APA (7th ed.) Citation

Xiao, J., She, Y., Li, K., Sha, Y., Cheng, Z., & Tong, Z. (2026). StemVLA: An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation.

Chicago Style (17th ed.) Citation

Xiao, Jiasong, Yutao She, Kai Li, Yuyang Sha, Ziang Cheng, and Ziang Tong. StemVLA: An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation. 2026.

MLA (9th ed.) Citation

Xiao, Jiasong, et al. StemVLA: An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation. 2026.