Diffusion Model Inference Acceleration

Follow this topic Ask about this topic

Momentum

40 papers in the last four weeks, up 100% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 335

All topics

Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization
Jun 5, 2026Shigui Li, Delu ZengFew-Step Diffusion Sampling Diffusion Model Inference Acceleration
School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
Jun 4, 2026Chensheng Dai, Shengjun Zhang, Yifan Li +3Video Diffusion Models Diffusion Transformer
1Tsinghua University · 2GigaAI
Tracing the Oracle: Improving Diffusion Timestep Scheduling for 3D CT Reconstruction
Jun 4, 2026Yujia Wu, Zhaoqiang LiuDiffusion Sampling Few-Step Diffusion Sampling
The authors are with the School of Computer Science and Engineering, University of Electronic Science and Technology of China.
ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE
Jun 4, 2026Mishan Aliev, Eva Neudachina, Ilya Bykov +4Diffusion Model Caching Diffusion Model Inference Acceleration
1HSE University, Russia · 2Yandex Research, Russia
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
Jun 4, 2026Yoshiyuki OotaniVideo Diffusion Models Video Editing
Independent Researcher
Flash-WAM: Modality-Aware Distillation for World Action Models
Jun 3, 2026Arman Akbari, Ci Zhang, Arash Akbari +6Video Diffusion Models Action-Conditioned World Models
1Northeastern University · University of Georgia · 3EmbodyX Inc.
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
Jun 3, 2026Thanh-Tung Le, Yunhan Zhao, Menglei Chai +5Autoregressive Diffusion Real-Time Interactive Video Generation
University of California, Irvine · Google · Google DeepMind
Supportive Token Revealing for Fast Diffusion Language Model Decoding
Jun 2, 2026Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez +4Masked Diffusion Models Diffusion Language Model Decoding
Department of Computer Science, University of Haifa · Institute for AI, University of Stuttgart · IMPRS-IS
RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction
Jun 2, 2026Zixuan Guo, Xiucheng Wang, Nan ChengFew-Step Diffusion Sampling Wireless Communications
School of Physics, Xidian University, Xi’an, 710071, China · State Key Laboratory of ISN and School of Telecommunications Engineering, Xidian University, Xi’an, 710071, China
Fast-dLLM++: Fréchet Profile Decoding for Faster Diffusion LLM Inference
Jun 1, 2026Siva Rajesh Kasa, Yasong Dai, Sumit Negi +1Language Model Decoding Parallel Decoding
Amazon Inc. · School of Computing, Australian National University.
FLARE: Diffusion for Hybrid Language Model
Jun 1, 2026Yuchen Zhu, Jing Shi, Chongjian Ge +9Diffusion Model Serving Diffusion Language Model Inference
1Adobe Research · 2Georgia Institute of Technology
GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
May 31, 2026Guanyu Zhou, Yao Liu, Yanglei Gan +5Event Time Prediction Temporal Point Processes
University of Electronic Science and Technology of China, Chengdu, China
Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
May 30, 2026Byoungwoo Park, Utkarsh A. Mishra, Jaemoo Choi +2Diffusion-Based Planning Long-Horizon Video Generation
KAIST
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
May 30, 2026Hyundong Jin, Yo-Sub HanParallel Decoding Diffusion Language Model Decoding
Yonsei University, Seoul, Republic of Korea
Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
May 30, 2026Jinyang Du, Shenghao Jin, Ziqian Xu +5Video Diffusion Models Diffusion Model Quantization
SenseTime
TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
May 30, 2026Zhuoyu Wang, Junnan Huang, Xinyu ChenTree Search Speculative Decoding
The Hong Kong University of Science and Technology (Guangzhou)
Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
May 29, 2026Jiacheng Lu, Haoyi Zhu, Sipei Yi +3Real-Time Interactive Video Generation Interactive World Models
1Zhejiang University · 2NVIDIA
LVSA: Training-Free Sparse Attention for Long Video Diffusion
May 29, 2026Gael Glorian, Ioannis Lamprou, Zhen Zhang +2Video Diffusion Models Long-Horizon Video Generation
Distributed Parallel Technology Laboratory, Paris Research Center, Huawei Technologies France · AI Framework and Data Technology Lab, Huawei Technologies Co., Ltd.
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
May 29, 2026Zekai Li, Ji Liu, Yiqing Huang +3Diffusion Language Model Decoding Diffusion Language Models
Advanced Micro Devices, Inc. (AMD)
Veda: Scalable Video Diffusion via Distilled Sparse Attention
May 28, 2026Shihao Han, Hao Yang, Xinting Hu +3Video Diffusion Models Diffusion Transformer
ByteDance Inc. · University of Science and Technology of China · The University of Hong Kong
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
May 28, 2026Soowon Oh, Nam Cao, Yujin Kim +4Speculative Decoding Diffusion Language Model Decoding
KAIST AI · Samsung Advanced Institute of Technology
Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models
May 28, 2026Heqiang Qi, Wei Huang, Mingyuan Bai +1Masked Diffusion Models Diffusion Language Model Inference
Zhejiang University · RIKEN Center for Advanced Intelligence Project · The Institute of Statistical Mathematics +1
LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers
May 27, 2026Jintao Li, Yong-Yi Wang, Zheng-An Wang +1Efficient Inference Inference-Time Optimization
Beijing Key Laboratory of Fault-Tolerant Quantum Computing, Beijing Academy of Quantum Information Sciences, Beijing, China · Beijing National Laboratory for Condensed Matter Physics, Institute of Physics, CAS, Beijing, China · Beijing Key Laboratory of Advanced Quantum Technology, Beijing, China +1
DEMON: Diffusion Engine for Musical Orchestrated Noise
May 27, 2026Ryan FosdickControllable Music Generation Audio Diffusion Models
Daydream
Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
May 27, 2026Tianyi Wu, Xiaoxi Sun, Yanhua Jiao +5Diffusion Language Model Inference Diffusion Language Model Decoding
*Equal contribution. The work is done during Tianyi’s internship at CBG Celia DeviceAI Team, Huawei. · 1Harbin Institute of Technology, Shenzhen · 2Huawei +1
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
May 26, 2026Yuchen Liang, Ness Shroff, Yingbin LiangDiffusion Sampling Diffusion Model Inference Acceleration
The Ohio State University
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
SoftCap: Soft-Budget Control for Diffusion Transformer Acceleration
May 26, 2026Yuhang Zhang, Junxiang Qiu, Huixia Ben +3Diffusion Transformer Diffusion Model Caching
Hefei University of Technology · University of Science and Technology of China · Anhui University of Science and Technology +1
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
May 26, 2026Xing Cong, Hanlin Tang, Kan Liu +3Diffusion Transformer Activation Sparsity
1Alibaba Group · 2Independent Researcher
On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
May 26, 2026William Yuan, Sungwon Jeong, Amirali AghazadehMarkov Models Diffusion Sampling
Georgia Institute of Technology

Jun 5, 2026, cs.LGJ/K move · Enter open · S save

Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization

Shigui Li, Delu Zeng

School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China

Few-Step Diffusion Sampling Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

A fundamental tension exists in the large-step inference of diffusion models via their deterministic probability flow ordinary differential equation (PF-ODE) trajectories, which we identify as the contractivity trap: efficient inference favors large step sizes, while aggressive steps and highly expressive denoisers can undermine contraction-based stability certificates for error suppression. To address this, we propose SteinDiff, a step-wise inference-time stabilization framework that employs Stein-derived corrections without requiring reference samples. Specifically, SteinDiff introduces a geometry-aware residual correction mechanism that regularizes large-step solver updates without retraining. To this end, we derive a closed-form Stein correction coefficient for step-wise solver adjustment, enabling reference-free adaptation to local data geometry. We further establish a score-controlled perturbation bound under distributional shifts and provide a complementary Stein perspective on EDM-style parameterizations. Extensive experiments demonstrate that SteinDiff mitigates severe artifacts and improves generative quality across large-step inference settings.

Momentum

Related topics

Latest papers 335