English
Related papers

Related papers: Not All Frames Deserve Full Computation: Accelerat…

200 papers

The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Mingzhen Sun , Weining Wang , Gen Li , Jiawei Liu , Jiahui Sun , Wanquan Feng , Shanshan Lao , SiYu Zhou , Qian He , Jing Liu

Existing long-term video prediction methods often rely on an autoregressive video prediction mechanism. However, this approach suffers from error propagation, particularly in distant future frames. To address this limitation, this paper…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Woonho Ko , Jin Bok Park , Il Yong Chun

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Longbin Ji , Xiaoxiong Liu , Junyuan Shang , Shuohuan Wang , Yu Sun , Hua Wu , Haifeng Wang

Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generation and iterative denoising. In this work, we tackle this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Zhen Zou , Xiaoxiao Ma , Jie Huang , Zichao Yu , Feng Zhao

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Xuzhe Zheng , Yuexiao Ma , Jing Xu , Xiawu Zheng , Rongrong Ji , Fei Chao

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Yinfei Yang , Jiasen Lu

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Howard Xiao , Brian Chao , Lior Yariv , Gordon Wetzstein

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Wentai Zhang , Ronghui Xi , Shiyao Peng , Jiayu Huang , Haoran Luo , Zichen Tang , Haihong E

Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they…

Machine Learning · Computer Science 2025-06-13 Samuel Belkadi , Steve Hong , Marian Chen , Miruna Cretu , Charles Harris , Pietro Lio

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Sheng Li , Yang Sui , Junhao Ran , Bo Yuan , Yue Dai , Xulong Tang

We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Wenming Weng , Ruoyu Feng , Yanhui Wang , Qi Dai , Chunyu Wang , Dacheng Yin , Zhiyuan Zhao , Kai Qiu , Jianmin Bao , Yuhui Yuan , Chong Luo , Yueyi Zhang , Zhiwei Xiong

Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrained by the slow inference speed of per-token generation, which often requires thousands of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Junhyuk So , Hyunho Kook , Chaeyeon Jang , Eunhyeok Park

We propose Spatio-temporal Crop Aggregation for video representation LEarning (SCALE), a novel method that enjoys high scalability at both training and inference time. Our model builds long-range video features by learning from sets of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Sepehr Sameni , Simon Jenni , Paolo Favaro

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zili Wang , Robert Zhang , Kun Ding , Qi Yang , Fei Li , Shiming Xiang

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Desai Xie , Zhan Xu , Yicong Hong , Hao Tan , Difan Liu , Feng Liu , Arie Kaufman , Yang Zhou

Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequential AR stage and the iterative multi-step denoising of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Zhen Zou , Xiaoxiao Ma , Mingde Yao , Jie Huang , LinJiang Huang , Feng Zhao

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However,…

Image and Video Processing · Electrical Eng. & Systems 2026-03-12 Sofia Iliopoulou , Dimitris Ampeliotis , Athanassios Skodras

Autoregressive (AR) image generators offer a language-model-friendly approach to image generation by predicting discrete image tokens in a causal sequence. However, unlike diffusion models, AR models lack a mechanism to refine previous…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Cheng Cheng , Lin Song , Di An , Yicheng Xiao , Xuchong Zhang , Hongbin Sun , Ying Shan

Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xiao Liu , Kai Liu , Naiyang Guan , Hongliang Lu , Zhixin Wang , Zhikai Chen , Renjing Pei , Yulun Zhang

Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Feihong Yan , Shaoyu Liu , Haixuan Wang , Shuai Lu , Linfeng Zhang , Huiqi Li , Xiangyang Ji
‹ Prev 1 2 3 10 Next ›