Michael S. Lee — accepted AI-conference papers

2026

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Yu Ying Chiu, Michael S. Lee, Rachel Calcott, Brandon Handoko, Paul de Font-Reaulx, Paula Rodriguez +12

ICLR 2026poster

As AI systems progresses, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provid…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Making AI Policies Transparent to Humans through Demonstrations

Michael S. Lee

AAAI 2024technical

Demonstrations are a powerful way of increasing the transparency of AI policies to humans. Though we can approximately model human learning from demonstrations as inverse reinforcement learning, we note that human learning can differ from algorithmic learning in key ways, e.g. humans are computation…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning

Michael S. Lee, Henny Admoni, Reid Simmons

IROS 2022poster

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement learning (IRL). Thus, robots can convey their beliefs and desires…

Cited by 18 Source ↗Scholar ↗

2018

Active Range and Bearing-based Radiation Source Localization

Michael S. Lee, Daniel Shy, William Red Whittaker, Nathan Michael

IROS 2018poster

3D radiation source localization is a common task across applications such as decommissioning, disaster response, and security, but traditional count-based sensors struggle to efficiently disambiguate between symmetries in sensor, source, and environment configurations. Recent works have demonstrate…

Cited by 22 Source ↗Scholar ↗