Hello!
I am Yihao. I am a final-year PhD candidate in the Computer Science department of UCLA, advised by Professor Baharan Mirzasoleiman.
My research focuses on understanding and enhancing the reliability of AI. I am currently working on LLM reasoning and safety alignment, and my previous research has also covered robustness and generalization, multimodal learning, and self-supervised learning.
I have recently received the OpenAI Superalignment Fast Grants🚀🚀
Email: yihaoxue [at] g.ucla.edu
Me (right)
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
Yihao Xue, Jiping Li, Baharan Mirzasoleiman
ICML, 2025
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
Investigating the Benefits of Projection Head for Representation Learning
Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman
ICLR, 2024
Yihao Xue, Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman
ICML, 2023 (Oral Presentation, 2.37%)
Investigating Why Contrastive Learning Benefits Robustness Against Label Noise
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
ICML, 2022
LoRA is All You Need for Safety Alignment of Reasoning LLMs
Yihao Xue, Baharan Mirzasoleiman
Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection
Yihao Xue, Kristjan Greenewald, Youssef Mroueh, Baharan Mirzasoleiman
Towards Mitigating Spurious Correlations in the Wild: A Benchmark & a more Realistic Dataset
Siddharth Joshi, Yu Yang, Yihao Xue, Wenhan Yang and Baharan Mirzasoleiman
Student Researcher, Google, Jun. 2025 - Present
with Vincent Cohen-Addad
Research Intern, MIT-IBM Watson AI Lab, Cambridge, Jun. 2024 - Sept. 2024
with Youssef Mroueh and Kristjan Greenewald
Research Intern, Cisco, Remote, Jun. 2022 - Sep. 2022
with Ali Payani
Outstanding reviewer of ICML 2022
Reviewer for ICML, Neurips, ICLR, IJCAI
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.