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. Adaptation to Intrinsic Dependence in Diffusion Language Models

    Feb 23, 2026Yunxiao Zhao, Changxiao CaiDiffusion Language Model InferenceDiffusion Language Models

  2. IDLM: Inverse-distilled Diffusion Language Models

    Feb 22, 2026David Li, Nikita Gushchin, Dmitry Abulkhanov +4Diffusion Language Model InferenceDiffusion Language Model Distillation

  3. Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance

    Feb 20, 2026Junde Wu, Minhao Hu, Jiayuan Zhu +7Diffusion Language ModelsDiffusion Language Model Decoding

  4. Sink-Aware Pruning for Diffusion Language Models

    Feb 19, 2026Aidar Myrzakhan, Tianyi Li, Bowei Guo +2LLM PruningDiffusion Model Pruning

  5. Scaling Beyond Masked Diffusion Language Models

    Feb 16, 2026Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang +4Diffusion Language ModelsDiffusion Models

  6. DAWN: Dependency-Aware Fast Inference for Diffusion LLMs

    Feb 6, 2026Lizhuo Luo, Zhuoran Shi, Jiajun Luo +4Diffusion Language Model InferenceDiffusion Language Model Decoding

  7. Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

    Feb 2, 2026Ziwei Luo, Ziqi Jin, Lei Wang +2Diffusion Language Model InferenceDiffusion Language Model Decoding

  8. ILRR: Inference-Time Steering Method for Masked Diffusion Language Models

    Jan 29, 2026Eden Avrahami, Eliya NachmaniMasked Diffusion ModelsLanguage Model Steering

  9. Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching

    Jan 28, 2026Fengrui Zuo, Zhiwei Ke, Yiming Liu +3Diffusion Language Model InferenceToken Pruning

  10. Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

    Jan 25, 2026Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo +4Adaptive InferenceBlockwise Diffusion Language Models

  11. Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models

    Jan 6, 2026Seunghwan Jang, Wonje Jeung, SooJean HanMarkov ModelsDiffusion Sampling

  12. CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

    Jan 5, 2026Yihao Liang, Ze Wang, Ximeng Sun +7Diffusion Language Model InferenceDiffusion Language Model Decoding

  13. A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

    Nov 19, 2025Duo Li, Zuhao Yang, Xiaoqin Zhang +2Multimodal Large Language ModelsDiffusion Language Model Inference

  14. Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

    Oct 13, 2025Qinglin Zhu, Yizhen Yao, Runcong Zhao +8Diffusion Language Model DecodingDiffusion Language Model Inference

  15. ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

    Oct 6, 2025Wonjun Kang, Kevin Galim, Seunghyuk Oh +8Diffusion Language Model InferenceParallel Decoding

  16. Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture

    Jun 24, 2025Shuchen Xue, Tianyu Xie, Tianyang Hu +5Masked Diffusion ModelsDecoder-Only Language Models