LTM：面向视觉-语言-动作模型的基于隐式转换的上下文内记忆
LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models
AI总结：
该研究针对机器人操作需记忆不可见交互的问题，提出LTM模型，通过隐式转换存储历史信息，在多个基准测试中表现优异，可扩展至大规模演示，适配受限记忆预算，提升真实机器人计数成功率。
摘要：
机器人操作通常需要记住不再可见的交互过程。我们提出隐式转换记忆（Latent Transition Memory，LTM），它将历史信息存储为连续观测之间的紧凑隐式转换。在π₀.₅上实例化为LTM-π后，我们的方法采用冻结的隐式动作编码器、轻量级适配器和因果KV缓存，实现增量推理，无需记忆特定语义标注或外部推理模型调用。在DreamDojo转换下，LTM-π在RoboMME上达到58.54%的成功率，在LIBERO-Mem上达到80.5%，在不使用外部推理模型或记忆特定标注的基线中表现最佳。消融实验证实了转换内容除时间线索外的贡献，以及延迟记忆准入的效率。将RoboMME演示规模扩大10倍，成功率从57.67%提升至87.50%；Cup Swap诊断实验凸显了过程监督在时间组合中的作用。在200-token的记忆预算下，成功率仍为84.00%，而无压缩时为87.50%。最后，真实机器人计数成功率从11.25%提升至82.50%。这些结果共同证明了隐式转换记忆的有效性、可扩展性和效率，凸显其处理复杂时间信息、受限上下文操作及真实世界机器人控制的能力。
英文摘要：
Robotic manipulation often requires remembering interactions that are no longer visible. We introduce Latent Transition Memory (LTM), which stores history as compact latent transitions between consecutive observations. Instantiated on $π_{0.5}$ as LTM-$π$, our method uses a frozen latent action encoder, a lightweight adapter, and causal KV caching for incremental inference without memory-specific semantic annotations or external reasoning-model calls. With DreamDojo transitions, LTM-$π$ achieves 58.54% success on RoboMME and 80.5% on LIBERO-Mem, performing best among baselines without external reasoning models or memory-specific annotations. Ablations support the contribution of transition content beyond temporal cues and the efficiency of delayed memory admission. Scaling RoboMME demonstrations tenfold improves success from 57.67% to 87.50%, while a Cup Swap diagnostic highlights the role of process supervision in temporal composition. Under a 200-token memory budget, success remains 84.00%, versus 87.50% without compression. Finally, real-robot counting success improves from 11.25% to 82.50%. Together, these results demonstrate the effectiveness, scalability, and efficiency of latent transition memory, highlighting its capacity for complex temporal information, bounded-context operation, and real-world robotic control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
