English
Related papers

Related papers: A Frame is Worth One Token: Efficient Generative W…

200 papers

Predicting future frames of a video sequence has been a problem of high interest in the field of Computer Vision as it caters to a multitude of applications. The ability to predict, anticipate and reason about future events is the essence…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Jasmeen Kaur , Sukhendu Das

World Foundation Models (WFMs) offer remarkable visual dynamics simulation capabilities, yet their application to precise robotic control remains limited by the gap between generative realism and control-oriented precision. While existing…

Robotics · Computer Science 2025-12-04 Yuhang Huang , Shilong Zou , Jiazhao Zhang , Xinwang Liu , Ruizhen Hu , Kai Xu

World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Siqiao Huang , Partha Kaushik , Michael Chen , Hengkai Pan , Kaiwen Geng , Omar Chehab , Fernando Moreno-Pino , Max Simchowitz

Multimodal Large Language Models (MLLMs) combine visual and textual representations to enable rich reasoning capabilities. However, the high computational cost of processing dense visual tokens remains a major bottleneck. A critical…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Mohamad Zamini , Diksha Shukla

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Hesong Wang , Xin Jin , Lu Lu , Chenhaowen Li , Jian Chen , Qiang Liu , Huan Wang

Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from long video sequences incurs prohibitive computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Minyoung Park , Taehun Kong , Sangjun Ahn

Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities…

Computer Vision and Pattern Recognition · Computer Science 2019-12-13 Hsu-kuang Chiu , Ehsan Adeli , Juan Carlos Niebles

We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. Building on a pre-trained SSL encoder, we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Ming Gui , Johannes Schusterbauer , Timy Phan , Felix Krause , Josh Susskind , Miguel Angel Bautista , Björn Ommer

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenqi Ouyang , Zeqi Xiao , Danni Yang , Yifan Zhou , Shuai Yang , Lei Yang , Jianlou Si , Xingang Pan

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Roman Bachmann , Jesse Allardice , David Mizrahi , Enrico Fini , Oğuzhan Fatih Kar , Elmira Amirloo , Alaaeldin El-Nouby , Amir Zamir , Afshin Dehghan

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Haichao Zhang , Yun Fu

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Ziyao Wang , Chen Chen , Jingtao Li , Weiming Zhuang , Jiabo Huang , Ang Li , Lingjuan Lyu

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons but tend to suffer from temporal inconsistencies. When…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Wilson Yan , Danijar Hafner , Stephen James , Pieter Abbeel

World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Dongwon Kim , Gawon Seo , Jinsung Lee , Minsu Cho , Suha Kwak

In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. This is realized through two key designs: (1) multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Cong Chen , Ziyuan Huang , Cheng Zou , Muzhi Zhu , Kaixiang Ji , Jiajia Liu , Jingdong Chen , Hao Chen , Chunhua Shen

Existing video recognition algorithms always conduct different training pipelines for inputs with different frame numbers, which requires repetitive training operations and multiplying storage costs. If we evaluate the model using other…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Yitian Zhang , Yue Bai , Chang Liu , Huan Wang , Sheng Li , Yun Fu

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

We present SceneTok, a novel tokenizer for encoding view sets of scenes into a compressed and diffusable set of unstructured tokens. Existing approaches for 3D scene representation and generation commonly use 3D data structures or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Mohammad Asim , Christopher Wewer , Jan Eric Lenssen

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yunhong Lu , Yanhong Zeng , Haobo Li , Hao Ouyang , Qiuyu Wang , Ka Leong Cheng , Jiapeng Zhu , Hengyuan Cao , Zhipeng Zhang , Xing Zhu , Yujun Shen , Min Zhang

Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due to (i) history-free initialization that mismatches policy…

Robotics · Computer Science 2026-03-19 Chaokang Jiang , Desen Zhou , Jiuming Liu , Kevin Li Sun