Publications
Our research has been published in the world's leading AI conferences and journals. We are committed to open science and make our code and datasets publicly available whenever possible.
Featured Publications
Self-Supervised Learning for 3D Object Detection in Autonomous Driving
We propose a novel self-supervised learning framework for 3D object detection that leverages temporal consistency and geometric constraints to learn robust representations from unlabeled LiDAR and camera data. Our method reduces annotation requirements by 80% while achieving state-of-the-art performance on multiple autonomous driving benchmarks.
Towards Fair and Robust AI in Medical Diagnosis
We present a comprehensive framework for developing fair and robust AI systems in medical diagnosis. Our approach combines adversarial debiasing with uncertainty quantification to ensure equitable performance across diverse patient populations. We validate our methods on multiple medical imaging tasks and demonstrate significant improvements in fairness metrics without sacrificing accuracy.
All Publications
2025
Hierarchical Reinforcement Learning for Complex Robotic Tasks
James Wilson, Sarah Johnson, Chris Lee
2024
On the Generalization Bounds of Neural Architecture Search
Michael Chen, Anna Lee, Robert Kim
Federated Learning with Differential Privacy for Healthcare Applications
Emily Rodriguez, Rachel Green, Michael Chen