Frederic Zhang | 张真
I'm an applied scientist at Amazon Australia, working on practical applications of vision-language models and generative models.
Previously, I was a research fellow at the Australian Institute for Machine Learning (AIML), working on model merging and parameter-efficient fine-tuning. I completed my PhD at the Australian National University (ANU), working with Prof. Stephen Gould, Dr. Dylan Campbell and Prof. Hongdong Li on the visual and spatial understanding of human–object interactions. Before that, I studied automation at Beijing Institute of Technology and mechatronics at the ANU, where I first took up research with Prof. Yuchao Dai and Prof. Richard Hartley.




