Foresight-Guided Action Refinement (FGAR), which asymmetrically exploits proximal foresight for local action enhancement and route-critical foresight for feature-wise correction and route-level guidance, is introduced, validating the effectiveness of dual-horizon foresight and FGAR learning.
SPRII, a training principle that uses relations between interactions as weak supervision for persistent context while retaining the learner's native objective, is introduced.
Jia-Xuan Dai, Quan Fang, Junyu Gao et al.· 0 citations
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.