الملخص
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning. These findings motivate ReWAM, a representation-centric world-action model built on pre-trained DINO features. Feature Calibration and a Temporal Representation Bottleneck organize these features into compact world states suited to dynamics modeling. Action-Grounded Representation Shaping routes only action-loss gradients to the bottleneck, thereby letting the policy shape what the representation encodes while the world model learns how it evolves. Without generative video pre-training, ReWAM achieves 93.6% success on RoboTwin 2.0. On RoboDojo, it achieves an average score of 12.29 and a success rate of 8.28% using approximately 600 hours of embodied pre-training data.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Jiang, H., Liu, L., Wang, X., Sun, Z., Chen, Z., Wang, S., Wang, X., Chen, X., Yao, J., Zhao, W., Yuan, S., Su, Z., Sui, W., Liu, W., & Wang, X. (2026). Rethinking Representations for World-Action Modeling. https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling
MLA 9
Jiang, Haoyi, et al. "Rethinking Representations for World-Action Modeling." https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling.
شيكاغو (المؤلف–التاريخ)
Jiang, Haoyi, Liu Liu, Xinjiang Wang, Zhihao Sun, Zequn Chen, Sen Wang, Xinjie Wang, Xia Chen, Jingfeng Yao, Weiheng Zhao, Shanglin Yuan, Zhizhong Su, Wei Sui, Wenyu Liu, and Xinggang Wang. 2026. "Rethinking Representations for World-Action Modeling." https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling.
هارفارد
Jiang, H., Liu, L., Wang, X., Sun, Z., Chen, Z., Wang, S., Wang, X., Chen, X., Yao, J., Zhao, W., Yuan, S., Su, Z., Sui, W., Liu, W. and Wang, X. (2026) 'Rethinking Representations for World-Action Modeling', Available at: https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling.
فانكوفر
Jiang H, Liu L, Wang X, Sun Z, Chen Z, Wang S, et al. Rethinking Representations for World-Action Modeling. https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling
IEEE
H. Jiang, L. Liu, X. Wang, Z. Sun, Z. Chen, S. Wang, X. Wang, X. Chen, J. Yao, W. Zhao, S. Yuan, Z. Su, W. Sui, W. Liu, and X. Wang, "Rethinking Representations for World-Action Modeling," https://omanscience.com/ar/articles/rethinking-representations-for-world-action-modeling.