AI RESEARCH
WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models
arXiv CS.CV
•
ArXi:2604.07957v1 Announce Type: cross Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct planners or trajectory predictors, while world models look-ahead reasoning by imagining future views. Yet predicting a reliable trajectory from a single egocentric observation remains challenging. Current VLMs often generate unstable trajectories, and world models, though able to synthesize plausible futures, do not directly provide the grounded signals needed for navigation learning.