MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
Lg-traj: Llm guided pedestrian trajectory prediction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Encore improves trajectory prediction by deriving explicitly biased rehearsal trajectories from ego observations to condition forecasts and simulate agent subjectivities.
citing papers explorer
-
MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
-
Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsals
Encore improves trajectory prediction by deriving explicitly biased rehearsal trajectories from ego observations to condition forecasts and simulate agent subjectivities.