Y. Isabel Liu 刘亦颉

PhD Student @ MIT CSAIL

Hi there! I’m a first-year PhD student at MIT CSAIL and EECS, advised by Prof. Leslie Kaelbling and Prof. Tomás Lozano-Pérez. Prior to MIT, I obtained my bachelor’s degree in CS and Math from Princeton University, where I worked with Prof. Tom Silver, Prof. Benjamin Eysenbach, and Prof. Elad Hazan.

Education

Research

General-purpose robots must operate effectively in partially observable, shared and dynamic environments. To do so, a robot needs to make effective decisions about what information to acquire, how to represent it, how much computation to perform and when to act, given limited resources. I consider these decisions together, since they draw on a finite resource budget. Humans naturally make such trade-offs. My research goal is to understand the underlying principles, and enable robots to perform such trade-offs effectively.

Some tools we can leverage are:

News

Publications

  1. CoRL

    Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them

    Carlota Parés-Morlans, Nils Kuhn, Y. Isabel Liu, Alberta Longhini, Jeannette Bohg
    Conference on Robot Learning (CoRL) 2026Spotlight
  2. CoRL

    Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures

    Bowen Li, Mayank Mishra, Y. Isabel Liu, Stone Tao, Nishanth Kumar, Alexander G. Gray, Ruwan Wickramarachchi, Jonathan Francis, Sebastian Scherer, Tom Silver
    Conference on Robot Learning (CoRL) 2026
  3. ICLR

    SLAP: Shortcut Learning for Abstract Planning

    Y. Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver
    International Conference on Learning Representations (ICLR) 2026
  4. Flash STU: Fast Spectral Transform UnitsCDC

    Flash STU: Fast Spectral Transform Units

    Y. Isabel Liu*, Windsor Nguyen*, Yagiz Devre, Evan Dogariu, Anirudha Majumdar, Elad Hazan
    IEEE Conference on Decision and Control (CDC) 2025

Awards & Honors

Contact

Email
isabeliu [at] csail [dot] mit [dot] edu
Social Media