226 citations · 272 across the 15 of their papers we have counts for
15 papers
A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehicles
Ruya Karagulle, Nikos Arechiga, Andrew Best +2
This work introduces a preference learning method that ensures adherence to given specifications, with an application to autonomous vehicles. Our approach incorporates the priority…
Training Towards Critical Use: Learning to Situate AI Predictions Relative to Human Knowledge
Anna Kawakami, Luke Guerdan, Yanghuidi Cheng +6
A growing body of research has explored how to support humans in making better use of AI-based decision support, including via training and onboarding. Existing research has focuse…
Drag-guided diffusion models for vehicle image generation
Nikos Arechiga, Frank Permenter, Binyang Song +1
Denoising diffusion models trained at web-scale have revolutionized image generation. The application of these tools to engineering design is an intriguing possibility, but is curr…
Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderings
Binyang Song, Chenyang Yuan, Frank Permenter +2
Generative AI models have made significant progress in automating the creation of 3D shapes, which has the potential to transform car design. In engineering design and optimization…
Towards a Learner-Centered Explainable AI: Lessons from the learning sciences
Anna Kawakami, Luke Guerdan, Yang Cheng +8
In this short paper, we argue for a refocusing of XAI around human learning goals. Drawing upon approaches and theories from the learning sciences, we propose a framework for the l…
Second-Order Sensitivity Analysis for Bilevel Optimization
Robert Dyro, Edward Schmerling, Nikos Arechiga +1
In this work we derive a second-order approach to bilevel optimization, a type of mathematical programming in which the solution to a parameterized optimization problem (the "lower…
Understanding and Shifting Preferences for Battery Electric Vehicles
Nikos Arechiga, Francine Chen, Rumen Iliev +12
Identifying personalized interventions for an individual is an important task. Recent work has shown that interventions that do not consider the demographic background of individua…
Finding Label and Model Errors in Perception Data With Learned Observation Assertions
Daniel Kang, Nikos Arechiga, Sudeep Pillai +2
ML is being deployed in complex, real-world scenarios where errors have impactful consequences. In these systems, thorough testing of the ML pipelines is critical. A key component…
Accelerating Understanding of Scientific Experiments with End to End Symbolic Regression
Nikos Arechiga, Francine Chen, Yan-Ying Chen +4
We consider the problem of learning free-form symbolic expressions from raw data, such as that produced by an experiment in any scientific domain. Accurate and interpretable models…
Certified Control: An Architecture for Verifiable Safety of Autonomous Vehicles
Daniel Jackson, Valerie Richmond, Mike Wang +6
Widespread adoption of autonomous cars will require greater confidence in their safety than is currently possible. Certified control is a new safety architecture whose goal is two-…
Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methods
Karen Leung, Nikos Aréchiga, Marco Pavone
This paper presents a technique, named STLCG, to compute the quantitative semantics of Signal Temporal Logic (STL) formulas using computation graphs. STLCG provides a platform whic…
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Kaidi Cao, Yining Chen, Junwei Lu +3
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imba…
Better AI through Logical Scaffolding
Nikos Arechiga, Jonathan DeCastro, Soonho Kong +1
We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtim…
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Kaidi Cao, Colin Wei, Adrien Gaidon +2
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classe…
Forward Invariant Cuts to Simplify Proofs of Safety
Nikos Arechiga, James Kapinski, Jyotirmoy Deshmukh +2
The use of deductive techniques, such as theorem provers, has several advantages in safety verification of hybrid sys- tems; however, state-of-the-art theorem provers require ex- t…