Zihao Yang

Zihao Yang

Research Intern at NYU VisionX. Graduated with a Bachelor's degree in CS & DS from NYU.

Hi, there! I’m Zihao(Gavin).

I am working in VisionX Lab as a research intern, advised by Professor Saining Xie. I graduated cum laude from New York University with a Bachelor’s degree in Computer Science and Data Science. Previously during my undergraduate program, I was working in OLAB and Memo Lab, advised by Professor Eric K. Oermann and Professor Chen Shuo. My research interests include Multimodality and AI for Science & Healthcare. My research currently focuses on compressing multimodal language models and improving their efficiency to enhance accessibility and broaden their applications.

I have been fortunate to be advised by Professor Xie, Professor Oermann, and Professor Shuo. I am also grateful for the memtorship from Lavender Y. Jiang, Xujin C. Liu, Professor Kyunghyun Cho, and Professor Samuel R. Bowman.

Email: zy2091@nyu.edu. CV: link.

Publication

Refining Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models
Yanbing Chen, Ruilin Wang, Zihao Yang, Lavender Jiang, Eric Oermann
Preprint

Medical large language models are vulnerable to attack
Daniel Alber, Zihao Yang, Anton Alyakin, Eunice Yang, Sumedha Rai, Aly Vallliani, Gabriel Rosenbaum, Ashley Amend-Thomas, David Kurland, Caroline Kremer, Alexander Eremiev, Bruck Negash, Daniel Wiggan, Michelle Nakatsuka, Karl Sangwon, Sean Neifert, Hammad Khan, Akshay Save, Adhith Palla, Eric Grin, Monika Hedman, Mustafa Nasir-Moin, Chris Liu, Lavender Jiang, Michal Mankowski, Dorry Segev, Yindalon Aphinyanaphongs, Howard Riina, John Golfinos, Daniel Orringer, Eric Oermann
Accepted for publication at Nature Medicine (Paper is available upon request.)

BPQA Dataset: Evaluating How Well Language Models Leverage Blood Pressures to Answer Biomedical Questions
Chi Hang, Ruiqi Deng, Lavender Jiang, Zihao Yang, Daniel Alber, Anton Alyakin, Eric Oermann
(Preprint will be posted soon. Paper is available upon request.)

Language Models Can Guess Your Identities from De-identified Clinical Notes
Lavender Jiang, Daniel Alber, Zihao Yang, Karl Sangwon, Xujin Liu, Kyunghyun Cho, Eric Oermann
Under review at ML4H 2024

Intriguing Effect of the Correlation Prior on ICD-9 Code Assignment
Zihao Yang, Chenkang Zhang, Muru Wu, Xujin Liu, Lavender Jiang, Kyunghyun Cho, Eric Oermann
ACL 2023 SRW

Education

  • (2020-2024) B.A., Computer Science & Data Science, New York University, New York, USA