作者位次 #6/10AAAI 2026Poster· Artificial Intelligence
ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
Yin Xie · Kaicheng Yang · Peirou Liang · Xiang An · Yongle Zhao · Yumeng Wang · Ziyong Feng · Roy Miles · Ismail Elezi · Jiankang Deng