photo taken by Ruizhi Liao

Peiqi Wang I am a Ph.D. student at MIT CSAIL. I work in the Medical Vision Group, advised by Polina Golland. I am interested in problems in medical vision and machine learning in healthcare, and more recently, in large language models. I interned at Deep Genomics, MIT-IBM Watson AI Lab, and Meta. Previously, I completed my B.S. in Computer Science at University of Toronto, where I worked on a few projects with Kyros Kutulakos, Kenneth Jackson. [ CV  |  Google Scholar  |  GitHub  |  LinkedIn  |  Twitter ]

Inference Compute-Optimal Video Vision Language Models
Peiqi Wang, ShengYun Peng, Xuewen Zhang, Hanchao Yu, Yibo Yang, Lifu Huang, Fujun Liu, Qifan Wang
Annual Meeting of the Association for Computational Linguistics (ACL), 2025
[ arXiv  |  Code ]

Calibrating Expressions of Certainty
Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M. Wells, Tina Kapur, Polina Golland
International Conference on Learning Representations (ICLR), 2025
[ arXiv  |  OpenReview  |  Code  |  Poster  |  MIT News  |  Spotify ]

Diversity Measurement and Subset Selection for Instruction Tuning Datasets
Peiqi Wang, Yikang Shen, Zhen Guo, Matthew Stallone, Yoon Kim, Polina Golland, Rameswar Panda
ICLR 2025 DATA-FM Workshop
[ arXiv  |  OpenReview ]

Sample-Specific Debiasing for Better Image-Text Models
Peiqi Wang, Yingcheng Liu, Ching-Yun Ko, William M Wells, Seth Berkowitz, Steven Horng, Polina Golland
Machine Learning for Healthcare Conference (MLHC), 2023
[ arXiv  |  Paper  |  Poster ]

Using Multiple Instance Learning to Build Multimodal Representations
Peiqi Wang, William M. Wells, Seth Berkowitz, Steven Horng, and Polina Golland
Information Processing in Medical Imaging (IPMI), 2023
[ arXiv  |  Paper  |  Poster ]