Luise Ge
email  / 
CV  / 
Teaching
I am a Computer Science PhD candidate at Washington University in St. Louis, advised by Prof. Yevgeniy Vorobeychik and Prof. Brendan Juba.
My research agenda is to develop foundations for pluralistic alignment—ensuring AI systems can navigate and respond to the inherent diversity and evolving nature of human values.
This challenge is multifaceted: individual values shift through emotional, cognitive, and social processes, while collective values may emerge from complex societal interactions or remain undefined and contested.
I aim to address alignment at both personal and societal scales, considering AI models both in terms of their internal representations and their interactions with the outside world.
To this end, I integrate methods from computational social choice, learning theory, logic, and optimization to study questions of value representation, aggregation, and adaptation in AI systems.
I started out as a cognitive science student at the University of Edinburgh, with the passion to figure out how mind works. While this curiosity has never diminished, it just happened that the beauty of maths struck me greatly.
I ended up getting a MSc in pure maths at Imperial College London under the guidance of the amazing Paolo Cascini. My master thesis was on algebraic geometry inspired by a fantastic idea called "the periodic table of shapes".
I have turned back to CS due to both the philosophical considerations and social impact of many computational problems. Outside of research, I enjoy reading, traveling, and engaging with art in all its forms.
|
|
News
- [May 2025] Our paper Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks is accepted into ICML 2025!
- [April 2025] Our paper Polynomial-Time Relational Probabilistic Inference in Open Universes is accepted into IJCAI 2025!
- [Oct 2024] I am going to attend the 10th Conference of Algorithmic Decision Theory at DIMACS, Rutgers University.
- [Sep 2024] Our paper Axioms for AI Alignment from Human Feedback is accepted into Neurips Spotlights!
- [May 2024] I will be presenting at the AAMAS 2024 Workshop on Social Choice and Learning Algorithms in Auckland, New Zealand
|
Research
-
Polynomial-Time Relational Probabilistic Inference in Open Universes
(α-β) Luise Ge,
Brendan Juba,
Kris Nilsson
IJCAI 2025
[arXiv] [tutorial]
-
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
Luise Ge,
Michael Lanier,
Anindya Sarkar,
Bengisu Guresti,
Yevgeniy Vorobeychik,
Chongjie Zhang
ICML 2025
[arXiv] [Shorter slides] [Invited Talk at MIT]
-
Axioms for AI Alignment from Human Feedback
(α-β) Luise Ge,
Daniel Halpern,
Evi Micha,
Ariel D. Procaccia,
Itai Shapira,
Yevgeniy Vorobeychik,
Junlin Wu
✦ Spotlight ✦ at NeurIPS 2024
[pdf]
-
Learning Linear Utility Functions From Pairwise Comparison Queries
Luise Ge,
Brendan Juba,
Yevgeniy Vorobeychik
AAMAS 2024 Workshop/ ADT 2024 abstract
[pdf] [arXiv] [slides]
-
Fair Allocation: Implementing and Evaluating an Algorithm for Competitive Allocation of Chores
Outstanding undergraduate thesis supervised by
Kousha Etessami
University of Edinburgh, 2022
[pdf]
|
|