CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
The Causal Semantic World Action Model (CSWAM) is presented, which augments FastWAM with a causal semantic expert built on V-JEPA 2.1, which provides temporally grounded representations of semantic state changes and motion with less dependence on appearance-specific details.
Tian-Bin Liu, Jian Zhu, Taiyi Su et al.
· 0 citations