Zhang L, Wang J, Li H, Zhang B, Liu W. HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 12];40(15):12618-26. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38257