IconCarter Blair
Picture of the author

I am currently doing a Master of Math in Computer Science at UWaterloo where I'm supervised byKate LarsonandEdith Law. My research mainly focuses on the intersection between social choice, reinforcement learning, and human-AI interaction. I am currently excited about participatory and pluralistic approaches to AI alignment.

You can reach me at cblair at uwaterloo dot ca.

Google Scholar LogoLinkedIn LogoGitHub LogoCV Logo

News

Publications

2024

Democratizing Reward Design for Personal and Representative Value-Alignment

Carter Blair, Kate Larson, Edith Law

Under review for CHI 2025
ArXiv LogoArXivPDF

Altared Environments: The Role of Normative Infrastructure in AI Alignment

Rakshit Trivedi, Nikhil Chandak, Carter Blair, Atrisha Sarkar, Tehilla Weltman, Dylan Hadfield-Menell, Gillian K Hadfield

Agentic Markets Workshop at ICML 2024
PDF

Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation

Atrisha Sarkar, Andrei Ioan Muresanu, Carter Blair, Aaryam Sharma, Rakshit S Trivedi, Gillian K Hadfield

Foundation Models and Game Theory Workshop at Economics and Computation 2024
ArXiv LogoArXivPDF

Liquid Ensemble Selection For Continual Learning

Carter Blair, Ben Armstrong, Kate Larson

AAMAS SCaLA Workshop 2024Canadian AI 2024
ArXiv LogoArXivPDF

Quantifying Emotional Responses to Immutable Data Characteristics and Designer Choices in Data Visualizations

Carter Blair, Xiyao Wang, Charles Perin

IEEE VIS 2024
ArXiv LogoArXivPDF