AI RESEARCH
MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
arXiv CS.LG
•
ArXi:2509.22403v2 Announce Type: replace Mobility Foundation Models (MFMs) have advanced the modeling of human movement patterns, yet they face a ceiling due to limitations in data scale and semantic understanding. While Large Language Models (LLMs) offer powerful semantic reasoning, they lack the innate understanding of spatio-temporal statistics required for generating physically plausible mobility trajectories.