# SPARK-VLA：53M参数实现无3D输入VLA空间理解蒸馏

> 原文链接：https://robotics.hellobike.com/papers/2026-11-10-2611-10443-2b513173
> 频道：papers | 更新日期：2026-11-10 | 标签：auto, arxiv
> 核心摘要：提出SPARK-VLA框架，通过空间表征蒸馏与知识路由机制，使0.5B参数VLA无需外部3D输入即具备空间理解力。仅53M可训练参数在LIBERO及真机任务中表现优异，代码已开源。

# SPARK-VLA：53M参数实现无3D输入VLA空间理解蒸馏

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models](https://arxiv.org/abs/2611.10443)（arXiv 2611.10443）

## 核心内容

针对现有视觉-语言-动作模型（VLA）依赖显式几何输入或单视觉通路导致语义丢失的问题，研究团队提出SPARK-VLA框架。该方法采用“保留-特化-路由”策略，在不引入外部3D传感器或专家模型推理的前提下，赋予VLA三维物理结构理解能力。实验显示，基于0.5B语言骨干网络，仅需约53M可训练参数，即可在LIBERO、LIBERO-Plus、CALVIN基准及真实世界操作任务中取得强劲性能，显著降低了3D感知VLA的训练与部署门槛。

技术核心包含空间表征蒸馏与轻量级知识路由两大模块。前者将冻结3D专家的空间理解能力迁移至LoRA适配的视觉分支，通过对齐注意力响应并保留原始视觉通路来维持预训练语义知识；后者利用动作损失梯度 derived 的路由监督，选择性地将与动作相关的视觉Token转发给语言模型。该架构避免了推理阶段对额外3D数据的依赖，实现了参数高效的空间自适应学习，相关代码已在GitHub开源供社区复现与验证。

## 关键看点

- **空间表征蒸馏**：对齐冻结3D专家与LoRA视觉分支注意力响应，在无外部3D输入下迁移空间理解能力
- **知识路由机制**：基于动作损失梯度生成路由监督，精准筛选动作相关视觉Token传输至语言模型
- **参数高效训练**：基于0.5B语言骨干仅微调约53M参数，在LIBERO及真机操作中验证了低资源3D适应性
- **开源资产释放**：完整代码已在GitHub开源，支持具身智能社区进行无3D传感器VLA算法复现与迭代

## 工程与产业观察

SPARK-VLA验证了通过蒸馏与路由机制可将3D空间理解内化至轻量化VLA中，摆脱了对推理端深度传感器的强依赖。其53M参数的极低微调成本为端侧具身模型部署提供了可行路径，解决了3D感知与语义保持的工程矛盾，对低成本机械臂操作算法研发具有直接参考价值。

## 英文摘要 (Abstract)

Understanding three-dimensional physical structure has become essential for vision-language-action models (VLAs). However, existing approaches either rely on explicit geometric inputs at inference time or adopt a single visual pathway, potentially compromising the visual-semantic knowledge inherited from pre-trained models. We present SPARK-VLA, Spatial Representation distillation and Knowledge routing for VLAs, a preserve-specialize-route framework for spatially adapting VLAs without requiring external 3D inputs or experts at inference. SPARK-VLA consists of two key components: (1) spatial representation distillation, which transfers 3D understanding from a frozen 3D expert to a LoRA-adapted visual branch by aligning attention responses while preserving the original visual pathway, and (2) a lightweight knowledge router, which selectively forwards action-relevant visual tokens to the language model using routing supervision derived from action-loss gradients. Across LIBERO, LIBERO-Plus, CALVIN, and real-world manipulation, SPARK-VLA achieves strong performance with only a 0.5B language backbone and approximately 53M trainable parameters, providing an effective and parameter-efficient approach to 3D-aware VLA learning. Code is available at https://github.com/park-jungin/spark-vla.

作者：Jungin Park, Chaoran Zhu, Changjae Oh, Kwanghoon Sohn
:::

## 原始参考来源 (Sources)

- [arXiv 2611.10443：Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models](https://arxiv.org/abs/2611.10443)