| layout | wide |
|---|---|
| author_profile | false |
Freya Tan
Hi, I'm Freya, a dual-degree graduate student in Electrical Engineering & Computer Science (EECS) and City Planning (DUSP) at MIT. My work sits at the intersection of artificial intelligence, machine learning, and urban systems, with a focus on applying computational methods to real-world challenges in infrastructure, mobility, and environmental resilience.
<p>
At the <a href="https://cityform.mit.edu/">City Form Lab</a>, I lead spatial modeling projects that apply graph-based network analysis and geospatial indexing techniques to estimate pedestrian activity across Maine. I also contribute to a research using vision-language models to detect and analyze social behavior from large-scale street view imagery datasets. My technical work includes building scalable data pipelines and applying spatial indexing and trajectory modeling to extract insights from multi-source urban data.
</p>
<p>
Previously, I worked as a Machine Learning Engineer Intern at Symmons Evolution, where I designed predictive ML systems and LLM-powered diagnostic tools for real-time building energy management. My work focused on developing generative AI solutions that integrated structured sensor data, enhancing LLM reliability through prompt engineering.
</p>
<p>
With a strong background in computer vision, spatial analytics, and systems modeling, I'm passionate about advancing AI-driven approaches that bridge machine learning and LLMs with real-world challenges to design more intelligent, resilient, and inclusive systems.
</p>
</div>
<!-- Right image content - larger headshot -->
<div style="flex: 1.2; display: flex; justify-content: center;">
<img src="/assets/images/freya_2024.png" alt="Freya's photo" style="max-width: 100%; box-shadow: 0 4px 8px rgba(0,0,0,0.1);">
</div>
Research Highlights
Analyzing human movement patterns and pedestrian behavior using spatial modeling, graph-based network analysis, and large-scale trajectory data to understand urban mobility dynamics.
Applying computer vision and multimodal AI models to urban imagery for detecting social interactions, analyzing built environments, and extracting spatial insights from visual data.
Developing LLM-powered systems for urban analytics, integrating structured sensor data with generative AI to create intelligent diagnostic and predictive urban systems.
Research and Projects
The world is changing because of the innovative methods of AI, and so am I. Much of my recent work is still in the peer review process or in draft form, but I will post as much as I can here.
Here are some highlights from my research portfolio. For a complete list of projects, please visit my Research & Projects page or check out my Publications.
{% include projects-section.html limit=3 %}
News
Stay updated with the latest news and developments in my research and projects.
{% include news-section.html limit=3 %}