English
Related papers

Related papers: NextFlow: Unified Sequential Modeling Activates Mu…

200 papers

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Yuexiao Ma , Xuzhe Zheng , Jing Xu , Xiwei Xu , Feng Ling , Xiawu Zheng , Huafeng Kuang , Huixia Li , Xing Wang , Xuefeng Xiao , Fei Chao , Rongrong Ji

This paper investigates the scaling properties of autoregressive next-pixel prediction, a simple, end-to-end yet under-explored framework for unified vision models. Starting with images at resolutions of 32x32, we train a family of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xinchen Yan , Chen Liang , Lijun Yu , Adams Wei Yu , Yifeng Lu , Quoc V. Le

Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Jie Liu , Zilyu Ye , Linxiao Yuan , Shenhan Zhu , Yu Gao , Jie Wu , Kunchang Li , Xionghui Wang , Xiaonan Nie , Weilin Huang , Wanli Ouyang

Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Shihao Zhao , Yitong Chen , Zeyinzi Jiang , Bojia Zi , Shaozhe Hao , Yu Liu , Chaojie Mao , Kwan-Yee K. Wong

Existing video prediction methods mainly rely on observing multiple historical frames or focus on predicting the next one-frame. In this work, we study the problem of generating consecutive multiple future frames by observing one single…

Computer Vision and Pattern Recognition · Computer Science 2018-08-28 Yijun Li , Chen Fang , Jimei Yang , Zhaowen Wang , Xin Lu , Ming-Hsuan Yang

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer…

Machine Learning · Computer Science 2026-05-27 Qingyu Shi , Jinbin Bai , Zhuoran Zhao , Wenhao Chai , Kaidong Yu , Jianzong Wu , Yunhai Tong , Xiangtai Li , Xuelong Li , Shuicheng Yan

Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in…

Machine Learning · Computer Science 2025-02-18 Sohil Atul Shah , Vladlen Koltun

We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memory-bound process that leads to high latency. Existing works…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Zhuoyang Zhang , Luke J. Huang , Chengyue Wu , Shang Yang , Kelly Peng , Yao Lu , Song Han

Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Jiacheng Zhang , Jie Wu , Yuxi Ren , Xin Xia , Huafeng Kuang , Pan Xie , Jiashi Li , Xuefeng Xiao , Weilin Huang , Shilei Wen , Lean Fu , Guanbin Li

In this paper, we present MVTokenFlow for high-quality 4D content creation from monocular videos. Recent advancements in generative models such as video diffusion models and multiview diffusion models enable us to create videos or 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Hanzhuo Huang , Yuan Liu , Ge Zheng , Jiepeng Wang , Zhiyang Dou , Sibei Yang

We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks. Our approach infers and synthesizes small- and large-scale details solely from a low-resolution…

Graphics · Computer Science 2021-12-15 Bruno Roy , Pierre Poulin , Eric Paquette

Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications. In recent years deep learning (DL) has been used to construct data-driven fluid-dynamic…

Machine Learning · Computer Science 2026-04-13 David Ramos , Lucas Lacasa , Fermín Gutiérrez , Eusebio Valero , Gonzalo Rubio

Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may…

Computer Vision and Pattern Recognition · Computer Science 2021-04-12 Jie An , Siyu Huang , Yibing Song , Dejing Dou , Wei Liu , Jiebo Luo

Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 G. Thomas Hudson , Dean Slack , Thomas Winterbottom , Jamie Sterling , Chenghao Xiao , Junjie Shentu , Noura Al Moubayed

Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with intelligent devices across diverse applications. However,…

Graphics · Computer Science 2025-04-01 Chaojian Li , Sixu Li , Linrui Jiang , Jingqun Zhang , Yingyan Celine Lin

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Yuwen Xiong , Mengye Ren , Wenyuan Zeng , Raquel Urtasun

Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Zhiyang Lu , Qinghan Chen , Ming Cheng

New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control accuracy, generation quality, and generation efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Sen Fang , Hongbin Zhong , Yalin Feng , Yanxin Zhang , Dimitris N. Metaxas

Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Edith Tretschk , Vladislav Golyanik , Michael Zollhoefer , Aljaz Bozic , Christoph Lassner , Christian Theobalt