Zixian Ma

Zixian Ma is a computer science researcher specializing in vision-language models and multimodal learning. She is currently pursuing a PhD at the University of Washington and conducting related research at the Allen Institute for Artificial Intelligence (Ai2). She holds a Bachelor's and Master's degree in Computer Science from Stanford University, where she engaged in deep learning and computer vision research at the Stanford Vision Lab. Her work focuses on designing and evaluating multimodal models, optimizing human-computer interaction, as well as generation and reasoning in vision-language models. Her research has been published in top conferences such as NeurIPS, CVPR, and EMNLP, and she has received multiple awards, including the Two Sigma PhD Fellowship and Qualcomm Innovation Fellowship.

• [2023–Present]·Ai2 (Allen Institute for Artificial Intelligence)·Researcher
  • Focused on research and application of multimodal models, including optimizing vision-language models and evaluating tool usability.

• [2018–2023]·Stanford University·Bachelor's and Master's in Computer Science
  • Majored in Computer Science with a focus on computer vision, deep learning, and human-computer interaction, and joined research projects at the Stanford Vision Lab.