Memory-Augmented Vision-Language-Action Models in Embodied AI:Methodological Advances, Efficiency Challenges, and Future Directions | Reading Group

Memory-Augmented Vision-Language-Action Models in Embodied AI: Methodological Advances, Efficiency Challenges, and Future Directions

keywords: Memory, VLA

论文分享主题接着上次的主题主要探讨记忆在VLA系统中的设计，与我目前主攻研究的方向很契合，记忆系统的设计可能对其他方向的同学也能有所帮助

完整PPT如下：

参考文献：
1.[NeurIPS 2025] RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems https://arxiv.org/abs/2508.01415

2.[ICLR 2026] MEMER: SCALING UP MEMORY FOR ROBOT CONTROL VIA EXPERIENCE RETRIEVAL https://arxiv.org/abs/2510.20328