They use RVT-2.

Citation

(Fang et al., 2025)

Fang, H., Grotz, M., Pumacay, W., Wang, Y. R., Fox, D., Krishna, R., & Duan, J. (2025). SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation. https://arxiv.org/abs/2501.18564