Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

多数 VLA 建立在仅用 2D 数据预训练的 VLM 上，缺乏准确空间感知；显式深度/点云输入受传感器噪声、硬件异构和数据覆盖限制，深度估计又受估计器性能约束。Spatial Forcing 把 VLA 中间视觉嵌入与预训练 3D 基础模型的几何表示对齐，在不依赖显式 3D 输入或深度估计器的情况下隐式强化空间理解。仿真和真机实验显示其超过 2D/3D VLA 基线，最高带来 3.8× 训练加速并改善数据效率。

Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data, which lack accurate spatial awareness and hinder their ability to operate in the 3D physical world. Existing solutions attempt to incorporate explicit 3D sensor inputs such as depth maps or point clouds, but these approaches face challenges due to sensor noise, hardware heterogeneity, and incomplete depth coverage in existing datasets. Alternative methods that estimate 3D cues from 2D images also suffer from the limited performance of depth estimators. We propose Spatial Forcing (SF), a simple yet effective alignment strategy that implicitly forces VLA models to develop spatial comprehension capabilities without relying on explicit 3D inputs or depth estimators. SF aligns intermediate visual embeddings of VLAs with geometric representations produced by pretrained 3D foundation models. By enforcing alignment at intermediate layers, SF guides VLAs to encode richer spatial representations that enhance action precision. Extensive experiments in simulation and real-world environments demonstrate that SF achieves state-of-the-art results, surpassing both 2D- and 3D-based VLAs. SF further accelerates training by up to 3.8x and improves data efficiency across diverse robotic tasks.