Zixian Ma headshot

Ph.D. Student @ University of Washington

zixianma [at] cs.washington.edu

My goal is to build multimodal agents as new interfaces through which people act in digital and physical worlds.

Hi! I am a PhD student (2023 - ?) in Computer Science and Engineering at the University of Washington, advised by Prof. Ranjay Krishna and Prof. Dan Weld, and supported by the Qualcomm Innovation Fellowship and Two Sigma PhD Fellowship. I build open vision-language models (Molmo2, MolmoPoint), agents that act on the web and with tools (MolmoWeb, LATTE), and benchmarks of what these systems can and can't do (Task Me Anything, CREPE). Before UW, I received my B.S. (Honors) and M.S. in Computer Science from Stanford, where I was fortunate to work with Prof. Fei-Fei Li and Prof. Michael Bernstein. Outside of research, you can find me 🍳 🎾 💃 🎤 🎟️ 🍵

4.8M+ Hugging Face downloads
1.7K+ GitHub stars
4 oral & highlight papers
3 best paper recognitions (1 conference, 2 workshop)

Recent highlights

More news

Awards & fellowships

Selected works

* equal contribution · † project lead · ♥ core contributor · full list on Google Scholar

Open vision-language models

Models and data that let agents see, point, and track in images, videos, and figures.

Multimodal agents

Agents that plan, use tools, and act on the web.

Evaluating multimodal models

Benchmarks that reveal what vision-language models can and can't do.

Human-AI interaction

How people evaluate and collaborate with AI.

Industry experience

Service & mentoring

Workshop organizer

Mentoring