I'm on the academic and industry job markets!
Hi, I'm Angie! I'm a final-year PhD candidate at MIT CSAIL advised by Arvind Satyanarayan in the Visualization Group. My research focuses on improving human-AI alignment by designing systems that reveal model representations and methods to shift them toward human expectations. I am honored to have my research supported by the MIT John Jarve Fellowship and Apple Scholars in AI/ML PhD Fellowship.
Previously, I received my SB and MEng in computer science from MIT, where I worked with Jim Glass and David Harwath in the Spoken Language Systems Group. Throughout my PhD, I've interned at Apple Research with Fred Hohman and IBM Research with Hendrik Strobelt.
Recent News
I will be at CHI in Yokohama 🌸 presenting Abstraction Alignment!
Gave a guest lecture 📚 on AI interpretability in Brown's Sociotechnical Systems and HCI course!
I will be at IEEE VIS 2024 chairing VISxAI and presenting Compress and Compare! 📊
Had a great time as a panelist at the NEMI 2024 workshop, discussing how mechanistic interpretability can help keep AI safe and beneficial. 🤖
Honored to receive an Apple Scholars in AI/ML PhD fellowship! 🍎
Today is my last day interning at Apple! The only thing better than Seattle in the summer 🌲 🌞 was getting to work with Fred Hohman, Yannick Assogba, Donghao Ren, Dominik Moritz, and Venkat Sivaraman!
Our paper, VisText, received an outstanding paper award 🏆 at ACL!
Publications
Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
Under Review at ICLR 2026
Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
CHI 2025
Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments
VIS 2024
DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
arXiv 2023
VisText: A Benchmark for Semantically Rich Chart Captioning
ACL 2023
Outstanding Paper
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
FAccT 2023
Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior
CHI 2022
Best Paper Honorable Mention
Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples
IUI 2022
Best Paper Honorable Mention