Aug 2026
Towards a Causally-inspired Evolving World Model for Vision-and-Language Navigation in Continuous Environments.
A causally-inspired evolving world modeling framework that formulates VLN-CE as a sequence of causal partially observable Markov decision processes that learns unified latent states that integrate vision, language, and action, and strengthens generalization across diverse navigation contexts.
Xuan Yao, Junyu Gao, Chang-Sheng Xu
· IEEE Transactions on Pattern... · 0 citations