English
Related papers

Related papers: WorldCache: Accelerating World Models for Free via…

200 papers

Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their core attention layers become a major bottleneck at inference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Dvir Samuel , Issar Tzachor , Matan Levy , Micahel Green , Gal Chechik , Rami Ben-Ari

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Guandong Li

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Zhendong Wang , Yifan Jiang , Huangjie Zheng , Peihao Wang , Pengcheng He , Zhangyang Wang , Weizhu Chen , Mingyuan Zhou

Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational requirements by caching similar features in the inference process…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Jiayi Pan , Jiaming Xu , Yongkang Zhou , Guohao Dai

Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. While recent advances have improved diffusion model efficiency, directly applying these…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Quanjian Song , Xinyu Wang , Donghao Zhou , Jingyu Lin , Cunjian Chen , Yue Ma

Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Zhentao Fan , Zongzuo Wang , Weiwei Zhang

Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation…

Machine Learning · Computer Science 2024-06-07 Jincheng Zhong , Xingzhuo Guo , Jiaxiang Dong , Mingsheng Long

Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…

Machine Learning · Computer Science 2026-02-04 Andre He , Sean Welleck , Daniel Fried

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Artificial Intelligence · Computer Science 2024-08-21 Chunting Zhou , Lili Yu , Arun Babu , Kushal Tirumala , Michihiro Yasunaga , Leonid Shamis , Jacob Kahn , Xuezhe Ma , Luke Zettlemoyer , Omer Levy

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from…

Multimedia · Computer Science 2025-01-09 Desen Sun , Henry Tian , Tim Lu , Sihang Liu

Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Boming Tan , Xiangdong Zhang , Ning Liao , Yuqing Zhang , Shaofeng Zhang , Xue Yang , Qi Fan , Yanyong Zhang

Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…

Machine Learning · Computer Science 2025-03-04 Xingzhuo Guo , Yu Zhang , Baixu Chen , Haoran Xu , Jianmin Wang , Mingsheng Long

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Mingyu Sung , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Tingyan Wen , Haoyu Li , Yihuang Chen , Xing Zhou , Lifei Zhu , Xueqian Wang

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard…

Computation and Language · Computer Science 2026-02-17 Yuchu Jiang , Yue Cai , Xiangzhong Luo , Jiale Fu , Jiarui Wang , Chonghan Liu , Xu Yang

Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Zihao Wu

Text-to-image generation employing diffusion models has attained significant popularity due to its capability to produce high-quality images that adhere to textual prompts. However, the integration of diffusion models faces critical…

Networking and Internet Architecture · Computer Science 2025-12-05 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Weijia Jia , Wei Zhao

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Weizhi Gao , Zhichao Hou , Junqi Yin , Feiyi Wang , Linyu Peng , Xiaorui Liu