prof_pic.jpg

I’m a Ph.D. candidate at Stanford CS, advised by Chelsea Finn and part of the IRIS lab. I am affiliated with SAIL, CRFM, and the ML Group at Stanford. My research is generously supported through grants and fellowships from OpenAI and KFAS. During my mandatory military service in South Korea, I served as a research scientist at Kakao and AITRICS, collaborating with Juho Lee. I hold a master’s degree in Computer Science (advised by Seungjin Choi) from POSTECH.

Here are some key questions that guide my research:

  • Teaching strong models: Pre-trained models already hold much of what we need to teach. How can we develop teaching paradigms that better leverage these inherent capabilities?
  • Underspecification: No dataset fully specifies its intended task. How can we help models recognize and represent the multiple valid interpretations of the data, and how do we best leverage this diversity of hypotheses?
  • Understanding information: Data carries an underlying essence (“information”) that goes beyond its specific form. How can we better conceptualize this notion and understand how models extract, process, and communicate it?

My name (윤호) is pronounced like ‘you-know’ said quickly, with an emphasis on ‘you’. Here is a good approximation.

Selected Papers

Test-Time Alignment via Hypothesis Reweighting

Yoonho Lee, Jonathan Williams, Henrik Marklund, Archit Sharma, Eric Mitchell, Anikait Singh, Chelsea Finn

arXiv preprint

Clarify: Improving Model Robustness with Natural Language Corrections

Yoonho Lee, Michelle Lam, Helena Vasconcelos, Michael S. Bernstein, Chelsea Finn

UIST 2024, NeurIPS 2023 workshops XAIA and ICBINB

AutoFT: Learning an Objective for Robust Fine-Tuning

Caroline Choi*, Yoonho Lee*, Annie S. Chen, Allan Zhou, Aditi Raghunathan, Chelsea Finn

NeurIPS 2023 workshop DistShift

Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features

Annie S. Chen*, Yoonho Lee*, Amrith Setlur, Sergey Levine, Chelsea Finn

ICLR 2024 (spotlight)

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning, Chelsea Finn

ICML 2023 (long oral)

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Yoonho Lee*, Annie S. Chen*, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn

ICLR 2023

Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks

Juho Lee, Yoonho Lee, Jungtaek Kim, Adam Kosiorek, Seungjin Choi, Yee Whye Teh

ICML 2019