Welcome to my academic homepage. I am a Ph.D. candidate in Computer Science at University of California, Los Angeles (UCLA). I went to Tsinghua University for college, also in CS.
I work on multimodal representation learning for visual reasoning and skill learning tasks. In particular, I'm interested in building and understanding inductive biases for learning representations from multi-modal data, so as to zero/few-shot (and systematically) generalize in real-world. Some of my research keywords can be found below:
© Xiaojian Ma 2022