cs.CVNov 17, 2026

Inertial Video World Models

Authors: Yuan Gao, Fan Xu, Yu Guo, Yuxu Lu, Zhengru Fang, Hao Wu, Xiaomeng Huang

Organizations: Tsinghua University · University of Science and Technology of China · City University of Hong Kong · Hong Kong Polytechnic University · 

Abstract

The physical world has inertia: it evolves from what already exists rather than being recreated at every instant. However, many existing video world models lack an explicit mechanism for inertial state evolution, leaving the continuity of motion and structure implicit in video prediction. During autoregressive rollouts, repeated reconstruction can accumulate errors and destabilize the predicted dynamics. To address this limitation, we introduce InertialWorld, an Inertial Video World Model that makes inertia a structural prior for autoregressive prediction: existing scene evidence is carried across time rather than reconstructed at every step. Central to this formulation is Inertial Memory, which turns memory from passive predictive context into an evolving video state with two complementary views: a dense Eulerian grid preserves scene-aligned evidence, while persistent Lagrangian carriers bind local content to learned canonical coordinates. At each step, the model transports the carrier content according to action-conditioned motion, predicts the complete next video state from the transported carriers and dense grid, and uses a learned gate to combine transported and newly predicted content into the memory for the next step. Extensive experiments across multiple domains, including robot manipulation, 3D game simulation, and open-world navigation, demonstrate that InertialWorld achieves competitive autoregressive prediction performance against strong video world model baselines. Codes link: https://github.com/YuanGao-YG/InertialWorld

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Video World Models Need Predictable Latents

    Oct 26, 2026Mattia Scardecchia, Sherry YangVideo World ModelsWorld Model Learning

  2. World in World: Explore the World with World Models

    Sep 10, 2026Chenxi Song, Yanming Yang, Chi ZhangCamera-Controlled Video GenerationLong-Horizon Video Generation

  3. Nano World Models: A Minimalist Implementation of Future Video Prediction

    May 17, 2026Siqiao Huang, Partha Kaushik, Michael Chen +5Action-Conditioned Video GenerationLong-Horizon Video Generation