J. Tae Emmerson

/teɪ/; pronounced tay
[email protected]

me (front) the dog
linkedin
google scholar
rabbit hole
I am an incoming graduate student at the UC San Diego. My interests span multimodal learning, inference optimization, AI safety, fairness and reasoning. Currently, I work at the Vector Institute under the supervision of Professor Zhijing Jin, affiliated with the University of Toronto, to make models safer and more governable.

Previously, I graduated with a Bachelor of Science in Computer Science from the University of Pittsburgh in 2024. While earning my degree, I worked part-time as a researcher and engineer at Signature Diagnostics with Professor Paul Cohen. After graduating, I was fortunate to work with Professor Adriana Kovashka and Professor Ryan Shi.

You might find me in either Pittsburgh, PA or San Diego, CA depending on the time of the year. If you're interested in a quick coffee chat or collaborating together, feel free to reach out!

Publications

CauSciBench: Can LLMs Automate Causal Inference in Real-World Scientific Research?
Sawal Acharya, Terry Jingchen Zhang, Andrew Kim, Rahul Babu Shrestha, Xianlin Sun, Pepijn Cobben, Maximilian Mordig, Tae Emmerson, Anahita Haghighat, Furkan Danisman, Yuen Chen, Clijo Jose, Andrei Ioan Muresanu, Justin Cui, Jiarui Liu, Yahang Qi, Punya Syon Pandey, Yinya Huang, Bernhard Schölkopf, Zhijing Jin ICML'26 | International Conference on Machine Learning
pdf|abstract

Causal AI Scientist: Towards End-to-End Causal Inference with Large Language Models
Sawal Acharya, Rahul Babu Shrestha, Tae Emmerson, Vishal Verma, Devansh Bhardwaj, Samuel Simko, Punya Syon Pandey, Anahita Haghighat, Yongjin Yang, Dominik Janzing, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin ICML'26 Workshop | Workshop on AI for Math, CS & ML
pdf|abstract

A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modeling
Kyle Buettner, Tae Emmerson, Adriana Kovashka IJCNLP-AACL'25 | International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics
pdf|abstract

Towards Automated Scoping of AI for Social Good Projects
Tae Emmerson, Rayid Ghani, Ryan Shi
preprint
pdf|abstract

B.Sc. Computer Science
University of Pittsburgh
2021 - 2024
M.Sc. Computer Science
University of California - San Diego
2026 - Present
Research Intern
Vector Institute
2025 - Present
Technical Member
EuroSafeAI
2026 - Present