Diffusion Language Model Inference

Ask about this topic

Overview

Diffusion language model inference studies how masked or continuous text representations can be refined over multiple steps, often updating many tokens in parallel rather than generating strictly left to right. Common approaches adapt which tokens to reveal or commit, reuse cached attention and activations, prune redundant computation, and use speculative decoding or verification to reduce denoising steps. Evaluation spans reasoning and code benchmarks, long-context tasks, multimodal generation, and serving measures such as latency, throughput, and energy use. The central tension is that more parallelism and caching can save computation but may harm coherence or accuracy, so current work seeks adaptive methods that balance speed with reliable generation across tasks and hardware.

Latest papers

CardsList

179 papers38 papers in the last four weeks, up 90% on the four weeks before. 0.2% of all new papers.

  1. DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling

    May 22, 2026Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis +3Diffusion Language ModelsDiffusion Language Model Distillation

    NVIDIA

  2. Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

    May 21, 2026Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel +4Masked Diffusion ModelsDiffusion Language Model Inference

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

  3. PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models

    May 20, 2026Yanyi Lyu, Letian Chen, Futing Sun +3Self-AttentionDiffusion Language Model Inference

    Harbin Institute of Technology (Shenzhen)

  4. TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

    May 19, 2026Zhiben Chen, Youpeng Zhao, Yang Sui +2Expert OffloadingLLM Inference Scheduling

    University of Central Florida · Rice University

  5. Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs

    May 18, 2026Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3Masked Diffusion ModelsLong-Context Language Modeling

    Tsinghua University · Shanghai Jiao Tong University · Infinigence AI

  6. Prefix-Adaptive Block Diffusion for Efficient Document Recognition

    May 16, 2026Mingxu Chai, Ziyu Shen, Chenyu Liu +9Diffusion Language Model InferenceDiffusion Model Caching

    Computation and Artificial Intelligence Innovative College, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · ByteDance, Shanghai, China

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

    May 15, 2026Shengyin Sun, Yiming Li, Renxi Liu +7Parallel Speculative DecodingMasked Diffusion Models

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

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

    May 14, 2026Xun Fang, Yunchen Li, Hang Yuan +1Speculative Decoding for Diffusion Language ModelsDiffusion Language Model Inference

    East China Normal University · Beijing Zhongguancun Academy

  9. Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models

    May 13, 2026Yejin Lee, Ungsik Kim, Yo-Sub HanAdversarial Attacks on LLMsDiffusion Language Model Inference

    Department of Computer Science, Yonsei University, Seoul 03722, Republic of Korea · Department of Computer Science and Engineering, Gyeongsang National University, Jinju 52828, Republic of Korea

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

    May 12, 2026Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham +3Language Model DecodingDiffusion Language Model Inference

    University of Oregon · Google DeepMind · Adobe Research

  11. Multi-Token Residual Prediction

    May 12, 2026Yufeng Xu, Zishuo Bao, Qian Wang +6Masked Diffusion ModelsMulti-Token Prediction

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

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

    May 10, 2026Haoyang Zhou, Li Kong, Shijie Ren +4Diffusion Model DistillationDiffusion Language Model Inference

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

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

    May 10, 2026Jeonseong KimDiffusion Language Model InferenceDiffusion Language Model Decoding

  14. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

    May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +3Flow MatchingDiffusion Language Model Inference

    1The Ohio State University · 2Apple

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

    May 5, 2026Michael Rottoli, Subhankar Roy, Stefano ParaboschiDiffusion Language Model InferenceDiffusion Language Model Decoding

    Universit`a degli Studi di Bergamo, Italy

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

    May 2, 2026Jinyuan Feng, Xin Yu, Yiqun Chen +5Diffusion Language Model InferenceDiffusion Language Model Decoding

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

  17. DARE: Diffusion Language Model Activation Reuse for Efficient Inference

    May 1, 2026Natalia Frumkin, Bokun Wang, Hung-Yueh Chiang +3Self-AttentionDiffusion Language Model Inference

    Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin · Cornell University

  18. When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models

    Apr 27, 2026Danny Wang, Ruihong Qiu, Zi HuangBlockwise Diffusion Language ModelsDiffusion Language Model Inference

    The University of Queensland

  19. R2R^2-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

    Apr 21, 2026Zhenbang Du, Kejing Xia, Xinrui Zhong +6Diffusion Language Model InferenceDiffusion Model Fine-Tuning

    Georgia Institute of Technology · NVIDIA

  20. Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

    Apr 17, 2026Jiaoyang Ruan, Xin Gao, Yinda Chen +5Diffusion Model AlignmentDiffusion Language Model Inference

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · University of Science and Technology of China, Hefei, China +1

  21. DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference

    Apr 17, 2026Xiang Xia, Wuyang Zhang, Jiazheng Liu +2Diffusion Language Model InferenceParallel Decoding

    University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

  22. Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

    Apr 16, 2026Aihua LiNon-Autoregressive Text GenerationFlow Matching

    Duke University

  23. Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models

    Apr 15, 2026Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +5Diffusion Language ModelsDiffusion Language Model Inference

    Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, USA · Department of Computer Science & Engineering, Texas A&M University, College Station, USA · Department of Biochemistry, Case Western Reserve University, Cleveland, USA +2

  24. LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models

    Apr 13, 2026Haocheng Xi, Harman Singh, Yuezhou Hu +9Diffusion Language Model InferenceDiffusion Model Inference Acceleration

    University of California, Berkeley · FuriosaAI · ICSI +2

  25. Introspective Diffusion Language Models

    Apr 13, 2026Yifan Yu, Yuqing Jian, Junxiong Wang +12Diffusion Language ModelsDiffusion Language Model Decoding

    Together AI · University of Illinois Urbana-Champaign · Princeton University +2

  26. Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models

    Apr 12, 2026Zhengnan Guo, Fei TanHallucination in Language ModelsDiffusion Language Models

    East China Normal University · Zhejiang University of Technology

  27. From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons

    Apr 11, 2026Xiangyu Ma, Teng Xiao, Zuchao Li +1Diffusion Language ModelsDiffusion Language Model Inference

    School of Artificial Intelligence, Wuhan University, Wuhan, China · School of Computer Science, Wuhan University, Wuhan, China

  28. ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

    Apr 10, 2026Lifeng Chen, Tianqi You, Hao Liu +8Radiology Report GenerationRadiology VLMs

    AIRC, Midea Group · Beijing Jiaotong University · Dalian University of Technology

  29. FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation--Full Version

    Apr 7, 2026Dat Nguyen-Cong, Tung Kieu, Hoang Thanh-TungDiffusion Language Model InferenceContinuous Diffusion Language Models

    FPT Software AI Center, FPT Corporation · Department of Computer Science, Aalborg University, Denmark · Quantum AI and Cyber Security Institute, FPT Corporation

  30. DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models

    Apr 6, 2026Satyam Goyal, Kushal Patel, Tanush Mittal +1Diffusion Language Model InferenceSpeculative Decoding for Diffusion Language Models

    Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA.