English
Related papers

Related papers: MemRoPE: Training-Free Infinite Video Generation v…

200 papers

Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Tianrui Zhu , Shiyi Zhang , Zhirui Sun , Jingqi Tian , Yansong Tang

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yang Xiao , Gen Li , Kaiyuan Deng , Yushu Wu , Zheng Zhan , Yanzhi Wang , Xiaolong Ma , Bo Hui

Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Shuai Yang , Yifan Zhou , Ziwei Liu , Chen Change Loy

Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…

Computation and Language · Computer Science 2025-08-01 Ali Veisi , Delaram Fartoot , Hamidreza Amirzadeh

Video compression has recently benefited from implicit neural representations (INRs), which model videos as continuous functions. INRs offer compact storage and flexible reconstruction, providing a promising alternative to traditional…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Jun Zhu , Xinfeng Zhang , Lv Tang , Junhao Jiang , Gai Zhang , Jia Wang

Video diffusion models have recently achieved remarkable results in video generation. Despite their encouraging performance, most of these models are mainly designed and trained for short video generation, leading to challenges in…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Zhuoling Li , Hossein Rahmani , Qiuhong Ke , Jun Liu

Video generation has made remarkable progress in recent years, especially since the advent of the video diffusion models. Many video generation models can produce plausible synthetic videos, e.g., Stable Video Diffusion (SVD). However, most…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Shaoshu Yang , Yong Zhang , Xiaodong Cun , Ying Shan , Ran He

Video diffusion models perform well in short-video synthesis, but their training-free extension to long videos often suffers from content drift, temporal inconsistency, and over-smoothed dynamics. Existing methods improve temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Fangda Chen , Shanshan Zhao , Longrong Yang , Chuanfu Xu , Zhigang Luo , Long Lan

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Umair Nawaz , Ahmed Heakl , Ufaq Khan , Abdelrahman Shaker , Salman Khan , Fahad Shahbaz Khan

Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid…

Machine Learning · Computer Science 2026-02-02 Yangyan Li

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Shengqu Cai , Weili Nie , Chao Liu , Julius Berner , Lvmin Zhang , Nanye Ma , Hansheng Chen , Maneesh Agrawala , Leonidas Guibas , Gordon Wetzstein , Arash Vahdat

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Fanshuai Meng , Weijia Jia , Wei Zhao

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jing Xu , Yuexiao Ma , Xuzhe Zheng , Xing Wang , Shiwei Liu , Chenqian Yan , Xiawu Zheng , Rongrong Ji , Fei Chao , Songwei Liu

Recent advances in 4D Gaussian Splatting (4DGS) have extended the high-speed rendering capability of 3D Gaussian Splatting (3DGS) into the temporal domain, enabling real-time rendering of dynamic scenes. However, one of the major remaining…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Sangwoon Kwak , Weeyoung Kwon , Jun Young Jeong , Geonho Kim , Won-Sik Cheong , Jihyong Oh

Text-to-video (T2V) generation has advanced rapidly, yet maintaining consistent character identities across scenes remains a major challenge. Existing personalization methods often focus on facial identity but fail to preserve broader…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Ziyang Mai , Yu-Wing Tai

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons but tend to suffer from temporal inconsistencies. When…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Wilson Yan , Danijar Hafner , Stephen James , Pieter Abbeel

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Daniel Bolya , Judy Hoffman

We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We…

Computation and Language · Computer Science 2026-05-18 Yufeng Du , Phillip Harris , Minyang Tian , Eliu A Huerta , Srikanth Ronanki , Subendhu Rongali , Aram Galstyan , Hao Peng

Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However, most existing models are trained on short clips, limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Yuchao Gu , Weijia Mao , Mike Zheng Shou

Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jente Vandersanden , Matheus Gadelha , Chun-Hao P. Huang , Hyeonho Jeong , Yulia Gryaditskaya