Faculty Candidate Seminars

Learning to Generate Data by Estimating Gradients of the Data Distribution

Towards Scalable Representation Learning for Visual Recognition

Advancing Quantum Science with Ytterbium Atom Arrays

Emerging Optics from Structured Nanomaterials

AI-powered Computational Imaging and Processing for Advancing Visualization and Perception in Biomedical Applications

Theoretical Foundations of Pre-trained Models

Learning to See the 3D world

Steps towards making machine learning more natural

Physics-Based Visual Computing for Efficient 3D Vision and Sensing

Artificial Intelligence for Geometry Processing

Fair and Reliable Machine Learning for High-Stakes Applications: Approaches Using Information Theory

Developing and Deploying Gallium Nitride Magnetometers for Harsh Environments

Leveraging Dataset Structure for Neural Network Prediction

Reliable Machine Learning in Feedback Systems

Understanding Human-Centric Sides of Deep AI Models

Cross-Layering in Future Wireless Networks: From Compact Full-duplex Radios to City-Scale Experimentation

Small-Data Learning in Big Cyber Physical Systems

Large-Scale Optimization and Nonconvexity: From Deep Learning to Energy Markets

Learning from Societal Data: Theory and Practice

Canceled: Scalability and Methods of Deep Learning from an Optimization Viewpoint

Towards Scalable Algorithms for Distributed Optimization and Learning

Learning Low-complexity Models from the Data – Geometry, Optimization, and Applications

Sight and Sound

Information Theoretic Limits in Learning: Applications to Privacy and Security

Delay, memory, and messaging tradeoffs in distributed service systems