Xie, Yin, Kaicheng Yang, Peirou Liang, Xiang An, Yongle Zhao, Yumeng Wang, Ziyong Feng, Roy Miles, Ismail Elezi, and Jiankang Deng. 2026. “ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (32):27099-107. https://doi.org/10.1609/aaai.v40i32.39924.