LATIDIA · Robótica

EmbodiedMind: Curación adaptativa de datos y aprendizaje de refuerzo de prefijos para una inteligencia incorporada eficiente

arXiv: 2609.19659v1Tipo de anuncio: nuevo Resumen: La capacitación en modelos de cimientos incorporados generalmente requiere conjuntos de datos a gran escala y amplios recursos computacionales, pero a menudo sufre de tres limitaciones críticas: (1)

La noticia

arXiv:2609.19659v1 Announce Type: new Abstract: Training embodied foundation models typically requires massive-scale datasets and extensive computational resources, yet often suffers from three critical limitations: (1) inefficient sample utilization due to low-informative samples; (2) imbalanced gradient contributions across heterogeneous tasks; and (3) severe credit assignment problem in long-horizon planning, where trajectory-level rewards indiscriminately penalize all tokens. To address these issues, we propose an efficient training paradigm that achieves state-of-the-art average performance through strategic data selection and hierarchical policy optimization. Our approach consists of three synergistic stages. First, Rejection Sampling-based Fine-Tuning (RSFT) filters out low-informative samples to establish robust behavioral priors while preventing distributional collapse. Second, Iterative Rejection GRPO (IR-GRPO) employs task-specific