Vesta: A Generalist Embodied Reasoning Model

Huggingface presents Vesta, a generalist embodied reasoning model that integrates localization, spatial reasoning, navigation, and long-horizon planning into a single model. Weighing in at 1.4B parameters, Vesta outperforms individual state-of-the-art baselines by 20% and an ensemble of category-best baselines by 10% across diverse benchmarks.