language-guidance

SPW-Nav 是一种流式全景世界模型，能根据语言指令从单张全景图实时生成一分钟2K 360度视频，并支持中途切换指令，用于语言引导的导航与3D场景探索。

RoboFollow introduces a diagnostic benchmark to expose the illusion of instruction-following in embodied agents by analyzing high scene entropy and perturbations, revealing gaps in current models despite strong initial performance.

MolmoMotion is a new language-guided 3D motion forecasting model that predicts future 3D point trajectories from video frames and action descriptions, achieving stronger performance than existing methods. Alongside the model, a large dataset (MolmoMotion-1M) and a benchmark (PointMotionBench) are released.