English
Related papers

Related papers: EVATok: Adaptive Length Video Tokenization for Eff…

200 papers

Video autoencoders compress videos into compact latent representations for efficient reconstruction, playing a vital role in enhancing the quality and efficiency of video generation. However, existing video autoencoders often entangle…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Cuifeng Shen , Lumin Xu , Xingguo Zhu , Gengdai Liu

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Xiang Li , Kai Qiu , Hao Chen , Jason Kuen , Jiuxiang Gu , Bhiksha Raj , Zhe Lin

Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disregarding the inherent variations in scale and complexity…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Kangle Deng , Hsueh-Ti Derek Liu , Yiheng Zhu , Xiaoxia Sun , Chong Shang , Kiran Bhat , Deva Ramanan , Jun-Yan Zhu , Maneesh Agrawala , Tinghui Zhou

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Maitreya Patel , Jingtao Li , Weiming Zhuang , Yezhou Yang , Lingjuan Lv

Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer:…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yang Yue , Fangyun Wei , Tianyu He , Jinjing Zhao , Zanlin Ni , Zeyu Liu , Jiayi Guo , Lei Shi , Yue Dong , Li Chen , Ji Li , Gao Huang , Dong Chen

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

A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Kunyang Li , Mubarak Shah , Yuzhang Shang

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

Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Xu Zhang , Cheng Da , Huan Yang , Kun Gai , Ming Lu , Zhan Ma

Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Zongyi Li , Shujie Hu , Shujie Liu , Long Zhou , Jeongsoo Choi , Lingwei Meng , Xun Guo , Jinyu Li , Hefei Ling , Furu Wei

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Yinfei Yang , Jiasen Lu

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Haozhe Qi , Kevin Qu , Mahdi Rad , Rui Wang , Alexander Mathis , Marc Pollefeys

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

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Yang Ye , Junliang Guo , Haoyu Wu , Tianyu He , Tim Pearce , Tabish Rashid , Katja Hofmann , Jiang Bian

Building correspondences across different modalities, such as video and language, has recently become critical in many visual recognition applications, such as video captioning. Inspired by machine translation, recent models tackle this…

Computer Vision and Pattern Recognition · Computer Science 2019-11-11 Silvio Olivastri , Gurkirt Singh , Fabio Cuzzolin

Autoregressive Model (AR) has shown remarkable success in conditional image generation. However, these approaches for multiple reference generation struggle with decoupling different reference identities. In this work, we propose the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Haiyue Sun , Qingdong He , Jinlong Peng , Peng Tang , Jiangning Zhang , Junwei Zhu , Xiaobin Hu , Shuicheng Yan

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yizhuo Li , Yuying Ge , Yixiao Ge , Ying Shan , Ping Luo

Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Weijing Wu , Qihua Liang , Bineng Zhong , Haiying Xia , Zhiyi Mo , Shuxiang Song

Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Kaiwen Zha , Lijun Yu , Alireza Fathi , David A. Ross , Cordelia Schmid , Dina Katabi , Xiuye Gu