Song W, Zhou Z, Zhao H, Chen J, Ding P, Yan H, et al. ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 27];40(22):18549-57. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38921