Diffusion Language Models

Follow this topic Ask about this topic

Recent momentum

-72%

11 papers in the last 28 days · 0.3% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Diffusion Language Models.

Period ending 2026-09-07

7 new papers

A weekly snapshot of new work published in Diffusion Language Models.

256 papers

Latest in Diffusion Language Models

Open your feed →

Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling
Sep 15, 2026Lixuan Wei, Wei Zhou, Jianwen Wu +3Diffusion Language Models LLM Inference Efficiency
Register Tokens for Bounded-State Reasoning in Diffusion Language Models
Sep 14, 2026Albert Ge, Chandan Singh, Yufan Zhuang +3Diffusion Language Models
Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
Sep 14, 2026Sophia Tang, Shiyi WangDiffusion Language Models
Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models
Sep 14, 2026Shijian Xu, Andrea Miele, Metod Jazbec +3Diffusion Language Models Dataset Distillation
DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models
Sep 14, 2026Pengyu Ji, Zichen Zhang, Xiang Hu +1Diffusion Language Models
CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
Sep 14, 2026Blake Olson, Yuhang Song, Emmett McQuinn +1Diffusion Language Models Curriculum Reinforcement Learning
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
Sep 14, 2026Vaibhav Singh, Pierre-André Noël, Torsten Scholak +2Diffusion Language Models Large Language Model Decoding
Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models
Sep 12, 2026Yixiang Liu, Zhongxing Xu, Zhonghua Wang +1Vision-Language Model Reasoning Diffusion Language Models
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
Sep 7, 2026Xiang Zhang, Varchas Gopalaswamy, Rahman Ejaz +2Diffusion Language Models Sparsity
In-Place Instruction Following in Diffusion Language Models
Sep 7, 2026Zheng Nie, Zherui Li, Jiaming Zhang +3Diffusion Language Models Instruction-Tuned Large Language Models
Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges
Sep 7, 2026Chenqi Li, Minghui Min, Dusit Niyato +1Diffusion Language Models Low-Latency Systems
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Sep 3, 2026Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham +14Diffusion Language Models Speculative Decoding
Reliability Challenges in Diffusion Vision-Language Models
Sep 1, 2026Md. Atabuzzaman, Chris ThomasDiffusion Language Models Large Language Model Reliability
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Sep 1, 2026Shengfang Zhai, Leo Marchyok, Yuling Shi +4Membership Inference Diffusion Language Models
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models
Aug 31, 2026Guoli Wang, Haonan Shi, Tu Ouyang +1Diffusion Language Models Large Language Model Safety
CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
Aug 31, 2026Wail Bouhedja, Amr Mohamed, Guokan ShangDiffusion Language Models Generating
DiffPDE: Masked Diffusion Language Models as PDE Solver
Aug 31, 2026Wenxuan Guo, Yuyang Hong, Lubin Fan +4Neural Partial Differential Equation Solvers Partial Differential Equations
Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding
Aug 31, 2026Ephrem WuDrafter End-To-End Speedup
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Aug 12, 2026Yushi Ye, Xu Chen, Haoyun Jiang +7Diffusion Language Models LLM Inference Efficiency
Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning
Aug 11, 2026Yuhang CaoDiffusion Language Models Diffusion Models
Reducing Pretraining-Generation Mismatch in Diffusion Language Models
Aug 10, 2026Xiaocheng Lu, Huabin Liu, Song Guo +1Diffusion Language Models Pocket-Conditioned Diffusion
Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language Models
Aug 9, 2026Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas AgneeswaranDiffusion Language Models Generalizable Ranking Purpose
Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
Aug 8, 2026Xuning He, Zinan Sheng, Yongding Tao +4Diffusion Language Models Rollback
Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Models
Aug 8, 2026Fan Zhou, Weitian Wang, Tim Van de CruysClassifier-Free Guidance Masked Diffusion Language Models
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
Aug 7, 2026Elena Dumitrescu, Gert Lek, Lydia Y. Chen +1Large Language Model Safety Diffusion Language Models
Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion
Aug 7, 2026Eric Cullhed, Albin Thörn ClelandAncient Greek Unicode U+2014
Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
Aug 7, 2026Jiankun Wang, Yisen Gao, Ziwei Zhang +3Retrieval-Augmented Generation Diffusion Language Models
Retrofitting Linear Attention into Diffusion Language Models
Aug 6, 2026Jinha Kim, Younghun Roh, Jaeyeon KimDiffusion Language Models LLM Inference Efficiency
Lost in Interpolation: Why Predictive Feedback Fails in Diffusion Language Models
Aug 6, 2026Lavanya Nigam, Ishaan Bansal, Aryan Sood +2Masked Diffusion Language Models Diffusion Language Models
Answer First, Reason Later: Commitment Order in Diffusion LLMs
Aug 6, 2026Jewon Yeom, Jaewon Sok, Seonghyeon Park +3Diffusion Language Models LLM Reasoning Methods
Scaling Inherently Interpretable Language Models
Aug 6, 2026Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7Model Interpretability Methods Diffusion Language Models
Separating quantum circuits from classical LLMs
Aug 4, 2026Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi +1Quantum Circuits Large Language Model Quantization
MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models
Aug 4, 2026Tong Ling, Hang Lei, Feng Xiao +5Masked Diffusion Language Models Diffusion Language Models
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
Aug 4, 2026Fengqi Zhu, Shaoxuan Xu, Jingyang Ou +11Mixture-Of-Expert Language Models Large Language Model Scale
Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
Aug 4, 2026Angelo Nardone, Paolo FerraginaLarge Language Model Compression Model and Context Compression
OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models
Aug 3, 2026Xiaocheng Lu, Hualei Zhang, Shuhan Guo +8Diffusion Language Models On-Policy Distillation
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
Aug 3, 2026Jiajun Liang, Yucheng Liao, Yukang Cao +12Diffusion Language Models Diffusion Transformers
xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding
Aug 3, 2026Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim +4Speculative Decoding Diffusion Language Models
EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning
Aug 3, 2026Dongwei Sun, Bowen Yao, Yujie Zhang +3Dense Video Captioning Change Detection
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models
Aug 3, 2026Xiang Xia, Cheng Yan, Yiming Zhang +3Mixture-Of-Expert Inference Diffusion Language Models
Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models
Aug 3, 2026Wonseok Lee, Jimyeong Kim, Jungmin Ko +1Reinforcement Learning Rollouts Diffusion Language Models
DeltaFlow: Noise-Adaptive Bidirectional Gated Delta Networks for Embedded Language Flows
Aug 2, 2026Guangfu Guo, Xiaoqian Lu, Linsey Pang +4Diffusion Language Models Causal Attention
Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs
Aug 1, 2026Zhenhong Sun, Hanqing Zhao, Yatao Bian +7Mathematical Reasoning Diffusion Language Models
DiffusionGemma Technical Report
Jul 31, 2026DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41Diffusion Language Models Autoregressive Generation
CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference
Jul 31, 2026Yifan Wu, Yufeng Zhang, Kenli LiDiffusion Language Models Multiple Reasoning Trajectories
Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
Jul 31, 2026Yaoxuan Dou, Yang ShuDiffusion Language Models Training-Inference Mismatch
Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models
Jul 30, 2026Chia-Ming Lee, Shao-Kai Liu, Ming-Ching Chang +3Diffusion Language Models Adaptive Sampling
Beyond the Bidirectional Promise: Re-evaluating the Robustness of Diffusion Language Models
Jul 29, 2026Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas AgneeswaranDiffusion Language Models
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Jul 28, 2026Zhengtao Yao, Runhao Li, Xupeng Chen +12Diffusion Language Models Causal Attention
Rethinking the Generation Order of Block Diffusion Language Models
Jul 27, 2026Kai Syun Hou, James KwokDiffusion Language Models Autoregressive Decoding
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Jul 27, 2026Alexey Gavrilov, Alan-Barsag Gazzaev, Sergey MuravyovGenerative Quality Text Generation
Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising
Jul 24, 2026Dengyu Wu, Clement Ruah, Jiechen Chen +2Diffusion Language Models LLM Inference Efficiency
Multi-Mask Diffusion Language Models for Few-Step Generation
Jul 22, 2026Sijin Chen, Yinuo Ren, Heyang Zhao +3Masked Diffusion Language Models Diffusion Language Models
Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models
Jul 21, 2026Brian K Chen, Chong Wu, Kenji KawaguchiDiffusion Language Models Speculative Decoding
AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
Jul 21, 2026Yu-Yang Qian, Hao-Cong Wu, Chen Chen +4Speculative Decoding Diffusion Language Models
ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding
Jul 20, 2026Keuntae Kim, Beomseok Lee, Hyunwoo Kim +1Diffusion Language Models Vision-Language Model Reasoning
FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
Jul 20, 2026Bing Tian, Haikun Liu, Xiaocheng Zhong +5Diffusion Language Models Parallel Decoding and Training
Trace-Based On-Policy Distillation for Masked Diffusion Language Models
Jul 18, 2026Haolin Ren, Ziyang Huang, Chenhao Yuan +2Diffusion Language Models Masked Diffusion Language Models
Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models
Jul 17, 2026Andy Catruna, Emilian RadoiMasked Diffusion Language Models Diffusion Language Models
Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models
Jul 17, 2026Yingqian Cui, Wei Deng, Lantao Mei +4Diffusion Language Models Masked Diffusion Language Models

Sep 15, 2026 · cs.CLJ/K move · Enter open · S save

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

Lixuan Wei, Wei Zhou, Jianwen Wu, Yipeng Shen+2

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.

Diffusion Language Models LLM Inference Efficiency

Open paper Ask about it PDF