Adaptive Computation for Diffusion Models

Latest papers

23 papers10 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

DUET: Dual-Sparse Inference for Block Diffusion Language Models
Nov 6, 2026Siyuan Yan, Shen Gu, Xiaoxing Ma +2Diffusion Language Model Inference Diffusion Model Inference Acceleration
State Key Laboratory for Novel Software Technology, Nanjing University, China
Scene-Adaptive Readout and Decoding in Diffusion Driving VLAs
Nov 1, 2026Seungjun Yu, Jiho Choi, Inha Kang +3Diffusion-Based VLA Models Vision-Language-Action Models
Korea Advanced Institute of Science and Technology (KAIST)
TDLM: Adaptive Temporal Integration for Diffusion Language Models
Oct 27, 2026Bohang Sun, Max Zhu, Francesco Caso +3Diffusion Language Models Diffusion Language Model Inference
Department of Computer Science and Technology, University of Cambridge · Department of Engineering Science, University of Oxford
TriTile: Three-Tier Attention for Video Diffusion Transformers
Oct 26, 2026Yeonjae Kim, Omin Kwon, Seong Hoon Seo +1Diffusion Model Inference Acceleration Video Diffusion Models
Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea.
MoDDiT: Simple Token Routing in Diffusion Transformers
Oct 20, 2026Jarek Liesen, Matthew T. Jackson, Benjamin Ellis +2Diffusion Transformer Adaptive Computation for Diffusion Models
British Open-ended Learning and Discovery
TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling
Oct 19, 2026Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu +5Diffusion Sampling Diffusion Model Inference Acceleration
The Hong Kong University of Science and Technology (Guangzhou) · University of Electronic Science and Technology of China · The Hong Kong University of Science and Technology +2
Diffusion Language Models Change Speed Across Tasks and Languages
Oct 19, 2026Mohsen Fayyaz, Ali Modarressi, Daniel Israel +2Diffusion Language Models Diffusion Language Model Inference
University of California, Los Angeles · CIS, LMU Munich · Munich Center for Machine Learning
Functional Cross-layer Experts Routing for One-step Diffusion Distillation
Oct 19, 2026Zile Huang, Ser-nam LimDiffusion Model Distillation Diffusion Distillation
University of Central Florida
PV-Decoding: Progressive Verification Decoding with Decode Gating for Diffusion Language Models
Oct 17, 2026Renxi Liu, Yiming Li, Shengyin Sun +8Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding
Huawei Technologies · City University of Hong Kong
ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
Oct 8, 2026Zekai Gu, Peng Wang, Jiahao Lu +3Adaptive Computation for Diffusion Models Video Diffusion Models
HKUST · VAST · Macau University of Science and Technology
CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
Oct 8, 2026Qinhan Lyu, Jusheng Zhang, Zhixing Zhang +4Adaptive Computation for Diffusion Models Diffusion Model Caching
Sun Yat-sen University
ALoDLM: Adaptively Looped Diffusion Language Models
Oct 3, 2026Liancheng Fang, Zhuowei Li, Youngeun Kim +10Adaptive Computation for Diffusion Models Diffusion Language Models
University of Illinois Chicago · Amazon AGI · Korea University
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
Sep 28, 2026Chong Wang, Zixuan Fu, Shiqi Huang +3Diffusion Transformer Diffusion Guidance
Nanyang Technological University · KTH Royal Institute of Technology · Hebei University of Technology
FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving
Jul 13, 2026Yaqi Qiao, Ping He, Songrun Xie +4Diffusion Model Serving Adaptive Computation for Diffusion Models
University of Illinois Urbana-Champaign · Vanderbilt University · HKUST +2
LESS Is More: Mutual-Stability Sampling for Diffusion Language Models
Jun 15, 2026Amr Mohamed, Guokan Shang, Michalis VazirgiannisMasked Diffusion Models Diffusion Language Model Decoding
1MBZUAI · 2Ecole Polytechnique
SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding
Jun 3, 2026Na Li, Chengda Wang, Mingju Gao +1Diffusion Language Model Inference Adaptive Computation for Diffusion Models
School of Computer Science, Peking University
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
May 29, 2026Zekai Li, Ji Liu, Yiqing Huang +3Adaptive Computation for Diffusion Models Diffusion Language Model Decoding
Advanced Micro Devices, Inc. (AMD)
PARE: Pruning and Adaptive Routing for Efficient Video Generation
May 26, 2026Yutong Wang, Yunke Wang, Tianfan Xue +4Video Diffusion Models Diffusion Transformer
The University of Sydney · The Chinese University of Hong Kong · Shanghai AI Laboratory
Token Time Continuous Diffusion for Language Modeling
May 7, 2026Parikshit Bansal, Sujay SanghaviContinuous Diffusion Language Models Diffusion Language Model Decoding
UT Austin
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
Mar 12, 2026Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +6Adaptive Computation for Diffusion Models Diffusion Transformer
Rice University · Snap Inc.
Diffusion Language Models Are Natively Length-Aware
Mar 6, 2026Vittorio Rossi, Giacomo Cirò, Davide Beltrame +3Adaptive Computation for Diffusion Models Diffusion Language Models
Department of Computing Sciences, Bocconi University, Milan, Italy.
TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
Mar 4, 2026Haowei Zhu, Tingxuan Huang, Xing Wang +7Diffusion Model Acceleration Diffusion Model Inference Acceleration
Tsinghua University · ByteDance
TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
Dec 13, 2025Ye Li, Jiahe Feng, Yuan Meng +9Diffusion Policy Adaptive Computation for Diffusion Models
Tsinghua University

Nov 6, 2026J/K move · Enter open · S save

DUET: Dual-Sparse Inference for Block Diffusion Language Models

Siyuan Yan, Shen Gu, Xiaoxing Ma, Chun Cao+1

State Key Laboratory for Novel Software Technology, Nanjing University, China

Diffusion Language Model Inference Diffusion Model Inference Acceleration Adaptive Computation for Diffusion Models Blockwise Diffusion Language Models Sparse Attention

Open paper AskPDF arXiv

Diffusion language models (DLMs) enable parallel token generation through iterative denoising, yet their inference remains costly due to repeated attention over a growing historical prefix and repeated processing of the entire current generation block. Historical attention becomes increasingly expensive as generation progresses, while all current-block positions are propagated through the Transformer at every denoising step even though only a small fraction are typically resolved at that step. In this paper, we introduce Duet, a training-free dual-sparse inference framework that addresses these challenges through prefix Key-Value (KV) sparsity and early query sparsity, respectively. Specifically, Duet exploits the concentration and cross-step stability of historical attention within each generation block to construct a compact historical KV subset that is reused across denoising steps. For query sparsity, Duet predicts update positions from shallow representations and propagates only the corresponding queries through the suffix Transformer layers, avoiding deep computation at positions unlikely to be updated in the current step. Experiments show that Duet maintains competitive accuracy while achieving 1.34

\times

/2.83

\times

end-to-end/per-step speedups on LLaDA2.1-mini and 2.41

\times

/4.72

\times

on SDAR-8B-Chat-b32 at a 32K context length.