Diffusion Language Model Inference

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

201 papers31 papers in the last four weeks, down 6% on the four weeks before. 0.2% of all new papers.

  1. ReMaRL: Learning to Unmask and Remask in Frozen Diffusion Language Models

    Nov 17, 2026Egor Shibaev, Danila Biktimirov, Ivan Klimov +3Diffusion Language Model InferenceDiffusion Language Model Decoding

  2. DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding

    Nov 16, 2026Jameson Sandler, Shane Bergsma, Mostafa Elhoushi +5Speculative DecodingLLM Inference Acceleration

  3. The Hidden Cost of MoE Diffusion Decoding: Profiling and Fixing the Sampler

    Nov 16, 2026Harshit Samrat, Ramakrishna Paramahamsa KompellaDiffusion Language Model InferenceDiffusion Language Model Decoding

  4. Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers

    Nov 14, 2026Sofian Zalouk, Vincent Counathe, Paul Jünger +4Masked Diffusion ModelsDiffusion Language Models

  5. Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models

    Nov 10, 2026Amir Mann, Jonathan Fhima, Shaked Brody +4Diffusion Language Model InferenceBlockwise Diffusion Language Models

  6. DUET: Dual-Sparse Inference for Block Diffusion Language Models

    Nov 6, 2026Siyuan Yan, Shen Gu, Xiaoxing Ma +2Diffusion Language Model InferenceDiffusion Model Inference Acceleration

  7. D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding

    Nov 4, 2026Baoyou Chen, Ruiqiao Mei, Guancong Lin +4Speculative DecodingSpeculative Decoding for Diffusion Language Models

  8. Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

    Oct 31, 2026Zhichen Zeng, Xichong Zhang, Junpan Wu +7Diffusion Language Model InferenceDiffusion Language Models

  9. RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models

    Oct 30, 2026Guangfu Guo, Xiaoqian Lu, Linsey Pang +4Long-Context Language ModelingDiffusion Language Model Inference

  10. KV Cache Quantization for Diffusion Language Models

    Oct 29, 2026Yan Tai, Yunan Ding, Guangzhao Li +5KV-Cache QuantizationDiffusion Language Model Inference

  11. DWISE: Denoising Workload-Informed Scheduling Engine

    Oct 29, 2026Lie Li, Wen Li, Junxiao Shen +2Diffusion Model ServingDiffusion Language Model Inference

  12. TDLM: Adaptive Temporal Integration for Diffusion Language Models

    Oct 27, 2026Bohang Sun, Max Zhu, Francesco Caso +3Diffusion Language ModelsDiffusion Language Model Inference

  13. Birth, Death and Diff: Insertion-Based Sequence Generation with Corrections

    Oct 25, 2026Durga Prasad Maram, Dhruvesh Patel, Tahira Naseem +4Diffusion Language ModelsText Generation

  14. How To Build A Modern Diffusion Language Model

    Oct 24, 2026Volodymyr Kuleshov, Marianne Arriola, Yair Schiff +2Diffusion Language ModelsDiffusion Language Model Inference

  15. SetCommit: Coordinated Token Commitments for Few-Step Diffusion Language Model Decoding

    Oct 22, 2026Yuannuo Feng, Yubing Ye, Wenshuai Yao +4Diffusion Language Model InferenceDiffusion Language Models

  16. DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding

    Oct 22, 2026Shidong Cao, Jing Ma, Wenhao Chai +3Constrained DecodingGrammar-Constrained Decoding

  17. Random Remasking Scales Masked Diffusion Inference

    Oct 22, 2026Zhaoyi Zhou, Frank Wu, Andrea ZanetteMasked Diffusion ModelsDiffusion Language Model Inference

  18. Loopholing All the Way: Language Modeling with pure Self-Conditioning

    Oct 21, 2026Adrien Deschenaux, Nadezhda Ilieva, Justin Deschenaux +6Diffusion Language ModelsContinuous Diffusion Language Models

  19. Looped Uniform Diffusion Language Models

    Oct 21, 2026Saiteja Utpala, Chieh-Hsin Lai, Yuki Mitsufuji +1Diffusion Language ModelsDiffusion Language Model Training

  20. DiffResearch: Accelerating Deep Research with Diffusion Language Models

    Oct 20, 2026Alan-Barsag Gazzaev, Alexey Gavrilov, Mikhail Mozikov +1Diffusion Language ModelsDiffusion Language Model Decoding