Diffusion Model Caching

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 72

All topics

Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
Jul 2, 2026Pranshu Chaturvedi, Parth Shroff, Tarun Suresh +2Mamba Long-Context Language Model Inference
Stanford University
Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding
Jul 2, 2026Marianne Arriola, Volodymyr KuleshovLanguage Model Decoding Diffusion Language Model Decoding
Department of Computer Science, Cornell University, Ithaca, NY, USA.
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
Jun 30, 2026Huanlin Gao, Fang Zhao, Qiang Hui +8Diffusion Sampling Diffusion Model Caching
Data Science & Artificial Intelligence Research Institute, China Unicom · Unicom Data Intelligence, China Unicom · National Key Laboratory for Novel Software Technology, Nanjing University
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
Jun 29, 2026Juncheng Ma, Yuxuan Du, Yanan Sun +8Diffusion Transformer Audio-Driven Facial Animation
Shenzhen Graduate School, Peking University, China · Shanghai AI Laboratory, China · Tencent Hunyuan, China +1
Affix Cache for Diffusion Large Language Models
Jun 26, 2026Kaihua Liang, An Zhong, Xin Tan +4KV Caching Memory-Efficient Inference
KAUST · CUHK · LUMS
Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation
Jun 26, 2026Yuhang Chen, Xianfeng Wu, Jinhao Duan +11Diffusion Language Model Inference Parallel Decoding
University of North Carolina at Chapel Hill · Meta AI
NaviCache: Test-Time Self-Calibration Caching for Video Generation
Jun 25, 2026Zheqi Lv, Zhibo Zhu, Jinke Wang +6Video Diffusion Models Diffusion Model Caching
Zhejiang University, Hangzhou, China · Cornell University, New York, USA · Tencent Hunyuan, Shenzhen, China +1
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
Jun 25, 2026Xuyue Huang, Zhe Chen, Wang Shen +1Video Diffusion Models Diffusion Transformer
Shenzhen Ubiquitous Data Enabling Key Laboratory, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Central Media Technology Institute, Huawei Technologies Co., Ltd., Shenzhen, China
MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
Jun 14, 2026Maoliang Li, Haojing Chen, Jiayu Chen +4Diffusion Transformer Diffusion Model Caching
School of Computer Science, Peking University, Beijing, China · School of Software Engineering, University of Electronic Science and Technology of China, Chengdu, China
Budget-Constrained Step-Level Diffusion Caching
Jun 11, 2026Mingkun Lei, Tong Zhao, Liangyu Yuan +1Diffusion Model Caching Diffusion Model Inference Acceleration
AGI Lab, Westlake University
TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
Jun 11, 2026Yu Meng, Xiangyang Luo, Letian Li +5Long-Horizon Video Generation Diffusion Model Caching
Tsinghua University · D-INFK, ETH Zürich
FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion
Jun 9, 2026Yu Lu, Junjie Yang, Piotr Koniusz +2KV Caching Long-Horizon Video Generation
Zhejiang University · University of New South Wales (UNSW) · Data61/CSIRO +1
Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction
Jun 7, 2026Yuhan Liu, Scott M. Leonard, Marlee Crews +5Diffusion Models for Image Restoration Diffusion Model Caching
Department of Radiology, Northwestern University, Chicago, IL, USA
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
WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
May 30, 2026Jinnan Yang, Yan Wang, Zhen Bi +5Long-Context Language Model Inference Diffusion Language Model Inference
Nanjing University of Science and Technology · Alibaba Group · Huzhou Normal 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
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
Enabling KV Caching of Shared Prefix for Diffusion Language Models
May 26, 2026Younghun Go, Jaehoon Han, Changyong Shin +2KV Caching KV-Cache Management
Korea University, South Korea
Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
May 24, 2026Mingyu Liang, Dingkun Xu, Jingwei XuDiffusion Transformer Diffusion-Based Image Generation
Laboratory for Novel Software Technology, Nanjing University, China
WorldKV: Efficient World Memory with World Retrieval and Compression
May 21, 2026Jung Yi, Minjae Kim, Paul Hyunbin Cho +3KV Caching Memory-Augmented Video Generation
1KAIST AI · 2Naver AI Lab
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
May 21, 2026Zachary Novack, Stephen Brade, Haven Kim +8Diffusion Model Alignment Controllable Music Generation
UC San Diego · MIT · Adobe
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
Prefix-Adaptive Block Diffusion for Efficient Document Recognition
May 16, 2026Mingxu Chai, Ziyu Shen, Chenyu Liu +9Diffusion Language Model Inference Diffusion Model Caching
Computation and Artificial Intelligence Innovative College, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · ByteDance, Shanghai, China
Accelerating Rectified Flow Models via Trajectory-Aware Caching
May 16, 2026Xiao Liu, Kai Liu, Naiyang Guan +5Video Diffusion Models Rectified Flow
Shanghai Jiao Tong University, Shanghai, China · Academy of Military Science, Beijing, China · Huawei Technologies Ltd, Shenzhen, China
Test-time Sparsity for Extreme Fast Action Diffusion
May 13, 2026Kangye Ji, Yuan Meng, Jianbo Zhou +3Diffusion Transformer Inference-Time Optimization
Tsinghua University · The Chinese University of Hong Kong
Muninn: Your Trajectory Diffusion Model But Faster
May 11, 2026Gokul Puthumanaillam, Hao Jiang, Ruben Hernandez +4Trajectory Generation Diffusion-Based Planning
University of Illinois Urbana-Champaign. · Florida International University. · Providence College.
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
May 10, 2026Yicheng Ji, Zhizhou Zhong, Jun Zhang +7Diffusion Model Caching KV-Cache Compression
ZJU · Video Rebirth · HKUST +1
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
May 10, 2026Shanwen Tan, Hao Li, Jingtao Zhang +4Long Video Generation Memory-Augmented Video Generation
University of Science and Technology of China · Fudan University · Georgia Institute of Technology +1
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
May 9, 2026Yixin Tang, Jiawei Guo, Junxian Li +6Diffusion Model Distillation Few-Step Diffusion Sampling
Shanghai Jiao Tong University · Nanyang Technological University · Honor Device Co., Ltd
Not All Tokens Need 40 Steps: Heterogeneous Step Allocation in Diffusion Transformers for Efficient Video Generation
May 7, 2026Ernie Chu, Vishal M. PatelVideo Diffusion Models Diffusion Transformer
Johns Hopkins University Baltimore, MD 21218

Jul 2, 2026, cs.LGJ/K move · Enter open · S save

Training Hybrid Block Diffusion Language Models with Partial Bidirectionality

Pranshu Chaturvedi, Parth Shroff, Tarun Suresh, Hangoo Kang+1

Stanford University

Mamba Long-Context Language Model Inference Blockwise Diffusion Language Models Diffusion Language Model Inference Diffusion Model Caching Diffusion Language Models

Open paper AskPDF arXiv

High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each decoding step must stream the accumulated key/value (KV) cache from memory, so bandwidth demand grows with context length while only one token is emitted. Two parallel approaches have therefore emerged: reducing memory access with efficient attention variants and linear-time mixers such as Mamba, or increasing parallel computation by generating blocks of tokens at once. However, technical challenges arise when combining these two ideas. Earlier hybrid diffusion models such as DiffuMamba use bidirectional Mamba mixing, including a reverse-direction scan relative to causal generation. This reverse scan needs to scan the entire sequence, so its states are not prefix-only and cannot be precisely reused as a cache even when diffusion is performed block by block. We propose a BDLM Mamba--attention hybrid that addresses this challenge by restricting the reverse Mamba scan to the active denoising block, which enables exact caching across blocks. In an 87M-parameter DCLM sweep, BDLM Mamba-H achieves the best C4-en validation perplexity compared to BDLM attention and full-sequence baselines. At 350M parameters, it remains competitive with BDLM attention. For long-context inference, BDLM Mamba-H reaches 19.7x the throughput of full-sequence DiffuMamba-H at 65K tokens and 3.7x the throughput of BDLM attention at 262K, showing that Mamba hybrids are a potential long-context diffusion architecture.

Momentum

Related topics

Latest papers 72