Yijia Dai

CS Ph.D. Student @ Cornell. 问心无愧.

yijia_looking.jpg

👋 ▫️ 👍 👀 ❕

I am a third-year Ph.D. student at Cornell, co-advised by Prof. Sarah Dean and Prof. Jennifer Sun. I am also a visiting student researcher in the Branson Lab at HHMI Janelia Research Campus.

I am interested in deep generative models across domains, from language to biological signals—understanding how strong models succeed on well-understood tasks, and using them to uncover new structure in less-understood signals from nature.

Publications

2025

  1. hmm.png
    Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context
    Yijia Dai, Zhaolin Gao, Yahya Sattar, and 2 more authors
    NeurIPS, 2025
    paper
  2. llm_training_v3.png
    LangPTune: Optimizing Language-based User Profiles for Recommendation
    Zhaolin Gao, Joyce Zhou, Yijia Dai, and 1 more author
    In CIKM, 2025
    paper
  3. ae.png
    Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration
    Viraj Mehta, Vikramjeet Das, Ojash Neopane, and 4 more authors
    COLM, 2025
    paper

2024

  1. pipeline_v1.png
    Language-Based User Profiles for Recommendation
    Joyce Zhou, Yijia Dai, and Thorsten Joachims
    WSDM, 2024
    paper

2023

  1. recsys_flowchart.gif
    Representation Learning in Low-rank Slate-based Recommender Systems
    Yijia Dai, and Wen Sun
    MFPL workshop @ ICML, 2023
    paper Poster

2019

  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
    paper