Yijia Dai

CS & Physics undergrad @ Cornell. 问心无愧.


👋 ▫️ 👍 👀 ❕

Learning is key for any type of intelligence. I love thinking about how human learns, and whether that is transferable to machines. Questions like Why ML requires more data than human?intrigue me.

My research interests are broadly learning robust user representations, and aligning machine to human reasoning. I’m fortunate to be working with Prof. Sarah Dean, Prof. Wen Sun, and Prof. Thorsten Joachims at Cornell. Currently, I study reinforcement learning and human-in-loop dynamical systems. Sample-efficient low-rank representation learning for dynamical and unobserved user states, computationally-efficient weighted logistic bandits, and “algorithm-of-thoughts” styled personalized question-understanding system are examples of what I am working on.



  1. recsys_flowchart.gif
    Representation Learning in Low-rank Slate-based Recommender Systems
    Yijia Dai, and Wen Sun
  2. ae.png
    Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration
    Viraj Mehta, Vikramjeet Das, Ojash Neopane, and 4 more authors


  1. FeCoNiCrAl.png
    Growth Mechanisms and the Effects of Deposition Parameters on the Structure and Properties of High Entropy Film by Magnetron Sputtering
    Yanxia Liang, Peipei Wang, Yufei Wang, and 9 more authors
    Materials, 2019