Diffusion Language Model Inference

Follow this topic Ask about this topic

Momentum

26 papers in the last four weeks, up 767% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 108

All topics

Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
Aug 8, 2026Xuning He, Zinan Sheng, Yongding Tao +4Diffusion Language Model Inference Diffusion Model Caching
School of Computer Science, Shanghai Jiao Tong University · College of Artificial Intelligence, Nankai University · School of Computer Science, Peking University
Retrofitting Linear Attention into Diffusion Language Models
Aug 6, 2026Jinha Kim, Younghun Roh, Jaeyeon KimBlockwise Diffusion Language Models Diffusion Language Model Inference
Apple · *Work done at MIT · Google DeepMind +1
Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
Aug 4, 2026Angelo Nardone, Paolo FerraginaDiffusion Language Model Inference Diffusion Language Models
University of Pisa, Department of Computer Science, Pisa, Italy · Scuola Superiore Sant’Anna, Pisa, Italy
xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding
Aug 3, 2026Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim +4Speculative Decoding for Diffusion Language Models Speculative Decoding
University of Illinois Urbana-Champaign · IBM
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models
Aug 3, 2026Xiang Xia, Cheng Yan, Yiming Zhang +3Expert Load Balancing Mixture-of-Experts Inference
University of Science and Technology of China, Hefei, China
CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference
Jul 31, 2026Yifan Wu, Yufeng Zhang, Kenli LiDiffusion Model Serving Diffusion Language Model Inference
College of Computer Science, Hunan University Changsha 410082, China
Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
Jul 31, 2026Yaoxuan Dou, Yang ShuMultimodal Large Language Models Diffusion Language Model Inference
School of Mathematics and Statistics, Beijing Institute of Technology Beijing, China
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 Model Inference Diffusion Language Model Decoding
National Yang Ming Chiao Tung University · University at Albany, SUNY
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
Jul 29, 2026Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4Masked Diffusion Models Diffusion Language Model Inference
University of Texas at Austin · Harvard University
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Jul 27, 2026Alexey Gavrilov, Alan-Barsag Gazzaev, Sergey MuravyovVector-Quantized Variational Autoencoder Diffusion Language Model Inference
ITMO University Saint-Petersburg, Russia
Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation
Jul 16, 2026Qicheng Zhao, Qi Sun, Zheyu YanActivation Sparsity Diffusion Language Model Inference
Zhejiang University
Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
Jul 14, 2026Daehoon Gwak, Minhyung Lee, Junwoo Park +1Masked Diffusion Models Inference-Time Scaling
KAIST AI · Yonsei University
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
Jul 8, 2026Meihua Dang, Stefano ErmonConstrained Generative Modeling Constrained Decoding
Stanford University
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack
Jul 5, 2026Nitin Kedia, Saurabh Agarwal, Myungjin Lee +1LLM Inference Scheduling LLM Inference Serving
The University of Texas at Austin Austin, United States · Cisco Research Bellevue, United States
TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decoding
Jul 3, 2026Chengcheng Wang, Tingzhang Luo, Wenhao Li +2Diffusion Language Model Inference Diffusion Language Model Decoding
University of Sydney · City University of Hong Kong
Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
Jul 2, 2026Pranshu Chaturvedi, Parth Shroff, Tarun Suresh +2Mamba Long-Context Language Model Inference
Stanford University
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
Jul 1, 2026Zhuoxuan Zhang, Kangqi Ni, Yuhang Chen +12Blockwise Diffusion Language Models Efficient Language Model Reasoning
Yang · 2UNC Chapel Hill · 1Meta AI
Low Perplexity is Repetition: A One-Dimensional Self-Conditioning Attractor in Continuous Diffusion LMs
Jul 1, 2026Shuai Zhang, Zijie Chen, Hongliang He +2Language Model Generation Evaluation Diffusion Language Model Inference
Zhejiang University · Westlake University · Ant Group
DiLaServe: High SLO Attainment Serving for Diffusion Language Models
Jun 27, 2026Tzu-Tao Chang, Benjamin Yuanyang Hong, Kiet Pham +1LLM Serving Diffusion Model Serving
University of Wisconsin-Madison USA
Affix Cache for Diffusion Large Language Models
Jun 26, 2026Kaihua Liang, An Zhong, Xin Tan +4KV Caching Memory-Efficient Inference
KAUST · CUHK · LUMS
Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation
Jun 26, 2026Yuhang Chen, Xianfeng Wu, Jinhao Duan +11Diffusion Language Model Inference Parallel Decoding
University of North Carolina at Chapel Hill · Meta AI
Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context
Jun 25, 2026Fitsum Reda, John Kamalu, Roger Waleffe +3Autoregressive Diffusion Blockwise Diffusion Language Models
NVIDIA
Improved Large Language Diffusion Models
Jun 24, 2026Shen Nie, Qiyang Min, Shaoxuan Xu +7Language Model Pretraining Masked Diffusion Models
Gaoling School of Artificial Intelligence, Renmin University of China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +1
HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval
Jun 19, 2026Omin Kwon, Doyeon Kim, Jongseok Park +3KV-Cache Offloading Diffusion Model Serving
Seoul National University Seoul, Republic of Korea · UC Berkeley Berkeley, CA, USA
Diffusion Language Models: An Experimental Analysis
Jun 17, 2026Thomas Bertolani, Davide Bucciarelli, Leonardo Zini +2Diffusion Language Model Inference Diffusion Language Model Decoding
University of Modena and Reggio Emilia, Italy · University of Pisa, Italy
DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models
Jun 17, 2026Zirui Wu, Lin Zheng, Jiacheng Ye +5Blockwise Diffusion Language Models Efficient Language Model Reasoning
The University of Hong Kong · Peking University
VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination
Jun 16, 2026Chunyu Liu, Zhengyang Fan, Kaisen Yang +1Masked Diffusion Models Diffusion Language Model Inference
Tsinghua University
Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens
Jun 15, 2026Yizhen Yao, Qinglin Zhu, Runcong Zhao +4Diffusion Language Model Inference Diffusion Language Model Decoding
King’s College London · The Chinese University of Hong Kong · The Alan Turing Institute, UK
Efficient On-Device Diffusion LLM Inference with Mobile NPU
Jun 11, 2026Tuowei Wang, Yanfan Sun, Ju RenAI Accelerator Inference On-Device Language Model Inference
Beihang University China · Tsinghua University China
Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models
Jun 9, 2026Jing Xiong, Qi Han, Shansan Gong +5Long-Context Language Model Inference Diffusion Language Model Inference
The University of Hong Kong · University of Michigan, Ann Arbor · LMSYS Org

Aug 8, 2026, cs.CLJ/K move · Enter open · S save

Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

Xuning He, Zinan Sheng, Yongding Tao, Huanyu Liu+3

School of Computer Science, Shanghai Jiao Tong University · College of Artificial Intelligence, Nankai University · School of Computer Science, Peking University

Diffusion Language Model Inference Diffusion Model Caching Diffusion Language Models Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irreversible autoregressive generation, but makes inference costly. Every denoising update alters the global context, forcing both prompt and response states to be recomputed even though only response tokens are revisable. Key-value (KV) caching could reduce this cost, yet conventional caching assumes immutable historical states and is therefore difficult to reconcile with rollback. In this paper, we introduce Adaptive Reuse of Cached Hidden States for Efficient Rollback (Archer), a training-free KV caching method for rollback-capable DLMs. Archer asymmetrically keeps the mutable response synchronized with the current hypothesis while reusing prompt K/V within a bounded state neighborhood. Although prompt representations also change under bidirectional attention, their token identities remain fixed; bounded reuse therefore amortizes repeated prompt computation without caching mutable response states. It also delays feedback from tentative tokens, reducing premature reinforcement of transient high-confidence errors and giving rollback more opportunity to correct them. Our analysis characterizes prompt reuse as a reversibility-aligned cache boundary, bounds its state-dependent approximation error, and gives a decoder-margin condition for preserving full-refresh decisions. Existing DLM acceleration often trades quality for speed. Archer shifts this frontier, attaining the best mean performance of 33.63% together with a 2.57x mean speedup on the main suite. Across evaluated settings, it improves Pass@1 by up to 3.05 points and reaches up to 2.95x speedup. Controlled analyses connect the quality gain to delayed prompt feedback and validate state-aware refresh. Our code is available at https://github.com/Hxnng/Archer.

Momentum

Related topics

Latest papers 108