p-MoD: building mixture-of-depths MLLMs via progressive ratio decay Aug 12, 2025· Jun Zhang , Desen Meng , Zhengming Zhang , Zhenpeng Huang , Tao Wu Limin Wang · 0 min read Cite URL Type Conference paper Publication Proceedings of the IEEE/CVF International Conference on Computer Vision Last updated on Aug 12, 2025 Authors Limin Wang Nanjing University ← MobileViCLIP: an efficient video-text model for mobile devices Aug 12, 2025 Scalable image tokenization with index backpropagation quantization Aug 12, 2025 →