English
Related papers

Related papers: UltraViCo: Breaking Extrapolation Limits in Video …

200 papers

Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then…

Computation and Language · Computer Science 2022-12-21 Yutao Sun , Li Dong , Barun Patra , Shuming Ma , Shaohan Huang , Alon Benhaim , Vishrav Chaudhary , Xia Song , Furu Wei

Image animation has seen significant progress, driven by the powerful generative capabilities of diffusion models. However, maintaining appearance consistency with static input images and mitigating abrupt motion transitions in generated…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Xin Ma , Yaohui Wang , Genyun Jia , Xinyuan Chen , Tien-Tsin Wong , Cunjian Chen

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuang Ai , Qihang Fan , Xuefeng Hu , Zhenheng Yang , Ran He , Huaibo Huang

Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error accumulation leads to significant temporal degradation when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Jia Li , Xiaomeng Fu , Xurui Peng , Weifeng Chen , Youwei Zheng , Tianyu Zhao , Jiexi Wang , Fangmin Chen , Xing Wang , Hayden Kwok-Hay So

Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jung Yi , Wooseok Jang , Paul Hyunbin Cho , Jisu Nam , Heeji Yoon , Seungryong Kim

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inconsistencies and motion artifacts. To overcome this, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinyu Peng , Han Li , Yuyang Huang , Ziyang Zheng , Yaoming Wang , Xin Chen , Wenrui Dai , Chenglin Li , Junni Zou , Hongkai Xiong

In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant computational challenges due to the extreme variance in sequence lengths within mixed-mode…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-19 Yucheng Guo , Yongjian Guo , Zhong Guan , Haoran Sun , Wen Huang , Wanting Xu , Jing Long , Shuai Di , Junwu Xiong

Data unlearning aims to remove the influence of specific training samples from a trained model without requiring full retraining. Unlike concept unlearning, data unlearning in diffusion models remains underexplored and often suffers from…

Machine Learning · Computer Science 2025-10-22 Jinseong Park , Mijung Park

Video diffusion models (VDMs) have demonstrated remarkable capabilities in text-to-video (T2V) generation. Despite their success, VDMs still suffer from degraded image quality and flickering artifacts. To address these issues, some…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Jiacheng Zhang , Jie Wu , Weifeng Chen , Yatai Ji , Xuefeng Xiao , Weilin Huang , Kai Han

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…

Computation and Language · Computer Science 2024-10-11 Chuanyang Zheng , Yihang Gao , Han Shi , Jing Xiong , Jiankai Sun , Jingyao Li , Minbin Huang , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, the large motion between frames makes this…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Jingxi Chen , Brandon Y. Feng , Haoming Cai , Tianfu Wang , Levi Burner , Dehao Yuan , Cornelia Fermuller , Christopher A. Metzler , Yiannis Aloimonos

Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Dohun Lee , Chun-Hao Paul Huang , Xuelin Chen , Jong Chul Ye , Duygu Ceylan , Hyeonho Jeong

Diffusion models are just at a tipping point for image super-resolution task. Nevertheless, it is not trivial to capitalize on diffusion models for video super-resolution which necessitates not only the preservation of visual appearance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Zhikai Chen , Fuchen Long , Zhaofan Qiu , Ting Yao , Wengang Zhou , Jiebo Luo , Tao Mei

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-02 Xin Tan , Yuetao Chen , Yimin Jiang , Xing Chen , Kun Yan , Nan Duan , Yibo Zhu , Daxin Jiang , Hong Xu

Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and…

Computation and Language · Computer Science 2026-05-01 Jiaqi Leng , Xiang Hu , Junxiong Wang , Jianguo Li , Wei Wu , Yucheng Lu

Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating sparse attention techniques for improving efficiency. However, existing training-free sparse…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jiayi Luo , Jiayu Chen , Jiankun Wang , Cong Wang , Hanxin Zhu , Qingyun Sun , Chen Gao , Zhibo Chen , Jianxin Li

Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Shitong Shao , Lichen Bai , Pengfei Wan , James Kwok , Zeke Xie

Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 ZiYi Dong , Chengxing Zhou , Weijian Deng , Pengxu Wei , Xiangyang Ji , Liang Lin

We conduct an in-depth analysis of attention in video diffusion transformers (VDiTs) and report a number of novel findings. We identify three key properties of attention in VDiTs: Structure, Sparsity, and Sinks. Structure: We observe that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Yuxin Wen , Jim Wu , Ajay Jain , Tom Goldstein , Ashwinee Panda