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

May 27, 2026cs.AI

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models

Chain-of-thought reasoning helps autoregressive models solve complex problems by generating intermediate steps that support later predictions. Masked diffusion models (MDMs) offer a similar opportunity through arbitrary-order generation: they can ideally reveal intermediate results along logical dependencies. In practice, however, standard decoding simply prioritizes high-confidence tokens, which need not align with this dependency order. We identify this discrepancy as the \emph{confidence shortcut}: models commit with high certainty to plausible tokens while neglecting long-range dependencies. In multi-digit addition, models predict higher-order digits without properly tracking carries through long chains. Controlled pretraining across diverse reasoning tasks confirms that confidence-guided ordering often selects suboptimal sequences, and confidence-aligned training schemes can exacerbate these failures---for example, increasing addition error rates by an order of magnitude. Our findings caution against relying solely on confidence to choose generation orders and against training objectives that reinforce this preference. The experimental code is available at https://github.com/jinha2536/mdm-arithmetic.

Dueun Kim, Albert No

Department of Artificial Intelligence, Yonsei University

Masked Diffusion Models Language Model Decoding Mathematical Reasoning Diffusion Language Model Decoding Diffusion Language Models

May 27, 2026cs.AI

Diffusion Large Language Models for Visual Speech Recognition

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the best of our knowledge, the first Diffusion Large Language Model (DLLM)-based VSR framework, formulating transcription as iterative masked denoising with flexible-order decoding. With confidence-based unmasking, DLLM-VSR commits high-confidence positions early and uses the committed tokens as bidirectional context to refine ambiguous ones. To adapt DLLMs to VSR, we introduce a two-stage masked-denoising training strategy that separates visual-to-text content alignment from length modeling. We further observe a performance gap compared with an upper-bound setting where the ground-truth transcript length is provided at inference, allowing the model to focus on transcript content decoding. To reduce this gap, we develop length-guided candidate decoding, which uses video duration to construct plausible transcript-length hypotheses and reranks the decoded candidates using length plausibility and decoding confidence. The proposed method achieves a 19.4% word error rate on LRS3, establishing state-of-the-art performance among methods using only LRS3 as labeled training data.

Jeong Hun Yeo, Chae Won Kim, Hyeongseop Rha +1

Integrated Vision Language Lab, KAIST, South Korea

Visual Speaker Recognition Diffusion Language Model Decoding Diffusion Language Models

May 27, 2026cs.CL

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models

Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model confidence for position selection, assuming that high-confidence positions are ready to be decoded. In this work, we revisit this assumption by studying when confidence misleads fully non-autoregressive (fully non-AR) decoding. EOT tokens can receive high confidence and cause incomplete generation; inserting a suffix anchor can mitigate this issue but introduces local overconfidence near the anchor, causing anchor-adjacent tokens to be decoded too early. To address these issues, we propose Suffix-Anchored Confidence Modulation, a simple training-free method that inserts a short suffix anchor to encourage response completion and modulates confidence near the anchor according to decoding progress. This preserves the response-completion benefit of suffix anchoring while reducing premature decoding of anchor-adjacent tokens. Across text-only reasoning, vision-language reasoning, and code-generation benchmarks, our method consistently improves confidence-based fully non-AR decoding, outperforms explicit EOT suppression, and preserves the parallel decoding advantage of fully non-AR generation.

Jungwon Park, Jimyeong Kim, Jungmin Ko +2

1RICS · 2AIIS · 3IPAI +2

Non-Autoregressive Text Generation Language Model Decoding Confidence Estimation in Language Models Diffusion Language Model Decoding Diffusion Language Models

May 27, 2026cs.CL

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

May 25, 2026cs.LG

Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models

Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns each decoding step into a position-selection problem: the model must choose not only which predictions are reliable in isolation, but also which positions should be committed together as context for later decoding steps. Existing confidence-based decoding ranks masked positions independently and commits the top-K positions, largely ignoring whether the committed tokens provide complementary visual grounding. We identify a step-level limitation of this strategy in multimodal settings: high-confidence tokens selected in the same step can rely on overlapping visual grounding, introducing visual redundancy among the committed tokens and leaving less complementary visual grounding available for later decoding. To quantify this effect, we introduce the Visual Redundancy Index (VRI), which measures visual grounding overlap among tokens committed in parallel. To control this redundancy during decoding, we propose Visual-Redundancy-Controlled Decoding (VRCD), a training-free inference-time decoding method that uses token-to-image attention to prioritize visually complementary positions. Across diverse multimodal benchmarks, VRCD reduces visual redundancy and remaining-position entropy with modest runtime overhead. In longer decoding experiments, it also achieves relative accuracy gains of up to 18.8% on M^3CoT and 6.9% on MMBench over confidence-based decoding. Code is available at https://github.com/infiniteYuanyl/VRCD.

Yulin Yuan, Hongshuo Zhao, Xiangming Meng

Zhejiang University · ZJUI-UIUC Institute

Language Model Decoding Multimodal Large Language Models Parallel Decoding Diffusion Language Model Decoding Multimodal Understanding

May 23, 2026cs.CL

The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models

Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tokens should be transferred into the partially decoded sequence at each step? We refer to this decision as token commitment. Existing frozen-generator decoders largely rely on hand-designed confidence rules or block-specific acceptance filters. We argue that token commitment can instead be learned as a reusable trace-state policy. We introduce TraceLock, a lightweight plug-in controller that instantiates this policy for a frozen diffusion language model. Since oracle commitment times are unavailable, TraceLock derives self-supervision from future stability: at decoding step t, a proposed token for position i is labeled stable if it matches the final token at position i after the full decoding trace completes. The controller scores variable-length trace states and decides which active token proposals should be committed to the partially decoded sequence. Once trained for a given frozen backbone, the controller can be deployed across local-window widths, generation lengths, and step budgets without retraining or per-setting calibration. Experiments on question answering, mathematical reasoning, and code generation show that TraceLock improves the quality-step tradeoff over heuristic and learned baselines, with particularly stable behavior under cross-setting deployment. Diagnostic analyses show that its decisions are not reducible to scalar confidence, suggesting that frozen diffusion language models expose a learnable space of commitment trajectories beyond confidence-based decoding. Code is available at https://github.com/BobSun98/TraceLock.

Bohang Sun, Max Zhu, Francesco Caso +5

Department of Computer Science and Technology, University of Cambridge · Department of Engineering Science, University of Oxford

Diffusion Language Model Decoding Diffusion Language Models

May 21, 2026cs.LG

Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset between denoising rounds, we propose Learned Relay Representations (Relay), a method that allows MDMs to be forward-thinking when denoising by explicitly learning how to propagate latent information for the benefit of future denoising steps. Relay introduces a differentiable per-token channel that passes information between forward passes and is trained via truncated backpropagation through time (BPTT). We show that this framework can be scaled to state-of-the-art Diffusion Language Models (DLMs), and is seamlessly compatible with techniques like block diffusion and KV caching. We first provide a thorough justification of the design choices in Relay on a challenging Sudoku-based planning task. We then scale Relay to Fast-dLLM v2, a state-of-the-art DLM, outperforming standard supervised finetuning on coding tasks while reducing inference latency by up to 32%. Our empirical results demonstrate that state-of-the-art DLMs can be explicitly trained to relay latent information forward across decoding steps, advancing the performance-latency Pareto frontier. We provide code for all our experiments.

Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel +4

University of Massachusetts Amherst · University of Toronto · Stanford University +3

Masked Diffusion Models Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Language Models

May 16, 2026cs.AI

AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation

Radiology report generation (RRG) aims to automatically produce clinically accurate textual reports from medical images. Existing methods predominantly rely on autoregressive (AR) language models, whose causal dependency structure restricts generation to a unidirectional left-to-right process. This paradigm can induce sequence bias, where models tend to follow stereotypical token orders and high-frequency report templates rather than fully grounding generation in image-specific evidence. In this paper, we propose AnchorDiff, the first masked-diffusion framework for RRG that integrates knowledge-graph-derived clinical anchors into diffusion language modeling. By leveraging bidirectional context and iterative refinement, AnchorDiff mitigates the limitations of fixed-order autoregressive decoding. Specifically, we introduce a topology-aware training strategy that uses RadGraph-derived entity hierarchies to assign clinically important tokens differentiated masking protection and loss weights. We further design an inference-time rewriting strategy that detects unstable committed tokens through perturbation-based testing and selectively revises them during denoising. Extensive experiments on the MIMIC-CXR and MIMIC-RG4 benchmarks demonstrate that AnchorDiff achieves state-of-the-art (SOTA) performance, showing the effectiveness of clinically anchored masked diffusion for radiology report generation.

Shiying Yu, Jielei Wang, Guoming Lu

University of Electronic Science and Technology of China

Radiology Report Generation Diffusion Language Model Decoding Diffusion Language Models

May 16, 2026cs.CL

Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We attribute this dilemma to a train-inference mismatch amplified by irreversible decoding. While training reconstructs tokens from randomly corrupted states, efficient inference requires an adaptive denoising order, where easier tokens are revealed earlier and context-dependent ones are deferred. This view motivates two complementary methods: an inference-time method that makes parallel decoding revokable, and a training-time extension that distills the reliable order exposed by this revokable process. Accordingly, we first propose Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable parallel generation. WINO aggressively drafts multiple tokens, verifies generated tokens with enriched global context, and re-masks unreliable ones for later refinement. Building on this discovered order, we further introduce WINO+, which injects the verified denoising trajectories produced by WINO into model parameters, aligning training with efficient inference. Experiments on LLaDA and MMaDA show that WINO improves both quality and efficiency, while WINO+ further strengthens this progression. On GSM8K, WINO improves accuracy from 73.24% to 75.82% with a 6.10x step reduction, and WINO+ further achieves 76.58% with a 6.83x reduction. On Flickr30K, WINO+ reaches a 16.22x step reduction with improved CIDEr. These results demonstrate that DLLMs can serve as their own efficiency teachers by first discovering reliable denoising orders through revokable decoding and then learning to follow them for faster generation. Code is available at https://github.com/Feng-Hong/WINO-DLLM/tree/WINO-plus.

Fanqin Zeng, Feng Hong, Geng Yu +6

Shanghai Jiao Tong University, Shanghai, China · Apple MLR, Cupertino, CA, USA · Tongji University, Shanghai, China +2

Diffusion Model Distillation Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Diffusion Language Model Distillation

May 15, 2026cs.CL

Dynamic Chunking for Diffusion Language Models

Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block conditioning. We argue that this rigid partition wastes structure already present in the sequence: blocks defined by position rather than by content separate semantically coherent tokens and group unrelated ones together. We introduce the \textbf{D}ynamic \textbf{C}hunking \textbf{D}iffusion \textbf{M}odel (DCDM), which replaces positional blocks with content-defined semantic chunks. At its core is Chunking Attention, a differentiable layer that routes tokens into

K

clusters parameterized by learnable subspaces and shaped end-to-end by the diffusion objective. The resulting cluster assignments induce a chunk-causal attention mask under which a discrete diffusion denoiser factorizes the sequence likelihood autoregressively over semantic chunks, strictly generalizing block discrete diffusion. On downstream benchmarks at parameter scales up to 1.5B, DCDM consistently improves over both unstructured and positional-block diffusion baselines, with the advantage stable across scales and visible early in training.

Yichen Zhu, Xiaoming Shi, Peng Zhao +3

CSE, HKUST · Xiaohongshu Inc. · Alibaba group +1

Document Chunking Autoregressive Diffusion Blockwise Diffusion Language Models Diffusion Language Model Decoding Diffusion Language Models

May 15, 2026q-bio.BM

Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design

Proteins perform their biological functions through three-dimensional structures encoded by amino acid sequences, and ligand-binding protein co-design requires models that generate sequence-structure compatible proteins under explicit ligand constraints. Although continuous diffusion and flow-based models support ligand-aware design in coordinate or latent spaces, existing discrete diffusion protein language models mainly operate over sequence or structure tokens without direct small-molecule conditioning. We introduce \textbf{ProtLiD

^2

}, a \textbf{Prot}ein \textbf{L}igand-conditioned \textbf{D}iscrete \textbf{D}iffusion model for protein sequence-structure co-design. ProtLiD

^2

jointly generates amino-acid sequence and discrete structure tokens while incorporating ligand chemical and geometric information through geometry-aware cross-attention. Trained on over one million ligand-protein complexes, ProtLiD

^2

extends masked discrete diffusion to ligand-aware functional protein design. We further propose maximum confidence-margin guided ReMask decoding, an inference-time self-correction strategy that retains confident predictions and remasks uncertain tokens. ProtLiD

^2

improves global fold confidence over Complexa in whole-protein design, increasing TM-score from 0.672 to 0.802 and pLDDT from 64.55 to 73.00. In pocket co-design, ProtLiD

^2

reduces active-site BB-RMSD from 3.46/3.40Å for FAIR/PocketGen to 1.97Å, and improves ligand-aware pass rates over PocketGen from 14.86% to 59.73% and from 6.08% to 23.49% under stricter docking thresholds. These results support ligand-conditioned discrete diffusion as an effective token-space framework for functional protein co-design. Code will be available at https://github.com/auroua/ProtLiD.

Chen Wei, Fanding Xu, Minghao Sun +5

Xi’an University of Posts & Telecommunications · National University of Singapore · Xi’an Jiaotong University +1

Protein Language Models Diffusion Language Model Decoding Molecular Generation Diffusion Language Models Protein Design

May 15, 2026cs.CL

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

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

May 14, 2026cs.CV

Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models

Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding for efficient inference and leveraging bidirectional attention for global context. Despite these advances, their behavior under long-form generation remains underexplored. In this work, we show that existing LDVLMs suffer from repetitive generation and degraded visual grounding, and identify two underlying causes. First, repetitive generation originates from a mask token prior: since generation tokens are initialized as mask tokens, their hidden representations progressively drift toward a shared prior direction over generation steps. Second, a fundamental misalignment between the positional attention bias and the iterative unmasking process suppresses attention toward informative visual tokens, degrading visual grounding. Based on these insights, we propose a training-free approach, introducing Mask Prior Suppression and Monotonic RoPE Scaling to mitigate mask prior drift and positional attention collapse during decoding. Experiments on general multimodal benchmarks and visual grounding tasks demonstrate improvements over baseline LDVLMs, with robust gains on long-form description benchmarks. Our results show that these failures can be effectively addressed with a lightweight, plug-and-play strategy that requires no additional training and generalizes across diverse LDVLM architectures.

Sujung Hong, Chanyong Yoon, Seong Jae Hwang

Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea.

Vision-Language Models Diffusion Language Model Decoding Visual Grounding Text Generation

May 14, 2026cs.CL

Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding

Discrete diffusion language models improve generation efficiency through parallel token prediction, but standard

X_0

prediction methods introduce factorization errors by approximating the clean token posterior with independent token-wise distributions. This paper proposes Factorization-Error-Free Discrete Diffusion Language Modeling (FeF-DLLM), which replaces independent clean-token prediction with an exact prefix-conditioned factorization of the clean posterior to better preserve token dependencies. To reduce the sequential cost introduced by prefix conditioning, FeF-DLLM further incorporates speculative decoding within diffusion denoising, accelerating inference while maintaining the parallel prediction and re-masking properties of DLLMs. Theoretically, we prove that FeF-DLLM generates from the true joint distribution and derive its expected acceleration ratio. Experiments on GSM8K, MATH, HumanEval, and MBPP demonstrate that our method improves accuracy by an average of 5.04 percentage points while achieving an average inference speedup of

3.86\times

.

Xun Fang, Yunchen Li, Hang Yuan +1

East China Normal University · Beijing Zhongguancun Academy

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

May 12, 2026cs.LG

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

May 12, 2026cs.LG

Multi-Token Residual Prediction

Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K.

Yufeng Xu, Zishuo Bao, Qian Wang +6

New York University · New York University Shanghai · Nous Research +1

Masked Diffusion Models Multi-Token Prediction Speculative Decoding Diffusion Language Model Inference Diffusion Language Model Decoding

May 12, 2026cs.CL

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acceleration, often improving decoding efficiency without substantially enhancing the model's underlying capability, and may even degrade performance under full diffusion decoding. In this work, we ask whether self-distilled trajectories can be used not merely for faster inference, but for genuine knowledge acquisition. Although these trajectories lie on the pretrained DLM's own distributional manifold and thus offer a potentially lower optimization barrier, we find that naively fine-tuning on them with standard NELBO objectives yields only marginal gains. To address this limitation, we propose \textbf{T}rajectory-\textbf{A}ligned optimization via \textbf{Bo}ltzmann \textbf{M}odeling (\textbf{TABOM}), a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference. TABOM models the inference unmasking preference as a Boltzmann distribution over predictive entropies and derives a tractable pairwise ranking objective to align the model's certainty ordering with the observed decoding trajectory. Empirically, TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.

Kecheng Chen, Ziru Liu, Xijia Tao +9

1City University of Hong Kong · 2Huawei Research · 3The University of Hong Kong

Diffusion Model Distillation Diffusion Model Fine-Tuning Diffusion Language Model Decoding Self-Distillation Diffusion Language Models Diffusion Language Model Distillation

May 12, 2026cs.LG

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward pass, enabling deeper drafters and longer accepted blocks. However, existing multi-token drafter objectives often use fixed position-dependent weighting schedules, such as head-dependent weights or block-position decays, which do not adapt as the positions limiting acceptance change during training. To address this, we derive per-position training weights from a differentiable surrogate of expected accepted draft length, matching the weight of each position to its log-probability gradient contribution. The resulting loss, D-PACE (Dynamic Position-Aware Cross-Entropy), shifts training signal toward positions that currently limit acceptance as the drafter improves. Across six benchmarks, two Qwen3-4B draft depths, two decoding temperatures, and two additional target models, D-PACE consistently improves both wall-clock speedup and average emitted length, with 2.3% measured training-time overhead and no changes to the drafter architecture or inference procedure.

Tianyu Wu, Yu Yao, Zhenting Qi +7

1Harvard · 2MIT

Speculative Decoding LLM Inference Acceleration Parallel Decoding Diffusion Language Model Decoding

May 12, 2026cs.CL

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations that carry meaning jointly. This one-token bottleneck limits both the expressiveness of the model during pre-training and its throughput at inference time. Existing remedies such as speculative decoding or diffusion-based language models either leave the underlying bottleneck intact or sacrifice the causal structure essential to language modeling. We propose BitLM, a language model that represents each token as a fixed-length binary code and employs a lightweight diffusion head to denoise multiple tokens in parallel within each block. Crucially, BitLM preserves left-to-right causal attention across blocks while making joint lexical decisions within each block, combining the reliability of autoregressive modeling with the parallelism of iterative refinement. By replacing the large-vocabulary softmax with bitwise denoising, BitLM reframes token generation as iterative commitment in a compact binary space, enabling more efficient pre-training and substantially faster inference without altering the causal foundation that makes language models effective. Our results demonstrate that the one-token-at-a-time paradigm is not a fundamental requirement but an interface choice, and that changing it can yield a stronger and faster language model. We hope BitLM points toward a promising direction for next-generation language model architectures.

Shaobin Zhuang, Yuang Ai, Jiaming Han +7

Shanghai Jiao Tong University · MMLab, The Chinese University of Hong Kong · Institute of Automation, Chinese Academy of Sciences +1

Multi-Token Prediction Autoregressive Language Modeling LLM Inference Acceleration Diffusion Language Model Decoding Diffusion Language Models

May 10, 2026cs.LG

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this advantage, most existing DLMs rely on a fixed generation length specified prior to decoding, which restricts their flexibility in real-world applications. While a few recent works attempt to support flexible-length generation, they typically suffer from notable limitations: some require costly retraining to accommodate variable-length outputs, while others depend solely on local confidence signals during decoding. Such local criteria fail to capture the evolving structure of the sequence, often resulting in suboptimal generation quality. In this paper, we propose a training-free, Bayesian structured decoding framework that formulates flexible-length generation as a dynamic structural inference problem. Our approach formulates flexible-length generation as a dynamic structural inference problem, jointly computing the expansion length, the block boundaries, and the decoding schedule. At each window expansion step, the method integrates local uncertainty with structural signals via a unified mechanism that supports dynamic structured generation, including both flexible block expansion and block organization, while maintaining coherence. Extensive experiments across multiple benchmarks demonstrate that our approach significantly improves generation quality and flexibility over existing fixed-length and flexible-length baselines. These results highlight the advantage of Bayesian structured decoding for diffusion language model, providing a principled and efficient solution for structured text generation.

Bian Sun, Kevin Zhai, Mubarak Shah +1

University of Central Florida

Diffusion Language Model Decoding Diffusion Language Models Text Generation

May 10, 2026cs.CL

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

May 10, 2026cs.CL

TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality. Existing acceleration methods often gain speed at the cost of accuracy. To address this limitation, we propose TAD, a Temporal-Aware trajectory self-Distillation framework. During data construction, we condition a teacher model on both the prompt and the ground-truth response to generate decoding trajectories, recording the intermediate masked states throughout the process. Based on how many decoding steps remain before each masked token is revealed, we partition masked positions into near and distant subsets. For near tokens, we train the student with a hard cross-entropy loss using the teacher trajectory tokens as labels, encouraging confident predictions for tokens that are about to be decoded. For distant tokens, we apply a soft KL divergence loss between the teacher and student token distributions, providing softer supervision and preserving future planning knowledge. This temporal-aware partition naturally gives rise to two deployment configurations: a Quality model that prioritizes accuracy and a Speed model that favors more aggressive acceleration. Experiments show that TAD consistently improves the accuracy-parallelism trade-off. On LLaDA, it raises average accuracy from 46.2% to 51.6% with the Quality model and average AUP from 46.2 to 257.1 with the Speed model. Our code is available at: https://github.com/BHmingyang/TAD

Haoyang Zhou, Li Kong, Shijie Ren +4

Gaoling School of Artificial Intelligence, Renmin University of China · Ant Group

Diffusion Model Distillation Diffusion Language Model Inference Diffusion Language Model Decoding Diffusion Language Models Diffusion Language Model Distillation

May 10, 2026cs.LG

Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Models

Diffusion language models (DLMs) offer a structural alternative to autoregressive generation: denoising can update tokens in arbitrary orders or in parallel rather than along a fixed left-to-right chain. In practice, fast DLM decoding remains strongly order-sensitive and often drifts toward autoregressive-like trajectories. We trace this tension to compatibility. At each reverse-time step, a DLM provides local denoising conditionals over the unresolved tokens. Arbitrary-order denoising becomes well defined when these local conditionals compose into order-invariant pseudo-joints. We formalize this view by defining order-induced pseudo-joints and a local denoising circulation: the log-ratio between the two pseudo-joints obtained by swapping a pair of unresolved positions. This circulation is zero under compatible conditionals, and global order gaps decompose into sums of local circulations along adjacent swaps. We further separate incompatibility-driven path dependence from conditional-dependence error in parallel updates and from order-specific estimation error. The resulting framework provides inference-only diagnostics for testing when DLM decoding is genuinely order-free.

Jeonseong Kim

Diffusion Language Model Inference Diffusion Language Model Decoding

May 9, 2026cs.LG

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence levels, which ensures negligible discrepancy between the marginal and joint distributions. However, the stringent confidence thresholds required to preserve accuracy severely constrain the scalability of parallelism. Through systematic token-level statistical analysis, we reveal that a substantial proportion of tokens converge to their correct predictions early in the denoising process yet fail to reach standard confidence thresholds, confirming that current confidence-based criteria are overly conservative. In response, we introduce LEAP (Lookahead Early-Convergence Token Detection for Accelerated Parallel Decoding). LEAP is a training-free, plug-and-play method that leverages future context filtering and multi-sequence superposition to detect early-converging tokens. By validating the alignment between early convergence and correctness, we enable reliable early decoding of these tokens. Benchmarking across diverse domains demonstrates that LEAP significantly lowers inference latency and decoding steps. Compared to confidence-based decoding, the average number of denoising steps is reduced by about 30%. On the GSM8K dataset, combining LEAP with dParallel accelerates decoding to 7.2 tokens per step while preserving model precision. LEAP effectively breaks the reliance on high-confidence priors, offering a novel paradigm for parallel decoding.

Haohui Zhang, Zhiye Wang, Xiaoying Gan +2

Shanghai Jiao Tong University

Parallel Decoding Diffusion Language Model Decoding Diffusion Model Inference Acceleration

May 8, 2026cs.LG

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply uniform intervention at every denoising step. We show this uniform schedule is inefficient and degrades quality, and the damage compounds when multiple attributes are steered jointly. To diagnose the failure, we train sparse autoencoders on four DLMs (124M-8B parameters) and find that different attributes commit on distinct schedules, varying in timing, sharpness, and magnitude. For instance, topic commits within the first 2% of denoising on MDLM, whereas sentiment emerges gradually over 20% of the process. Motivated by these profiles, we propose an adaptive scheduling mechanism that concentrates intervention where each attribute is actively forming. An idealized allocation analysis predicts that attributes with more sharply concentrated emergence benefit more from adaptive scheduling, a prediction we confirm empirically. Across seven single- and multi-attribute steering tasks on four DLMs, adaptive steering consistently improves the control-quality balance over uniform and interval-restricted baselines.

Hanhan Zhou, Shamik Roy, Rashmi Gangadharaiah

AWS AI Labs Santa Clara, CA 95054

Language Model Steering Diffusion Language Model Decoding Diffusion Timestep Scheduling Diffusion Language Models

May 8, 2026cs.CL

Fast Byte Latent Transformer

Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the Byte Latent Transformer (BLT) through new training and generation techniques. First, we introduce BLT Diffusion (BLT-D), a new model and our fastest BLT variant, trained with an auxiliary block-wise diffusion objective alongside the standard next-byte prediction loss. This enables an inference procedure that generates multiple bytes in parallel per decoding step, substantially reducing the number of forward passes required to generate a sequence. Second, we propose two extensions inspired by speculative decoding that trade some of this speed for higher generation quality: BLT Self-speculation (BLT-S), in which BLT's local decoder continues generating past its normal patch boundaries to draft bytes, which are then verified with a single full-model forward pass; and BLT Diffusion+Verification (BLT-DV), which augments BLT-D with an autoregressive verification step after diffusion-based generation. All methods may achieve an estimated memory-bandwidth cost over 50% lower than BLT on generation tasks. Each approach offers its own unique advantages, together removing key barriers to the practical use of byte-level LMs.

Julie Kallini, Artidoro Pagnoni, Tomasz Limisiewicz +5

FAIR at Meta · Stanford University · University of Washington

Speculative Decoding LLM Inference Acceleration Byte-Level Language Model Language Modeling Diffusion Language Model Decoding Diffusion Language Models

May 7, 2026cs.CL

CoBit: Language Modeling with Bitstream Diffusion

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion approaches have narrowed this gap. In this work, we further close the autoregressive gap by modeling text as a continuous diffusion process over fixed-width binary bitstreams. We refer to the resulting model as CoBit (Continuous Bitstream Diffusion). Our approach represents semantic tokens as analog bit sequences and uses a matched-filter residual parameterization to isolate contextual learning from analytic independent-bit posteriors. Crucially, we adopt a stochastic sampler that applies Langevin-type corrections gated by the entropy-rate profile, concentrating stochasticity in high-information regions while remaining nearly deterministic elsewhere. On LM1B, our 130M-parameter model reaches a generative perplexity (GenPPL) of 59.76 at matched real-data entropy (4.31) using 256 neural function evaluations (NFEs), outperforming prior DLM baselines and reaching the autoregressive reference. On OpenWebText (OWT), our sampler establishes a new continuous-DLM Pareto frontier, achieving GenPPL 27.06 at entropy 5.26 using 4x fewer steps than previous 1024-NFE baselines. Scaling the same recipe to a 462M-parameter model (CoBit-M) further improves the OWT GenPPL-entropy frontier over the 130M model (CoBit-S) and over medium-scale continuous and discrete DLM baselines, reaching GenPPL 19.5 at entropy 5.40, near real-data entropy (5.44), and approaching pretrained GPT-2 Medium over the high-quality region. As an additional benefit, bitstream diffusion removes the O(V) vocabulary scaling bottleneck of standard DLMs: by predicting O(log V) bitwise logits via semantic bit-patching, it lowers memory and raises throughput, a scalable paradigm as vocabulary sizes grow.

Georgios Batzolis, Mark Girolami, Luca Ambrogioni

Department of Engineering, University of Cambridge. · Devotion AI Labs Ltd. · Donders Institute for Brain, Cognition, and Behaviour, Radboud University.

Diffusion Language Model Decoding Diffusion Language Models Continuous Diffusion Language Models Diffusion Model Inference Acceleration Diffusion Models

May 5, 2026cs.LG

Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs

Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional autoregressive paradigm. However, this parallelism is constrained by the requirement of a fixed-size response length prior to generation. This architectural limitation imposes a severe trade-off: oversized response length results in computational waste on semantically meaningless padding tokens, while undersized response length causes output truncation requiring costly re-computations that introduce unpredictable latency spikes. To tackle this issue, we propose Predict-then-Diffuse, a simple and model-agnostic framework that enables compute-budgeted inference per input query by first estimating the response length and then using it to run inference with D-LLM. At its core lies an Adaptive Response Length Predictor (AdaRLP), which estimates the optimal response length given an input query. As a measure against under-estimating the response length and re-running inference with a higher value, we introduce a data-driven safety mechanism based on a small increase of the predicted length. As a whole, our framework avoids wasting computation on padding tokens, at the same time preserving output quality. Experimental validation on multiple datasets demonstrates that Predict-then-Diffuse significantly reduces computational costs (FLOP) compared to the default D-LLM inference mechanism, while being robust to skewed data distributions.

Michael Rottoli, Subhankar Roy, Stefano Paraboschi

Universit`a degli Studi di Bergamo, Italy

Diffusion Language Model Inference Diffusion Language Model Decoding

May 4, 2026cs.LG

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite their progress, the fixed-size block generations remain a critical bottleneck for effective and coherent reasoning. 1. From a global perspective, different reasoning tasks would correspond to different optimal decoding block sizes, which makes a ``one-size-fits-all'' assumption ineffective. 2. Even within a single reasoning task, the rigid block partitioning would break the logical flow and reduce reasoning coherence. Through empirical observations, we reveal that for block-wise entropy, incorrect reasoning exhibits a fluctuating and unsteady trend between blocks, whereas the correctly generated tasks follow a consistent descending trend. Therefore, this paper proposes b1, a novel post-training framework for dLLMs that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective with reinforcement learning to enhance reasoning coherence.b1 integrates seamlessly as a plug-and-play module with existing dLLM's post-training algorithms. Extensive experiments across various reasoning benchmarks showcase b1's consistent improvement over existing fixed-size block baselines. Our code has been released at https://github.com/YanJiangJerry/Block-R1.

Yan Jiang, Ruihong Qiu, Zi Huang

School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Queensland, Australia

Blockwise Diffusion Language Models Diffusion Language Model Decoding

May 2, 2026cs.CL

Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast

The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, current decoding strategies fail to leverage this capability, typically exhibiting a local preference that overlooks the heterogeneous information density within the context, ultimately degrading generation quality. To address this limitation, we systematically investigate high-information-density (HD) tokens and present two key findings: (1) explicitly conditioning on HD tokens substantially improves output quality; and (2) HD tokens exhibit an early-decoding tendency, converging earlier than surrounding tokens. Motivated by these findings, we propose Focus on the Core \textbf{(FoCore)}, a training-free decoding strategy that utilizes HD tokens in a self-contrast manner, wherein HD tokens are temporarily remasked as negative samples, to guide generation. We further introduce FoCore_Accelerate \textbf{(FoCore_A)}, an efficient variant that, upon detecting HD token convergence, performs parallel decoding over stable candidates within a local context window, substantially accelerating generation. Extensive experiments on math, code and logical reasoning benchmarks demonstrate that FoCore consistently improves generation quality and efficiency across both LLaDA and Dream backbones. For instance, on HumanEval, FoCore improves pass@1 from 39.02 to 42.68 over standard Classifier-Free Guidance, while FoCore-A reduces the number of decoding steps by 2.07x and per-sample latency from 20.76s to 8.64s (-58.4%).

Jinyuan Feng, Xin Yu, Yiqun Chen +5

Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Renmin University of China +1

Diffusion Language Model Inference Diffusion Language Model Decoding Contrastive Decoding Diffusion Model Inference Acceleration