English
Related papers

Related papers: PackForcing: Short Video Training Suffices for Lon…

200 papers

Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such as sparse attention…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Jiaxiu Jiang , Wenbo Li , Jingjing Ren , Yuping Qiu , Yong Guo , Xiaogang Xu , Han Wu , Wangmeng Zuo

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hang Guo , Zhaoyang Jia , Jiahao Li , Bin Li , Yuanhao Cai , Jiangshan Wang , Yawei Li , Yan Lu

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Boxun Xu , Yuming Du , Zichang Liu , Siyu Yang , Ziyang Jiang , Siqi Yan , Rajasi Saha , Albert Pumarola , Wenchen Wang , Peng Li

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

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Vatsal Agarwal , Saksham Suri , Matthew Gwilliam , Pulkit Kumar , Abhinav Shrivastava

Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Zeyu Zhang , Shuning Chang , Yuanyu He , Yizeng Han , Jiasheng Tang , Fan Wang , Bohan Zhuang

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Zheyu Zhang , Ziqi Pang , Shixing Chen , Xiang Hao , Vimal Bhat , Yu-Xiong Wang

Video generation is pivotal to digital media creation, and recent advances in autoregressive video generation have markedly enhanced the efficiency of real-time video synthesis. However, existing approaches generally rely on heuristic KV…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Hanmo Chen , Chenghao Xu , Xu Yang , Xuan Chen , Cheng Deng

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinying Lin , Xuyang Liu , Yiyu Wang , Teng Ma , Wenqi Ren

Video compression has always been a popular research area, where many traditional and deep video compression methods have been proposed. These methods typically rely on signal prediction theory to enhance compression performance by…

Computer Vision and Pattern Recognition · Computer Science 2023-08-31 Lv Tang , Xinfeng Zhang , Gai Zhang , Xiaoqi Ma

Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Junchao Huang , Xinting Hu , Boyao Han , Shaoshuai Shi , Zhuotao Tian , Tianyu He , Li Jiang

Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jintao Chen , Chengyu Bai , Junjun Hu , Xinda Xue , Mu Xu

Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shida Wang , YongXiang Hua , Zhou Tao , Haoyu Cao , Linli Xu

Autoregressive video generation relies on history context for content consistency and storytelling. As video histories grow longer, efficiently encoding them remains an open problem - particularly for personal users and local workflows…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Lvmin Zhang , Shengqu Cai , Muyang Li , Chong Zeng , Beijia Lu , Anyi Rao , Song Han , Gordon Wetzstein , Maneesh Agrawala

Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long inference latency, which largely…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Long Zhuo , Guangcong Wang , Shikai Li , Wayne Wu , Ziwei Liu

The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow…

Computation and Language · Computer Science 2025-04-01 Jeffrey Willette , Heejun Lee , Youngwan Lee , Myeongjae Jeon , Sung Ju Hwang

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ziyi Wang , Haoran Wu , Yiming Rong , Deyang Jiang , Yixin Zhang , Yunlong Zhao , Shuang Xu , Bo XU

For any video codecs, the coding efficiency highly relies on whether the current signal to be encoded can find the relevant contexts from the previous reconstructed signals. Traditional codec has verified more contexts bring substantial…

Image and Video Processing · Electrical Eng. & Systems 2023-03-15 Jiahao Li , Bin Li , Yan Lu

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Haoran Hao , Jiaming Han , Yiyuan Zhang , Xiangyu Yue

Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectively modeling the temporal dimension (i.e. capturing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Lingyu Kong , Hongzhi Zhang , Jingyuan Zhang , Jianzhao Huang , Kunze Li , Qi Wang , Fuzheng Zhang