English
Related papers

Related papers: DySink: Dynamic Frame Sinks for Autoregressive Lon…

200 papers

We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Tariq Berrada Ifriqi , John Nguyen , Karteek Alahari , Jakob Verbeek , Ricky T. Q. Chen

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-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

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yuyang You , Yongzhi Li , Jiahui Li , Yadong Mu , Quan Chen , Peng Jiang

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Zengqun Zhao , Yanzuo Lu , Ziquan Liu , Jifei Song , Jiankang Deng , Ioannis Patras

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Taiye Chen , Zihan Ding , Anjian Li , Christina Zhang , Zeqi Xiao , Yisen Wang , Chi Jin

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 generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content. These models are structurally anchored to the first frame: its key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yusuf Dalva , Pinar Yanardag

Diffusion-based video depth estimation methods have achieved remarkable success with strong generalization ability. However, predicting depth for long videos remains challenging. Existing methods typically split videos into overlapping…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Yue-Jiang Dong , Wang Zhao , Jiale Xu , Ying Shan , Song-Hai Zhang

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

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Sihui Ji , Xi Chen , Shuai Yang , Xin Tao , Pengfei Wan , Hengshuang Zhao

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Jiwen Yu , Jianhong Bai , Yiran Qin , Quande Liu , Xintao Wang , Pengfei Wan , Di Zhang , Xihui Liu

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Youngrae Kim , Qixin Hu , C. -C. Jay Kuo , Peter A. Beerel

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Yu Shang , Lei Jin , Yiding Ma , Xin Zhang , Chen Gao , Wei Wu , Yong Li

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chao Yuan , Pan Li

Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Xinhang Gao , Junlin Guan , Shuhan Luo , Wenzhuo Li , Guanghuan Tan , Jiacheng Wang

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jiahao Shao , Yuanbo Yang , Hongyu Zhou , Youmin Zhang , Yujun Shen , Vitor Guizilini , Yue Wang , Matteo Poggi , Yiyi Liao

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

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Kai-En Lin , Guowei Yang , Lei Xiao , Feng Liu , Ravi Ramamoorthi