Dissertation Defenses

Robust Scene Estimation for Goal-directed Robotic Manipulation in Unstructured Environments

Clarifying Oblique Specifications of Relational Queries

Improving Programming Support for Hardware Accelerators Through Automata Processing Abstractions

Democratizing Self-Service Data Preparation through Program Synthesis for Non-expert Users

Agent-based Models for Analyzing Strategic Adaptations to Government Regulation

Thwarting Advanced Code-reuse Attacks

Using Sensor Redundancy in Vehicles and Smartphones for Driving Security and Safety

Towards Seamless Human-Mobility Interaction

Runtime Systems for Persistent Memories

Enabling Usable and Performant Trusted Execution

Thermal and QoS-Aware Embedded Systems

Estimation of Information Measures and Applications in Machine Learning

Multimodal Character Representation for Visual Story Understanding

Learning Hierarchical Compositional Task Definitions through Online Situated Interactive Language Instruction

Demographic-Aware Natural Language Processing

Efficient Deep Neural Network Computation on Processors

Addressing Variability in Speech when Recognizing Emotion and Mood In-the-Wild

Designing and Evaluating Physical Adversarial Attacks and Defenses for Machine Learning Algorithms

Energy Efficient Algorithms in Low-Energy Wireless Sensor Networks

Rethinking Context Management of Data Parallel Processors in an Era of Irregular Computing

Towards a More Predictable Database System

Building and Querying Structured Knowledge Sources from Natural Language Text

Its Data All the Way Down: Exploring the Relationship Between Machine Learning and Data Management

Reducing Redundant Computation and Data in Non-deterministic Systems by Exploiting the Computation-data Duality

Requirements Testing and Verification for Smart Systems through Systematic Software Analysis