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

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
May 15, 2026Xiaoxuan He, Siming Fu, Zeyue Xue +9Diffusion Model Alignment Video Diffusion Models
Zhejiang University · Joy Future Academy · Independent Researcher +1
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
May 13, 2026Jiahui Niu, Kefan Gu, Yucheng Zhao +5Efficient VLA Model Inference Speculative Decoding
State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Dexmal +1
Understanding and Accelerating the Training of Masked Diffusion Language Models
May 13, 2026Chunsan Hong, Sanghyun Lee, Chieh-Hsin Lai +5Masked Diffusion Models Diffusion Model Acceleration
1KAIST · 2Sony AI · University of Tokyo +1
Fast Image Super-Resolution via Consistency Rectified Flow
May 12, 2026Jiaqi Xu, Wenbo Li, Haoze Sun +8Rectified Flow Consistency Distillation
The Chinese University of Hong Kong · Huawei Noah’s Ark Lab · HKUST (GZ) +1
QDSB: Quantized Diffusion Schrödinger Bridges
May 12, 2026Tobias Fuchs, Florian Kalinke, Nadja KleinSchrödinger Bridges Diffusion Model Acceleration
Karlsruhe Institute of Technology, Karlsruhe, Germany
LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR
May 11, 2026Pedram Fekri, WenChen Li, William Chen +1Latent Diffusion Models HDR Imaging
Monks AI Research Lab, Toronto, Ontario, Canada
Elucidating Representation Degradation Problem in Diffusion Model Training
May 11, 2026Zhipeng Yao, Dazhou Li, Zitong Zhang +6Deep Learning Optimization Diffusion Model Acceleration
University of Louisville · Shenyang University of Chemical Technology · Florida International University +2
When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation
May 10, 2026Dongqi ZhengIdentity-Preserving Image Generation Few-Step Diffusion Sampling
A Few-Step Generative Model on Cumulative Flow Maps
May 5, 2026Zhiqi Li, Duowen Chen, Yuchen Sun +1One-Step Generative Modeling Flow-Based Generative Modeling
Georgia Institute of Technology, Atlanta, United States of America
AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
May 5, 2026Ruibin Min, Yexin Liu, Aimin Pan +5Diffusion Model Alignment Diffusion Transformer
Sun Yat-sen University · The Hong Kong University of Science and Technology · VNET Group +2
TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
May 4, 2026Sowmya Vajrala, Akshay Bankar, Manjunath Arveti +5Diffusion Distillation Few-Step Diffusion Sampling
Samsung Research Institute Bangalore, India
Skipping the Zeros in Diffusion Models for Sparse Data Generation
May 3, 2026Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6Synthetic Data Generation Diffusion Model Acceleration
1RPTU University Kaiserslautern-Landau · 2Heidelberg Univer · University of California, Irvine.
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
May 2, 2026Jinhao Zhang, Zhexuan Zhou, Huizhe Li +5Visuomotor Policy Learning Diffusion Policy
Harbin Institute of Technology, Shenzhen · Shanghai Jiao Tong University
SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
May 2, 2026Huy Duong, Trong-Tung Nguyen, Cuong Pham +3Subject-Driven Image Generation Identity-Preserving Image Generation
Qualcomm AI Research
Consistent Diffusion Language Models
Apr 30, 2026Hasan Amin, Yuan Gao, Yaser Souri +4Few-Step Diffusion Sampling Diffusion Model Acceleration
Department of Computer Science, Purdue University · Microsoft
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Apr 21, 2026Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec +1Trajectory Optimization Trajectory Generation
Inria - Département d’Informatique de l’École normale supérieure, PSL Research University, France · Courant Institute, New York University, USA
Optimally Bridging Semantics and Data: Generative Semantic Communication via Schrödinger Bridge
Apr 20, 2026Dahua Gao, Ruichao Liu, Minxi Yang +3Semantic Communication Few-Step Diffusion Sampling
School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi 710071 China · Pazhou Lab, Huangpu, Guangdong 510555 China · Peng Cheng Laboratory, Shenzhen, Guangdong 518055 China +1
Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement
Apr 20, 2026Hongxu Jiang, Fei Li, Boxiao Yu +43D Medical Imaging Medical Image Super-Resolution
Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA · Department of Medicine, University of Florida, Gainesville, FL, USA · Department of Biomedical Engineering, University of Florida, Gainesville, FL +2
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Apr 10, 2026Zile Wang, Zexiang Liu, Jiaxing Li +20Real-Time Interactive Video Generation Long-Horizon Video Generation
Skywork AI
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
Mar 14, 2026Eshed Gal, Moshe Eliasof, Eldad HaberDiffusion Transformer Visual SSMs
University of British Columbia, Vancouver, BC Canada · University of Cambridge, Cambridge, United Kingdom
Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
Feb 13, 2026Sangwoo Jo, Sungjoon ChoiDiffusion Model Sampling Diffusion Sampling
Department of Artificial Intelligence, Korea University, Seoul, South Korea.
Just on Time: Token-Level Early Stopping for Diffusion Language Models
Feb 11, 2026Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi +7Diffusion Language Model Inference Diffusion Language Model Decoding
SoftServe Inc.
Shiva-DiT: Residual-Based Differentiable Top- $k$ Selection for Efficient Diffusion Transformers
Feb 5, 2026Jiaji Zhang, Hailiang Zhao, Jiaju Wu +3Diffusion Model Acceleration Diffusion Transformer
College of Computer Science and Technology, Zhejiang University · 3Nanyang Technological University
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
Oct 6, 2025Théophane Vallaeys, Jakob Verbeek, Matthieu CordImage Tokenization Image Reconstruction
Meta Fundamental AI Research · Sorbonne University
VRWKV-Editor: Reducing quadratic complexity in transformer-based video editing
Sep 30, 2025Abdelilah Aitrouga, Youssef Hmamouche, Amal El Fallah SeghrouchniVideo Diffusion Models Video Editing
International Artificial Intelligence Center of Morocco University Mohammed VI Polytechnic Rabat, Morocco · Sorbonne University, LIP6 - UMR 7606 CNRS, France
NABLA: Neighborhood Adaptive Block-Level Attention
Jul 17, 2025Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva +6Video Diffusion Models Diffusion Transformer
Kandinsky Lab, Moscow, Russia
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
May 24, 2025Yiheng Li, Feng Liang, Dan Kondratyuk +3Diffusion Model Acceleration Diffusion Models
UC Berkeley, Berkeley CA 94720, USA · UT Austin, Austin TX 78712, USA · Rekursiv.ai, Mountain View CA, 94041
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Mar 12, 2024Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki +1Video Diffusion Models Long-Horizon Video Generation
The University of Tokyo

May 15, 2026, cs.CVJ/K move · Enter open · S save

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Xiaoxuan He, Siming Fu, Zeyue Xue, Weijie Wang+8

Zhejiang University · Joy Future Academy · Independent Researcher+1

Diffusion Model Alignment Video Diffusion Models Group Relative Policy Optimization Diffusion Policy RL for Diffusion Models Diffusion Model Acceleration

Open paper AskPDF arXiv

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

Momentum

Related topics

Latest papers 88