Hello!

I am Yihao. I am a third year PhD student in the Computer Science department of UCLA, advised by Professor Baharan Mirzasoleiman

My research focuses on understanding and enhancing the reliability of machine learning. I primarily approach this by studying how inputs are represented within machine learning models and how the structure of these representations affects models' generalization and robustness.

I have recently received the OpenAI Superalignment Fast Grants🚀🚀

Email: yihaoxue [at] g.ucla.edu

Publications


Few-shot Adaption to Distribution Shifts By Mixing Source and Target Embeddings

Yihao Xue, Ali Payani, Yu Yang, Baharan Mirzasoleiman

ICML, 2024


Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise

Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman

UAI, 2024 (Spotlight)


Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

Yihao Xue, Siddharth Joshi, Dang Nguyen, Baharan Mirzasoleiman

ICLR, 2024

[project page]


Investigating the Benefits of Projection Head for Representation Learning

Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman

ICLR, 2024

[project page]


Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression.

Yihao Xue,  Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman

ICML, 2023 (Oral Presentation, 2.37%)

[project page]


Investigating Why Contrastive Learning Benefits Robustness Against Label Noise

Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman

ICML, 2022


Preprints

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions

Yihao Xue, Jiping Li, Baharan Mirzasoleiman

ArXiv, 2025


Towards Mitigating Spurious Correlations in the Wild: A Benchmark & a more Realistic Dataset

Siddharth Joshi, Yu Yang, Yihao Xue, Wenhan Yang and Baharan Mirzasoleiman


Experience

Research Intern, MIT-IBM Watson AI Lab, Cambridge, Jun. 2024 - Sept. 2024

Research Intern, Cisco, Remote, Jun. 2022 - Sep. 2022

Professional Activities

Outstanding reviewer of ICML 2022

Reviewer for ICML, Neurips, ICLR, IJCAI

More about me

My last name is pronounced as  [ sh EW eh ].

I like playing tennis and ping-pong, watching TV shows and spending lots of time doing nothing.


... And if you're wondering what I do during those nothing moments – well, it's not exactly nothing. I listen to music quite a bit, particularly when it comes to certain types of classical music. Here's a glimpse of my top 6 favorite musicians at the moment. Feel free to reach out if you share the same interest and would like to discuss music ... or research.