Two Sigma Fellowships recognize doctoral students pushing the frontiers of STEM fields such as applied mathematics, computer science, physics, and statistics. In our series, The Fellowship Forum, we catch up with past and present Two Sigma Fellows to spotlight the fascinating research they’re pursuing in their respective fields.
Zixian Ma is a Two Sigma Fellow and doctoral student at the University of Washington. We spoke with Zixian about how the Two Sigma Fellowship has supported her doctoral journey and her work in AI — spanning multimodal agents, vision-language models, and human-AI interaction.
What is your area of research, and what excites you most about the field?
I work at the intersection of Computer Vision, Natural Language Processing, and Human-Computer Interaction. My research interests broadly span multimodal language models, agents, and human-agent interaction. I’m most excited about future models and agents becoming better at fine-grained perception and smarter in how they interact with people.
What does having the fellowship behind you mean for the day-to-day reality of doing your research?
Having the fellowship behind me gives me both practical freedom and confidence that the research direction I’m pursuing matters to the broader research community and industry. It allows me to focus on building interactive multimodal AI systems that can understand the world, interact with people, and help solve real-world problems. It also gives me room to pursue more ambitious, higher-risk ideas without constantly optimizing for short-term milestones.
What’s happening in your field right now that you think deserves more attention?
Foundation models are becoming increasingly interactive, and we’re moving toward more real-time forms of interaction that go beyond turn-based exchanges. I think we should pay more attention to improving human-agent interaction – not only by making models more interactive, but also by developing better ways to support more expressive forms of human intent specification.
What’s something about your doctorate journey that has surprised you?
I’m surprised by how much I’ve learned, not only about research, but also about myself and life in general. I now have a better sense of my strengths and weaknesses and have developed a more concrete vision of the person I’d like to become. Oh, and I’m also surprised by how fast time flies! I guess that means I’ve mostly enjoyed my PhD life : )
What advice would you give someone starting a doctorate?
What to work on is arguably one of the most important questions to think about. Choosing a research direction is very important, but it is also a deeply personal decision. I’d suggest choosing your research projects based on your own excitement, principles, and goals rather than external signals.
What’s a question or idea outside your core research that you can’t stop thinking about?
Outside my core research, I can’t help thinking about one question: What will be the next groundbreaking technology to fundamentally and positively transform human lives? What will be the next internet, the next mouse, or the next ChatGPT?
Is there something you’re passionate about beyond your research that influences how you approach your work?
Yes, I’m also passionate about good design and effective visualization. That passion has influenced both my research topics and my style of scientific communication. I love making figures and finding the simplest visual ways to convey complex ideas.