原文:FlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND Flash
作者:Yuseon Choi, Sanghyeon Park, Eunjong Lee, Hanseo Lee, Sangjin Kim
来源:arXiv cs.RO(机器人)
正文
Computer Science > Hardware Architecture
arXiv:2611.25580v1 (cs)
[Submitted on 19 Nov 2026]
Title:FlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND Flash
Authors:Yuseon Choi, Sanghyeon Park, Eunjong Lee, Hanseo Lee, Sangjin Kim
View a PDF of the paper titled FlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND Flash, by Yuseon Choi and 4 other authors
View PDF
HTML (experimental)
Abstract:Embodied agents are emerging as a promising paradigm for complex robotic tasks, leveraging Vision-Language-Action (VLA) and World Action Models (WAMs) to generate actions through Diffusion Transformer (DiT)-based iterative denoising. However, existing models often struggle to generalize to out-of-distribution (OOD) environments. We observe that retrieving successful experiences and using them to warm-start denoising enables agents to better adapt to unfamiliar situations while reducing computational overhead. This creates a new opportunity to improve task accuracy and inference efficiency simultaneously, in contrast to conventional acceleration techniques that trade accuracy for computation. However, realizing this opportunity requires scaling experience banks, introducing substantial storage and search overhead that challenges the capacity, bandwidth, and power constraints of edge systems.
We propose FlashX, a CMOS Directly Bonded to Array (CBA)-based NAND flash architecture for scalable experience reuse in embodied agents. FlashX exploits CBA’s high internal bandwidth for parallel pSLC key search, employing interleaved Compute-in-Flash (CIF) engines to sustain sensing throughput while retaining dense TLC latent storage. Proprioception-aware clustering further reduces search overhead and enables incremental experience acquisition without global reclustering. Evaluations across VLA and WAM workloads demonstrate up to 12.24%p and 7.43%p improvements in task success under dense and compute-efficient configurations, respectively. FlashX achieves 2.57$\times$ higher search throughput than the strongest prior NAND search architecture under pSLC sensing, with a further 9.7$\times$ search reduction through clustering. This delivers 1.29–3.95$\times$ end-to-end speedup and 1.12–2.34$\times$ energy efficiency improvement over SSD-based retrieval.
Subjects:
Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI); Robotics (cs.RO)
Cite as:
arXiv:2611.25580 [cs.AR]
(or
arXiv:2611.25580v1 [cs.AR] for this version)
https://doi.org/10.48550/arXiv.2611.25580
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
主题
cs.AR · 人工智能 · 机器人
由「前沿雷达」于 2026-11-19 采集。正文取自原文页面,已保留出处链接。标题与正文版权归原作者所有。
评论
加载中…