English
Related papers

Related papers: Self Forcing: Bridging the Train-Test Gap in Autor…

200 papers

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Xiaofeng Mao , Shaohao Rui , Kaining Ying , Bo Zheng , Chuanhao Li , Mingmin Chi , Kaipeng Zhang

Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yuheng Wu , Xiangbo Gao , Tianhao Chen , Xinghao Chen , Qing Yin , Zhengzhong Tu , Dongman Lee

Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distilled from a corresponding many-step…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jiaqi Feng , Justin Cui , Yuanhao Ban , Cho-Jui Hsieh

Self-forcing video generation extends a short-horizon video model to longer rollouts by repeatedly feeding generated content back in as context. This scaling path immediately exposes a systems bottleneck: the key-value (KV) cache grows with…

Machine Learning · Computer Science 2026-03-31 Suraj Ranganath , Vaishak Menon , Anish Patnaik

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Xiaofei Wu , Guozhen Zhang , Zhiyong Xu , Yuan Zhou , Qinglin Lu , Xuming He

Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the current generation with conditioning from the future. In camera-guided video generation with a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Chonghyuk Song , Michal Stary , Boyuan Chen , George Kopanas , Vincent Sitzmann

Despite rapid progress in autonomous driving, reliable training and evaluation of driving systems remain fundamentally constrained by the lack of scalable and interactive simulation environments. Recent generative video models achieve…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yaoru Li , Federico Landi , Marco Godi , Xin Jin , Ruiju Fu , Yufei Ma , Muyang Sun , Heyu Si , Qi Guo

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Tianwei Yin , Qiang Zhang , Richard Zhang , William T. Freeman , Fredo Durand , Eli Shechtman , Xun Huang

With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of video diffusion models (VDMs) generate long videos in an…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Kaifeng Gao , Jiaxin Shi , Hanwang Zhang , Chunping Wang , Jun Xiao

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

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate videos in an…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Kaifeng Gao , Jiaxin Shi , Hanwang Zhang , Chunping Wang , Jun Xiao , Long Chen

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

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

Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…

Computation and Language · Computer Science 2026-04-08 Dat Nguyen-Cong , Tung Kieu , Hoang Thanh-Tung

Autoregressive video models are promising for world modeling via next-frame prediction, but they suffer from exposure bias: a mismatch between training on clean contexts and inference on self-generated frames, causing errors to compound and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Ryan Po , Eric Ryan Chan , Changan Chen , Gordon Wetzstein

In this work, we propose Mutual Forcing, a framework for fast autoregressive audio-video generation with long-horizon audio-video synchronization. Our approach addresses two key challenges: joint audio-video modeling and fast autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Yupeng Zhou , Lianghua Huang , Zhifan Wu , Jiabao Wang , Yupeng Shi , Biao Jiang , Daquan Zhou , Yu Liu , Ming-Ming Cheng , Qibin Hou

Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Jianbiao Mei , Tao Hu , Xuemeng Yang , Licheng Wen , Yu Yang , Tiantian Wei , Yukai Ma , Min Dou , Botian Shi , Yong Liu

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