Zhang, Rongyu, et al. “MoLe-VLA: Dynamic Layer-Skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 22, Mar. 2026, pp. 18764-72, doi:10.1609/aaai.v40i22.38945.