World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal training that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architect...
Yue Su, Bo-Kai Lin, Xin-Kai Wang et al.· 1 citation· ⚡1
This work jointly varies model size, training tokens, and forward and backward loop counts across nearly 600 training runs and fit a unified scaling law that captures the effects of looping and truncation through effective parameters, showing that at fixed model size, the compute-optimal loop count and training-token b...
Xu-Yuan Xiong, Si-Yu Chen, Zi-Han Shao et al.· 1 citation
Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent understanding of evolving world state. Building such a benchmark from real-world videos is challenging because the underlying world state is pa...
Kuan Zhang, Yu-Kun Chen, Zhi-Hao Yang et al.· 0 citations
SG-WAM introduces learnable dynamics tokens and a Self-Guided World Predictor that forecasts their future latent states conditioned on intervening robot actions, and is a self-guided framework that learns geometry-aware action-conditioned dynamics directly in the policy-derived representation space.
Ruiteng Zhao, Zheng-Shen Zhang, Yue Su et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
