I am a 1st/3rd year PhD student at Carnegie Mellon University’s Language Technologies Institute. My research focuses on alignment and reasoning for large language models. I am advised by Professor Mona Diab at CMU and work closely with Professor Zhijing Jin at the University of Toronto. I have completed internships at Amazon Rufus in Seattle in 2025, where I worked on honesty alignment for reasoning models; at Amazon AWS Bedrock in New York in 2024, where I studied multimodal hallucination; and at WarpEngine in Shanghai in 2023, where I built a personalized chatbot product.
Previously, I worked with Professors Rada Mihalcea and Zhijing Jin in the LIT group at the University of Michigan on NLP for social good. I have also had a great time working with Professor Wei Hu on improving the worst-group robustness.
PhD in Language Technologies, Aug 2025 - ??
Carnegie Mellon University, Pittsburgh
Master of Language Technologies, Sept 2023 - May 2025
Carnegie Mellon University, Pittsburgh
BSE in Computer Science, Sept 2021 - May 2023
University of Michigan, Ann Arbor
BSE in Electrical and Computer Engineering, Sept 2019 - Aug 2023
Shanghai Jiao Tong University
"Language Model Alignment in Multilingual Trolley Problems"
NeurIPS PLuralistic Alignment Workshop 2024 Oral
"Synatra: Turning indirect knowledge into direct demonstrations for digital agents at scale"
NeurIPS 2024
"Inducing Elasticity in Foundation Models: Post-Training Techniques for Adaptable Inference"
NeurIPS ENLSP Workshop 2024