arXiv 2512.099272025-12-10cs.RO

令牌扩展-合并：面向视觉-语言-动作模型的免训练令牌压缩

Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models

College of Science and Engineering, Hamad Bin Khalifa University（1 科学与工程学院，哈马德·本·卡西姆大学）；Mohamed bin Zayed University of Artificial Intelligence（2 摩萨·本·扎耶德人工智能大学）；College of Computer Science and Technology, Zhejiang University（3 计算机科学与技术学院，浙江大学）

Yifan Ye, Jiaqi Ma, Jun Cen, Zhihe Lu

备注：: 8 pages, 5 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TEAM-VLA通过动态令牌扩展与合并机制，实现无需训练的视觉-语言-动作模型高效推理，提升速度并保持任务性能。

摘要：

视觉-语言-动作（VLA）模型在大规模多模态数据集上预训练后，已成为机器人感知和控制的强大基础。然而，其庞大的规模，通常以十亿参数计，对实时部署提出了重大挑战，因为推理过程在动态环境中变得计算成本高且延迟敏感。为此，我们提出了令牌扩展和合并-VLA（TEAM-VLA），一种无需训练的令牌压缩框架，旨在加速VLA推理同时保持任务性能。TEAM-VLA引入了一种动态令牌扩展机制，该机制在注意力突出区域的周围空间中识别并采样额外的有用令牌，以增强上下文完整性。这些扩展的令牌随后在更深层的层中在动作感知指导下被选择性合并，从而有效减少冗余同时保持语义一致性。通过在单次前馈传递中结合扩展和合并，TEAM-VLA在效率和有效性之间实现了平衡的权衡，无需任何重新训练或参数更新。在LIBERO基准上的广泛实验表明，TEAM-VLA在保持或甚至超越完整VLA模型任务成功率的同时，显著提高了推理速度。代码已公开在https://github.com/Jasper-aaa/TEAM-VLA上。

英文摘要：

Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant challenges for real-time deployment, as inference becomes computationally expensive and latency-sensitive in dynamic environments. To address this, we propose Token Expand-and-Merge-VLA (TEAM-VLA), a training-free token compression framework that accelerates VLA inference while preserving task performance. TEAM-VLA introduces a dynamic token expansion mechanism that identifies and samples additional informative tokens in the spatial vicinity of attention-highlighted regions, enhancing contextual completeness. These expanded tokens are then selectively merged in deeper layers under action-aware guidance, effectively reducing redundancy while maintaining semantic coherence. By coupling expansion and merging within a single feed-forward pass, TEAM-VLA achieves a balanced trade-off between efficiency and effectiveness, without any retraining or parameter updates. Extensive experiments on LIBERO benchmark demonstrate that TEAM-VLA consistently improves inference speed while maintaining or even surpassing the task success rate of full VLA models. The code is public available on \href{https://github.com/Jasper-aaa/TEAM-VLA}{https://github.com/Jasper-aaa/TEAM-VLA}

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。