作者位次 #5/8ICML 2026Spotlight· Applications / Computer Vision
OmniFit: Bridging Modalities via Layer-Adaptive Token Compression for Omnimodal Large Language Models
Zining Wang · Zhihang Yuan · Yingjie Zhai · Wenshuo Li · Han Shu · Ruihao Gong · Jinyang Guo · Xianglong Liu