AAAI 2026technical0 citations

ObjecTok: Learning Holistic and Robust Object Tokens for MLLMs

Sihan Wang, Xiyao Liu, Lianqing Liu, Zhi Han

Abstract

Mainstream multimodal large language models (MLLMs) rely on patch-based tokenization methods, which compromise the integrity of objects and thereby limit the model

BibTeX
@inproceedings{aaai2026_objectoklearning,
  title = {ObjecTok: Learning Holistic and Robust Object Tokens for MLLMs},
  author = {Sihan Wang and Xiyao Liu and Lianqing Liu and Zhi Han},
  booktitle = {AAAI 2026},
  year = {2026}
}