English
Related papers

Related papers: InfinityStar: Unified Spacetime AutoRegressive Mod…

200 papers

Generating realistic, dyadic talking head video requires ultra-low latency. Existing chunk-based methods require full non-causal context windows, introducing significant delays. This high latency critically prevents the immediate,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Bohong Chen , Haiyang Liu

Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Yuwei Guo , Ceyuan Yang , Hao He , Yang Zhao , Meng Wei , Zhenheng Yang , Weilin Huang , Dahua Lin

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…

Machine Learning · Computer Science 2026-04-08 Fu-Yun Wang , Hao Zhou , Liangzhe Yuan , Sanghyun Woo , Boqing Gong , Bohyung Han , Ming-Hsuan Yang , Han Zhang , Yukun Zhu , Ting Liu , Long Zhao

Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Xi Ye , Guillaume-Alexandre Bilodeau

Recent advances in text-to-video diffusion models have enabled the generation of high-quality videos conditioned on textual descriptions. However, most existing text-to-video models rely solely on textual conditions, lacking general…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Yuheng Chen , Teng Hu , Jiangning Zhang , Zhucun Xue , Ran Yi , Lizhuang Ma

Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Giannis Daras , Weili Nie , Karsten Kreis , Alex Dimakis , Morteza Mardani , Nikola Borislavov Kovachki , Arash Vahdat

Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However,…

Reconstructing spatially and temporally coherent videos from time-varying measurements is a fundamental challenge in many scientific domains. A major difficulty arises from the sparsity of measurements, which hinders accurate recovery of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Bingliang Zhang , Zihui Wu , Berthy T. Feng , Yang Song , Yisong Yue , Katherine L. Bouman

We introduce a method to generate temporally coherent human animation from a single image, a video, or a random noise. This problem has been formulated as modeling of an auto-regressive generation, i.e., to regress past frames to decode…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Tserendorj Adiya , Jae Shin Yoon , Jungeun Lee , Sanghun Kim , Hwasup Lim

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Bin Wu , Mengqi Huang , Shaojin Wu , Weinan Jia , Yuxin Wang , Zhendong Mao , Yongdong Zhang

Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Haohan Weng , Tianyu Yang , Jianan Wang , Yu Li , Tong Zhang , C. L. Philip Chen , Lei Zhang

Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Vladimir Arkhipkin , Zein Shaheen , Viacheslav Vasilev , Elizaveta Dakhova , Andrey Kuznetsov , Denis Dimitrov

Building video world models upon pretrained video generation systems represents an important yet challenging step toward general spatiotemporal intelligence. A world model should possess three essential properties: controllability,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Jianxiong Gao , Zhaoxi Chen , Xian Liu , Junhao Zhuang , Chengming Xu , Jianfeng Feng , Yu Qiao , Yanwei Fu , Chenyang Si , Ziwei Liu

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Xiaoxiao Ma , Feng Zhao , Pengyang Ling , Haibo Qiu , Zhixiang Wei , Hu Yu , Jie Huang , Zhixiong Zeng , Lin Ma

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

Image and Video Processing · Electrical Eng. & Systems 2024-10-28 Ruihan Yang , Yibo Yang , Joseph Marino , Stephan Mandt

Modeling and synthesizing complex hand-object interactions remains a significant challenge, even for state-of-the-art physics engines. Conventional simulation-based approaches rely on explicitly defined rigid object models and pre-scripted…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Zisu Li , Hengye Lyu , Jiaxin Shi , Yufeng Zeng , Mingming Fan , Hanwang Zhang , Chen Liang

We present VoiceStar, the first zero-shot TTS model that achieves both output duration control and extrapolation. VoiceStar is an autoregressive encoder-decoder neural codec language model, that leverages a novel Progress-Monitoring Rotary…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Puyuan Peng , Shang-Wen Li , Abdelrahman Mohamed , David Harwath

Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Yi Wei , Shunpu Tang , Liang Zhao , Qiangian Yang

Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Yixuan Zhu , Jiaqi Feng , Wenzhao Zheng , Yuan Gao , Xin Tao , Pengfei Wan , Jie Zhou , Jiwen Lu

Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive adversarial post-training (AAPT) to transform a pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Shanchuan Lin , Ceyuan Yang , Hao He , Jianwen Jiang , Yuxi Ren , Xin Xia , Yang Zhao , Xuefeng Xiao , Lu Jiang