Jiajun Song

Research Engineer at BIGAI. Previous @PKU Math @Duke Stats

profile.jpeg

Starting as an applied statistician, I have developed a keen interest in challenging inference problems in the real world. There is rarely a clean setup, and novel and complex issues consistently emerge in the data, such as spill-over spatial effects, feedback loop in the system, network interference and so on.

Meanwhile, in an era when more people come to foundation models for their excellence at prediction, obtaining interpretability and effective model inference poses a formidable challenge.

My current interests lie in

  • (Causal) Inference framework in complex settings, such as networks or correlated data.

  • Analyzing foundation models with statistical methods, such as high-dimensional statistics.

 

Posts

Publications

  1. Preprint
    Uncovering hidden geometry in Transformers via disentangling position and context
    Jiajun Song, and Yiqiao Zhong
    arXiv preprint arXiv:2310.04861, 2023