Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths
Year: 2026
Type: conference-paper
Abstract: YiJie Huang, Xiaocui Yang, Shi Feng, Wen Zhang, Kaisong Song, Yifei Zhang, Daling Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Institutions: Northeastern University, Alibaba Group (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Keywords: multimodal alignment, multimodal captioning
Open Access status: hybrid
Awards: G3523622274, G6718616873, G8666265765
OpenAlex ID: W7166871748
