HiMe: Hierarchical Memory Framework for Vision-Language-Action ModelsHiMe：视觉语言行动模型的分层记忆框架
S 1.7T11 sources1 个来源R7-research
Researchers propose HiMe, a hierarchical embodied memory framework that addresses the "frequency-competence paradox" in Vision-Language-Action (VLA) models, which currently struggle with long-horizon tasks requiring memory and reasoning beyond immediate observations.
The framework decouples embodied intelligence into three components: a high-frequency Executor for real-time control, a Sentry for working memory, and a Planner for long-term strategy, balancing execution speed with reasoning capability.
The system introduces dynamic knowledge management with Add, Update, and Delete operations for memory plasticity, demonstrating improved success rates in long-horizon robotic tasks during experiments.