science and Technology, ShanghaiTech University · §Shanghai Engineering Research Center of Intelligent Vision and Imaging · ¶Tencent

Non-Autoregressive Text Generation Diffusion Language Model Decoding Diffusion Language Models

Sep 12, 2026cs.AI

Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models

Diffusion vision-language models generate answers through iterative refinement, exposing intermediate answer trajectories that can be inspected and controlled at inference time. However, this controllability creates a reasoning-need mismatch, where a universal generation length is applied to questions with different reasoning demands. Visually closed questions may be harmed by continued refinement after a stable answer has formed, whereas reasoning-sensitive questions may be harmed by premature commitment. We formulate this problem as reasoning-budget mismatch and study it in LLaDA-V. Rather than choosing a universal generation length, our training-free controller routes each example to early commitment, baseline preservation, or reasoning-supportive decoding using trajectory signals from answer closure, commitment evidence, and representation revision pressure, without using ground-truth answers. Across answer-focused, mixed-reasoning, and CoT-sensitive benchmarks, routed control improves robustness over fixed long decoding, pure short decoding, and single-rule interventions. The gains are not explained by shorter outputs alone. Answer-closed examples often benefit from commitment, whereas CoT-sensitive examples require preserving or supporting intermediate reasoning. Taken together, these results suggest diffusion VLM decoding should route inference-time control by the state suggested by the observed trajectory instead of relying on a universal decoding length.

Yixiang Liu, Zhongxing Xu, Zhonghua Wang +1

Southern University of Science and Technology · Monash University

Diffusion Language Model Inference VLM Reasoning Diffusion Language Model Decoding Inference-Time Compute Allocation Diffusion Language Models

Sep 1, 2026cs.LG

From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion

Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-

p

rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a training-free sampler that stores selected argmax tokens and inserts them into subsequent model inputs. Our analysis gives a rationale for selecting later and for keeping selected tokens visible. Under the exact forward process, the Bayes error of selecting a clean token cannot increase as noise decreases, while in a simple latent-mode model, keeping the selected token visible helps later parallel predictions agree on the same sequence-level choice. Empirically, paired experiments on Duo-distilled then separate this persistent effect from single-step top-

p

restriction and scalar temperature scaling. Under the same finalization rule, CRS without top-

p

truncation reaches lower generative perplexity (GenPPL) than fixed

p=0.95

and

p=0.9

baselines across budgets of 8--64 function evaluations (NFE). At 64 NFE, the comparison at matched unigram entropy also gives lower GenPPL for CRS, yielding a more favorable GenPPL--entropy tradeoff. Base Duo shows the same direction in a descriptive comparison, while other diversity and continuation metrics can rank these operating points differently. These results identify support restriction and persistent context as distinct controls of that tradeoff.

Satoshi Hayakawa

The University of Tokyo

Diffusion Sampling Diffusion Language Model Decoding Diffusion Language Models