cs.CVNov 9, 2026

QCC-WM: Linking Macro-State Dynamics and Visual Generation via Quotient Causal Construction

Authors: Zhizhong Fu, Wei Zhou, Zhaoyang Jiang, Yudong Lin, Songlun Li, Zhi Li, Feifan Chen, Gaoming Li, 

Organizations: School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China · Department of Radiology, Huzhou Maternity & Child Health Care Hospital, Huzhou, 313000, China · Department of Radiology, Huzhou Maternity & Child Health Care Hospital Affiliated to Huzhou Normal University, Huzhou, 313000, China · School of Health and Wellbeing, University of Glasgow, Glasgow, G12 8TB, United Kingdom · 

Abstract

A key challenge in action-conditioned world modeling is to construct macro-states from high-dimensional observations that support recursive prediction under actions, while keeping their predicted evolution consistent with visual changes in generated observations. We propose QCC-WM, a visual world model based on Quotient-based Causal Construction. QCC-WM uses action responses to guide macro-variable construction for recursive action-conditioned prediction. A shared reference quotient measurement constrains the consistency between predicted states and observed changes, allowing macro-level predictions to provide structured constraints for future visual generation. Using translational and rotational actions and their predicted responses, the model aggregates local visual features into macro-nodes with spatial correspondence through causal abstraction, and recursively predicts node content and motion under a shared reference measurement. Macro-level predictions guide future observation generation, while predicted motion transports historical appearance information. Node-level errors between generated observations and macro-level targets are then mapped back to the corresponding spatial regions for correction, improving consistency between visual generation and macro-level predictions. On the US-VLA dataset, QCC-WM achieves an ROI-MSE of 0.01861 for four-step prediction. Compared with the best baseline at each prediction horizon, it reduces LPIPS by 48.59%, 41.68%, and 30.23% for four-step prediction and eight- and sixteen-step recursive extrapolation, respectively. Ablation studies and mechanism analyses show that motion-guided reference transport mainly improves pixel reconstruction, while node-level error feedback further improves perceptual quality and consistency between generated observations and macro-level predictions.

Figures & tables

Explore similar work

CardsList
  1. WorldReward: Reward Modeling for Camera-Conditioned World Models

    Sep 3, 2026Yibin Wang, Zehan Wang, Junshu Tang +13Reward ModelingCamera-Conditioned Video Generation