Xinyu is currently a Postdoctoral Research Fellow at the Centre for Augmented Reasoning, Australian Institute for Machine Learning, working with Prof. Qi Wu. He received his Ph.D. degree from the School of Computer and Mathematical Sciences at The University of Adelaide, Australia, under the supervision of Prof. Chunhua Shen.

Xinyu’s research interests lie at the intersection of Computer Vision and Natural Language Processing, especially in topics related to Multi-modal Large Language Models, Optical Character Recognition, and other Multi-modality Applications. Recently, he has been exploring the use of instruction-tuning techniques to adapt text-based LLMs to broader modalities, thereby enabling the processing of more complex tasks. Xinyu has co-authored publications in notable conferences and journals such as CVPR, ACMMM, TPAMI, IJCV, TMM, TCSVT, and PR.