Search Results for author: Mariah L. Schrum

Found 3 papers, 0 papers with code

CoS: Enhancing Personalization and Mitigating Bias with Context Steering

no code implementations2 May 2024 Jerry Zhi-Yang He, Sashrika Pandey, Mariah L. Schrum, Anca Dragan

Proper usage of the context enables the LLM to generate personalized responses, whereas inappropriate contextual influence can lead to stereotypical and potentially harmful generations (e. g. associating "female" with "housekeeper").

Bayesian Inference Language Modelling +1

MAVERIC: A Data-Driven Approach to Personalized Autonomous Driving

no code implementations20 Jan 2023 Mariah L. Schrum, Emily Sumner, Matthew C. Gombolay, Andrew Best

We find that our approach generates driving styles consistent with end-user styles (p<. 001) and participants rate our approach as more similar to their level of aggressiveness (p=. 002).

Autonomous Driving

Meta-active Learning in Probabilistically-Safe Optimization

no code implementations7 Jul 2020 Mariah L. Schrum, Mark Connolly, Eric Cole, Mihir Ghetiya, Robert Gross, Matthew C. Gombolay

Learning to control a safety-critical system with latent dynamics (e. g. for deep brain stimulation) requires taking calculated risks to gain information as efficiently as possible.

Active Learning Meta-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.