الملخص
Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual and intervened predictions, but uniform aggregation weights responses equally without explicitly incorporating physical priors. Our key insight is to incorporate physical priors into candidate reliability learning, motivating LPA-CWM with a lightweight Learned Physical Adjudicator (LPA). Trained on dense MOVi-F trajectories, the 3.0M-parameter LPA compares visual context and response structure across an unordered candidate set to predict relative weights; windowed localization and one paired re-evaluation recover motion with the CWM frozen. Existing video-level benchmarks do not directly assess motion correspondence, where low localization error can conceal missing trajectory segments. We introduce Completeness-aware Motion Correspondence (CMC), a ground-truth-anchored protocol jointly measuring localization, completeness, visibility, and continuity, counting missing predictions as failures on visible dynamic points. Across DAVIS, Kinetics, and RoboTAP, LPA-CWM improves all main CMC measures over Uniform CWM, with relative gains of 18.1%--60.0% in average Dynamic Correspondence Accuracy ($\mathrm{DCA}_{\mathrm{avg}}$), and improves TAP-Vid First tracking accuracy (overview: https://LPA-CWM.github.io).
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Wu, K., Liu, X., Yao, G., Chen, J., Chen, Z., Zhang, M., Wang, P., & Cui, S. (2026). LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models. https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models
MLA 9
Wu, Kunwei, et al. "LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models." https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models.
شيكاغو (المؤلف–التاريخ)
Wu, Kunwei, Xiang Liu, Guocai Yao, Junming Chen, Zhikang Chen, Min Zhang, Pengwei Wang, and Sen Cui. 2026. "LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models." https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models.
هارفارد
Wu, K., Liu, X., Yao, G., Chen, J., Chen, Z., Zhang, M., Wang, P. and Cui, S. (2026) 'LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models', Available at: https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models.
فانكوفر
Wu K, Liu X, Yao G, Chen J, Chen Z, Zhang M, et al. LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models. https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models
IEEE
K. Wu, X. Liu, G. Yao, J. Chen, Z. Chen, M. Zhang, P. Wang, and S. Cui, "LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models," https://omanscience.com/ar/articles/lpa-cwm-a-learned-physical-adjudicator-for-motion-reasoning-with-counterfactual-world-models.