About me
I am a PhD student at MIT Media Lab under the supervision of Dr. Paul Liang. My research interests lie in the field of multimodal learning, particularly multimodal LLMs, and its applications to healthcare. My recent interest lies in methods of training large MLLMs on highly heterogeneous and noisy real-world data.
Before joining MIT, I was a masters student at Stanford University majoring in Computer Science. I was a research assistant in Stanford SVL and Partnership in AI-Assisted Care (PAC) Lab supervised by Dr. Li Fei-Fei and Dr. Ehsan Adeli.
Before joining Stanford, I graduated with the highest honor in Computer Science and Math from Emory University. I was in Emory Brain Network Lab under the supervision of Dr. Carl Yang, working on graph mining in the area of healthcare.
Publications
Wei Dai, Peilin Chen, Chanakya Ekbote, Paul Pu Liang, QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training, Conference on Neural Information Processing Systems (NeurIPS), 2025. Oral Presentation (Top 0.36%).
Wei Dai, Peilin Chen, Malinda Lu, Daniel Li, Haowen Wei, Hejie Cui, Paul Pu Liang: Data Foundations for Large Scale Multimodal Clinical Foundation Models, International Conference on Machine Learning (ICML), 2025.
Wei Dai, Zelun Luo, Debadutta Dash, Shrinidhi Kowshika Lakshmikanth, Ehsan Adeli, Arnold Milstein, Li Fei-Fei, Kevin Schulman: Developing ICU Clinical Behavioral Atlas Using Ambient Intelligence and Computer Vision, The New England Journal of Medicine AI (NEJM-AI), 2025.
Wei Dai, Hejie Cui, Xuan Kan, Ying Guo, Carl Yang: Transformer Based Hierarchical Clustering on Brain Networks, IEEE International Symposium on Biomedical Imaging (IEEE-ISBI), 2023.
Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, Carl Yang: Brain Network Transformer, Conference on Neural Information Processing Systems (NeurIPS), 2022. (Spotlight Presentation)
Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang. Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis, MICCAI, 2022. (Oral Presentation, top 2%, Poster)
Hejie Cui, Wei Dai, Yanqiao Zhu, Xuan Kan, Antonio Aodong Chen Gu, Joshua Lukemire, Liang Zhan, Lifang He, Ying Guo, Carl Yang. BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks, IEEE-TMI, 2022.
Wei Dai: Introduction to Monstrous Moonshine, Emory Undergraduate Research Symposia (EURS), 2021
Megan Lagerquist, Wei Dai, Teresa Yu, Yi Cao: Cross-Culture Analysis of Gender and Royalty in Folktales with an Application of Natural Language Processing Tools, SouthEastern Undergraduate Sociology Symposium (SEUSS), 2021
Preprints
Hengzhi Li, Brendon Jiang, Alexander Naehu, Regan Song, Justin Zhang, Megan Tjandrasuwita, Chanakya Ekbote, Steven-Shine Chen, Adithya Balachandran, Wei Dai, Rebecca Chang, Paul Pu Liang, PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
Wei Dai, Zelun Luo, Zane Durante, Debadutta Dash, Arnold Milstein, Kevin Schulman, Ehsan Adeli, Li Fei-Fei: Towards Fine-Grained Video Question Answering.