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 328

All topics

GRACE: Generation-aware latent compression for efficient video generation
Oct 7, 2026Jiyoung Kim, Paul Hyunbin Cho, Jisu Nam +5Diffusion Model Inference Acceleration Video Diffusion Models
KAIST AI · Kakao Corp.
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration
Oct 7, 2026Yuxiang Xiong, Ruiyan Wang, Wenqiang Wang +5Diffusion Model Caching Diffusion Model Inference Acceleration
Shanghai Jiao Tong University · Alibaba Cloud Computing · Alibaba Token Hub, Alibaba Group
Koopman Observers for Diffusion Acceleration: Correcting Feature Forecasts with Shallow Measurements
Oct 7, 2026Hanru Bai, Yuanchao Xu, Fengyi LiDiffusion Model Inference Acceleration Diffusion Model Caching
ETH Zurich · Max Planck Institute for Intelligent Systems · Kyoto University +1
Pooling Representation Autoencoders for Efficient Diffusion
Oct 7, 2026Ramón Calvo-González, Youssef Saied, François FleuretAutoencoders Diffusion-Based Image Generation
University of Geneva · University of Geneva and Meta
Consistent Distribution Matching for Data-Free Diffusion Distillation
Oct 6, 2026Yuxiang Fu, Qi Yan, Zike Wu +4Diffusion Model Distillation Diffusion Model Inference Acceleration
University of British Columbia · Vector Institute for AI · Canada CIFAR AI Chair
SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
Oct 6, 2026Jixing Zhou, Xinming HuangChannel Estimation Conditional Diffusion Models
Worcester Polytechnic Institute Worcester, MA, USA
Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation
Oct 6, 2026Liao Ma, Jiayi Song, Yunfeng Wu +2Video Diffusion Models Diffusion Transformer
School of Artificial Intelligence, Shanghai Jiao Tong University · School of Data Science, Fudan University · School of Computing and Data Science, The University of Hong Kong
RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing
Oct 6, 2026Wanning He, Yuyao Zhang, Yu-Wing TaiDiffusion Transformer Image Generation
Dartmouth College
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Oct 5, 2026Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5Video Diffusion Models Diffusion Transformer
Fudan University · Tencent HY · Shanghai Innovation Institute +4
Level-of-Token Diffusion
Oct 5, 2026Kiyohiro Nakayama, Brian Chao, Jan Ackermann +5Video Diffusion Models Diffusion Transformer
Stanford University · Google
The Unexpired Plan: A Free Monitor for Accelerated Diffusion Policies
Oct 5, 2026Yi Zhao, Sebastian SchererRobotics Diffusion Policy
AirLab, The Robotics Institute Carnegie Mellon University, Pittsburgh, PA, USA
Hybrid-Basis Feature Forecasting for Diffusion Sampling Acceleration
Oct 4, 2026Kai-Liang Cheng, Yuan-Yuan Cheng, Yu-fan Jin +1Diffusion Sampling Diffusion Model Caching
University of Science and Technology of China, China
Clock Diffusion: Efficient Semi-Autoregressive Continuous Diffusion Language Models
Oct 1, 2026Yair Schiff, Omer Belhasin, Roy Uziel +7Diffusion Language Model Inference Language Modeling
NVIDIA · Cornell University
Looped Diffusion Transformer
Sep 30, 2026Yong Xien Chng, Tianyi Chen, Wenwen Tong +7Diffusion Transformer Recurrent Transformers
SenseTime Research · LeapLab, Tsinghua University · Nanyang Tehnological Univesity
Distribution Matching Distillation for Continuous Diffusion Language Models
Sep 30, 2026Paul Le Van Kiem, Dario Shariatian, Umut Simsekli +1Diffusion Model Distillation Diffusion Language Models
Inria, PSL Research University · Cohere · CMAP, Ecole Polytechnique
Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models
Sep 30, 2026Stipe Frković, Metod Jazbec, Christian A. NaessethMasked Diffusion Models Speculative Decoding for Diffusion Language Models
University of Amsterdam · UvA-Bosch Delta Lab, University of Amsterdam
Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
Sep 30, 2026Jinwei Li, Daniel TenbrinckGraph Signal Processing Diffusion Model Inference Acceleration
Department of Data Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen, Germany
The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching
Sep 30, 2026Dong Wang, Wenwu Tang, Francesco Corti +3Diffusion Model Caching Diffusion Timestep Scheduling
Graz University of Technology, Austria · Swiss Data Science Center, Switzerland · ETH Zurich, Switzerland +1
DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
Sep 30, 2026Zeqi Xiao, Qingle Liu, Kaiwen Zhang +3KV-Cache Management Autoregressive Video Generation
Nanyang Technological University · Tsinghua University · Princeton University
PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion Transformers
Sep 30, 2026Yun Dai, Jiarui Wen, Huiping Zhuang +2Video Diffusion Models Diffusion Transformer
South China University of Technology
Acceleration of Diffusion Language Model through Discrete Average Generator
Sep 29, 2026Yidong Ouyang, Zhengyan Wan, Themis Haris +8Few-Step Diffusion Sampling Diffusion Language Model Inference
University of California, Los Angeles · Google · Work done as a research intern at Google
LongLive-Plug: Once-for-All Distillation for Video Generation
Sep 29, 2026Shuai Yang, Luozhou Wang, Wei Huang +9Video Diffusion Models Diffusion Model Distillation
NVIDIA
Time-Anchored Diffusion Language Models: Latent-Space Caching for Fast Generation
Sep 29, 2026Joel Anto Paul, Litu Rout, Aditya Akella +1Diffusion Language Model Inference Diffusion Model Caching
UT Austin
Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control
Sep 29, 2026Zibo Wang, Haochen Han, Pengzhen Ren +2Robotic Control Efficient VLA Model Inference
Pengcheng Laboratory
Parameterized Stripe Attention for Efficient Video Generation
Sep 29, 2026Xingyu Jia, Baole Ai, Ang Wang +2Video Diffusion Models Diffusion Transformer
Alibaba Group
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Sep 29, 2026Xiaoxu Chen, Qin Yang, Haoran Bai +2Diffusion Transformer Video Restoration
Alibaba Group · Xidian University
RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
Sep 29, 2026Yiming Liu, Ben Wan, Tongxuan Liu +5Classifier-Free Guidance Diffusion Model Caching
School of Software, Tsinghua University, Beijing, China · BNRist, Tsinghua University, Beijing, China · JD.com, Beijing, China
Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge
Sep 28, 2026Yitong Li, Jincheng Yu, Junsong Chen +6Video Diffusion Models GPU Kernel Optimization
NVIDIA Research, Efficient AI Team & Singapore Lab.
Unlocking Few-Step Diffusion for Faithful Previews
Sep 28, 2026Jing Jia, Sifan Liu, Guanyang WangDiffusion Sampling Few-Step Diffusion Sampling
Department of Computer Science, Rutgers University · Department of Statistical Science, Duke University · Department of Statistics, Rutgers University
CAST: Reconstruction-Coupled Acceleration of Interactive World Models
Sep 28, 2026Leyang Chen, Junyi Wu, Fanqing Kong +2Real-Time Interactive Video Generation Inference Acceleration
Shanghai Jiao Tong University

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

GRACE: Generation-aware latent compression for efficient video generation

Jiyoung Kim, Paul Hyunbin Cho, Jisu Nam, Donghoon Lee+4

KAIST AI · Kakao Corp.

Diffusion Model Inference Acceleration Video Diffusion Models Video Token Compression Diffusion Transformer

Open paper AskPDF arXiv

Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, since a higher compression ratio degrades reconstruction quality and recovering it requires more channels, which is known to slow the convergence of the DiT. The compressed latent also differs from the one the DiT was trained on, so the pretrained DiT must be either retrained from scratch or adapted at considerable cost. Compressing the autoencoder the DiT was trained with appears to preserve compatibility, yet optimizing it for reconstruction alone still shifts the latent away from the distribution the DiT has learned. To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT. Specifically, we keep a frozen base latent from the pretrained encoder and learn a residual latent for the information lost under stronger compression, while aligning the compressed latent with the pretrained latent in the feature space of the frozen DiT so that the autoencoder is optimized for generation. We then adapt the DiT with lightweight fine-tuning and asymmetric denoising, where the base is denoised ahead of the residual. GRACE reduces the token count of Wan2.1-I2V-14B by 8x and its latency by 11.1x at 480x832x81, while matching the generation quality of the pretrained pipeline before compression on VBench.

Momentum

Related topics

Latest papers 328