Diffusion Model Acceleration

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 88

All topics

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
Reward Lightning: Fast Video Generation via Homologous Preference Distillation
Jul 4, 2026Jiaxiang Cheng, Bing Ma, Xuhua Ren +4Diffusion Model Alignment Reward Modeling
Tencent Hunyuan, China
CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation
Jul 4, 2026Xuyao Huang, Zelai Deng, Xu Wang +2Camera-Controlled Video Generation Image-to-Video Generation
Shanghai Jiao Tong University · Nankai University · Transsion
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Jul 2, 2026Xingyu Zheng, Xianglong Liu, Yifu Ding +4Diffusion Model Acceleration Diffusion Model Inference Acceleration
State Key Laboratory of Complex & Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University · Nanyang Technological University +5
Post-Training Pruning for Diffusion Transformers
Jul 1, 2026Chengzhi Hu, Xuewen Liu, Jing Zhang +3Diffusion Transformer Diffusion-Based Image Generation
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
Jun 30, 2026Hyunsoo Lee, Inwoo Hwang, Young Min KimDiffusion Sampling Diffusion Model Acceleration
ECE, Seoul National University · INMC & IPAI, Seoul National University
SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending
Jun 27, 2026Haoran Bai, Xiaoxu Chen, Xiaoyu Liu +4Video Diffusion Models Few-Step Diffusion Sampling
1Alibaba Group · 2Harbin Institute of Technology · 3Xi’an Jiaotong University
OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal
Jun 26, 2026Qinming Zhou, Chenxi Sun, Deyang Kong +6Image Inpainting Diffusion Model Acceleration
Shanghai Jiao Tong University · Tsinghua University · University of Electronic Science and Technology of China +3
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
Jun 26, 2026Zipeng Guo, Lichen Ma, Yu He +4Diffusion Transformer Pixel-Space Diffusion Models
Xi’an Jiaotong University
Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
Jun 25, 2026Shubham Vaijanath Phoolari, Aleyna Kara, Christoph Lauer +1Diffusion Guidance Diffusion Model Acceleration
Authors are with CARIAD SE, Germany. · Author is with the Institute of Automotive Engineering (FZD), TU Darmstadt, Germany. · Author is with the Technical University of Munich, Germany.
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
Jun 23, 2026Sijie Wang, Zhengyu Qing, Zhiqiang Tan +6Reinforcement Learning Distributed RL
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen · Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou) · Huawei Technologies Ltd.
PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation
Jun 13, 2026Tianqi Chen, Jun Hou, Yinchi Zhou +3Diffusion Models for Image Restoration Image-to-Image Translation
Department of Radiology, Northwestern University, Chicago, IL, USA · Department of Biomedical Engineering, Yale University, New Haven, CT, USA · Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
Jun 11, 2026Jeeho Ryoo, Yongchan Jung, Muhammad Ali Khaliq +3Medical Imaging GPU Kernel Optimization
Fairleigh Dickinson University Vancouver, BC, Canada · The University of Colorado at Colorado Springs Colorado Springs, CO, USA · Northeastern University Vancouver, BC, Canada
MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
Jun 7, 2026Lianyu Pang, Tianlin Pan, Cheng Da +5Diffusion Model Alignment Diffusion Transformer
The Hong Kong University of Science and Technology · Kuaishou Technology · University of Chinese Academy of Sciences
LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing
Jun 4, 2026Jianzong Wu, Hao Lian, Jiongfan Yang +12Video Diffusion Models Video Editing
Peking University, Alibaba Group
Efficient and Training-Free Single-Image Diffusion Models
Jun 3, 2026Haojun Qiu, Kiriakos N. Kutulakos, David B. LindellImage Generation Diffusion-Based Image Generation
Department of Computer Science, University of Toronto · Vector Institute
Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection
Jun 2, 2026KeXiang Mao, FanCheng LiFew-Step Diffusion Sampling Diffusion Model Acceleration
School of Physics and Technology, Wuhan University, Wuhan 430072, China · Hongyi Honor College, Wuhan University, Wuhan 430072, China
Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
Jun 1, 2026Huayang Huang, Ruoyu Wang, Jinhui Zhao +5Diffusion Model Distillation Diffusion Model Acceleration
School of Computer Science, Wuhan University · MiLM Plus, Xiaomi Inc. · School of Artificial Intelligence, Wuhan University +1
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
May 28, 2026Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral +4Video Diffusion Models Self-Attention
1Virginia Tech · 2fal
OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning
May 27, 2026Yunyang Ge, Xianyi He, Zezhong Zhang +4Video Diffusion Models Text-to-Video Generation
1Peking University · 2Nanyang Technological University, Singapore · 3Rabbitpre AI
BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models
May 27, 2026Fei Deng, Yanwu Xu, Zhipeng Bao +4Diffusion Model Acceleration Diffusion-Based Image Editing
Google
SANTS: A State-Adaptive Scheduler for World Action Models
May 27, 2026Yirui Sun, Guangyu Zhuge, Keliang Liu +4Action-Conditioned World Models Visuomotor Policy Learning
Fudan University · Deep Computing Era Technology Co., Ltd · Harbin Institute of Technology
Hierarchical Variational Policies for Reward-Guided Diffusion
May 20, 2026Kushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld +2Diffusion Models for Image Restoration Diffusion Model Guidance
Department of Computer Science University of California Irvine
Rethinking Cross-Layer Information Routing in Diffusion Transformers
May 20, 2026Chao Xu, Maohua Li, Qirui Li +9Diffusion Transformer Residual Learning
Alibaba Group · Nanjing University · Zhejiang University
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
May 18, 2026Yukang Chen, Luozhou Wang, Wei Huang +13GPU Acceleration Long Video Generation
NVIDIA
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
May 18, 2026Peiliang Cai, Evelyn Zhang, Jiacheng Liu +8Video Diffusion Models Autoregressive Diffusion
1SJTU · 2SDU · 3HUST +4
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
May 18, 2026Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar +1Few-Step Diffusion Sampling Diffusion Model Acceleration
University of Amsterdam · Microsoft Research, Cambridge
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
May 18, 2026Yucheng Guo, Yongjian Guo, Zhong Guan +6Video Diffusion Models GPU Kernel Optimization
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
May 16, 2026Shaodong Xu, Zhendong Wang, Litong Gong +4Diffusion Model Alignment Diffusion Transformer
University of Science and Technology of China
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
May 15, 2026Ziyang Mai, Yuyao Zhang, Yu-Wing TaiVideo Diffusion Models Long-Horizon Video Generation
Dartmouth College

Jul 16, 2026, cs.AIJ/K move · Enter open · S save

Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation

Qicheng Zhao, Qi Sun, Zheyu Yan

Zhejiang University

Activation Sparsity Diffusion Language Model Inference Diffusion Model Acceleration

Open paper AskPDF arXiv

Diffusion Multimodal Large Language Models (DMLLMs) are highly effective for multimodal reasoning, yet their inference efficiency is significantly hindered by fixed-length generation constraints. Since the actual output length is unknown, output sequences are padded to a predefined maximum length, resulting in substantial redundant computation over unnecessary [EOS] tokens. In this work, we discover that DMLLMs implicitly reveal their valid semantic boundary at the very first denoising step through a distinct shift in MLP activation sparsity. Leveraging this observation, we propose Seer, a training-free framework that detects this boundary using a Signal-to-Noise Ratio (SNR)-based criterion and performs one-shot truncation of the redundant suffix for all subsequent computations. To preserve these theoretical gains during batched serving, Seer incorporates a hybrid execution strategy that maximizes throughput while seamlessly accommodating dynamic sequence lengths. Experimental results demonstrate that Seer effectively eliminates padding waste, accelerating throughput by up to

\sim

\times

. Across 9 benchmarks, Seer robustly maintains overall performance and even improves accuracy on complex visual tasks by mitigating noise leakage (e.g., DocVQA score increases from 63.52 to 63.66), offering a highly efficient, plug-and-play solution for DMLLM acceleration.

Momentum

Related topics

Latest papers 88