English
Related papers

Related papers: Latent Video Prediction Learns Better World Models

200 papers

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhaochong An , Orest Kupyn , Théo Uscidda , Andrea Colaco , Karan Ahuja , Serge Belongie , Mar Gonzalez-Franco , Marta Tintore Gazulla

Forecasting future events is a fundamental capability for general-purpose systems that plan or act across different levels of abstraction. Yet, evaluating whether a forecast is "correct" remains challenging due to the inherent uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Jacob C Walker , Pedro Vélez , Luisa Polania Cabrera , Guangyao Zhou , Sayna Ebrahimi , Rishabh Kabra , Carl Doersch , Maks Ovsjanikov , João Carreira , Shiry Ginosar

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

Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification…

Machine Learning · Computer Science 2026-03-24 Liu hung ming

Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals. Due to limited temporal context window sizes, these models often struggle to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Tong Wu , Shuai Yang , Ryan Po , Yinghao Xu , Ziwei Liu , Dahua Lin , Gordon Wetzstein

Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos. This enables the video…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Ziyi Lin , Shijie Geng , Renrui Zhang , Peng Gao , Gerard de Melo , Xiaogang Wang , Jifeng Dai , Yu Qiao , Hongsheng Li

Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we…

Computer Vision and Pattern Recognition · Computer Science 2019-09-02 Keren Gu , Brandon Yang , Jiquan Ngiam , Quoc Le , Jonathon Shlens

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Marissa A. Weis , Kashyap Chitta , Yash Sharma , Wieland Brendel , Matthias Bethge , Andreas Geiger , Alexander S. Ecker

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…

Computer Vision and Pattern Recognition · Computer Science 2023-04-12 Xudong Lin , Simran Tiwari , Shiyuan Huang , Manling Li , Mike Zheng Shou , Heng Ji , Shih-Fu Chang

World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the…

Machine Learning · Computer Science 2026-02-25 Leonardo F. Toso , Davit Shadunts , Yunyang Lu , Nihal Sharma , Donglin Zhan , Nam H. Nguyen , James Anderson

Current video generation models produce high-quality aesthetic videos but often struggle to learn representations of real-world physics dynamics, resulting in artifacts such as unnatural object collisions, inconsistent gravity, and temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Siddarth Nilol Kundur Satish , Devesh Jaiswal , Hongyu Chen , Abhishek Bakshi

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

Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video…

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

Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Chao-Yuan Wu , Philipp Krähenbühl

Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses great challenges to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Ping Li , Chenhan Zhang , Xianghua Xu

With the advancement of deep learning-driven video editing technology, security risks have emerged. Malicious video tampering can lead to public misunderstanding, property losses, and legal disputes. Currently, detection methods are mostly…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Pengfei Pei

World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a…

Machine Learning · Computer Science 2026-05-26 Santosh Kumar Radha , Oktay Goktas

Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on…

Machine Learning · Computer Science 2026-01-22 Yongchao Huang

Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been explored to define…

Machine Learning · Computer Science 2025-10-02 Marco Bagatella , Matteo Pirotta , Ahmed Touati , Alessandro Lazaric , Andrea Tirinzoni