外观
论文arXiv 2610.1209020 天前
为视觉-语言-动作模型重组并精炼潜在推理流
原文链接：Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models（arXiv 2610.12090 · 发布日期：2026-10-08）
Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
针对VLA每次查询重复重建潜在推理的问题，FLOWMEM复用成功潜在片段并精炼，在RoboMME和LIBERO-Plus验证。
核心要点
- 现有方法在执行后丢弃成功推理，需从头重构相似计算。
- FLOWMEM动态检索并重组兼容潜在片段，形成随进展变化的推理路线。
- 推理路线再结合当前视觉和本体感知证据精炼，用于条件化动作生成。
- 在RoboMME和LIBERO-Plus上成功率达48.0%和77.3%，优于无记忆策略。
验证范围与局限：验证范围为RoboMME和LIBERO-Plus实验，摘要未说明真机或仿真设置。
英文摘要 (Abstract)
Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot actions. While existing methods learn to generate or refine such states for each policy query, they discard successful reasoning after execution and therefore reconstruct similar computation from scratch. We present Reasoning and Flow Memory (FLOWMEM), a unified VLA model that turns successful latent computation into reusable reasoning experience. Rather than appending a fixed retrieved context, FLOWMEM dynamically retrieves and recomposes compatible latent fragments as the embodied context evolves, forming a reasoning route that follows the temporal structure and progress of successful computation. The route is then refined using current visual and proprioceptive evidence before it conditions action generation. Experiments on RoboMME and LIBERO-Plus show that FLOWMEM attains 48.0% and 77.3% success, outperforming memory-free policies by 1.7 and 4.1 percentage points, respectively. These results demonstrate the value of reusing successful latent computation for closed-loop VLA control.
作者：Shi Hongyu, Sen Zhao, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Qinghua Zhang
来源
本页事实对应的公开页面，以原文为准。