Due to their increasing complexity, autonomous decision-making agents rely on increasingly advanced algorithms, from classical control theory to reinforcement learning (RL) and, more recently, large vision-language models. While these algorithms […]
AI-assisted clinical decisions in medicine, and particularly in dermatology, demand fine-grained understanding across diverse skin tones, body sites, and disease types, yet expert-annotated datasets are scarce, demographically imbalanced, and almost devoid of rare presentations. This dissertation develops four deep learning systems for this low-label, low-coverage regime. We introduce HealNet, which learns wound healing stages from […]
Graphics Processing Units (GPUs) have become essential platforms for parallel computing, supporting applications far beyond graphics. Central to GPU programming models is its memory consistency specification (MCS), which defines the semantics of concurrent shared-memory operations and interacts with other language features to determine security guarantees such as memory safety. Understanding whether implementations conform to an […]
Dual Attention Transformers (DATs) extend decoder-only Transformers with a dedicated relational-attention stream, making them a natural architecture for abstract identity rules such asABA and ABB. Surprisingly, we find that comparably sized GPT-2 models outperform DATs on these tasks. We investigate this gap with two complementary mechanistic analyses. First, causal mediation analysis shows that DATs exhibit […]
While the human brain learns continually, mastering new tasks without forgetting the old and adapting to unfamiliar ones from context alone, modern neural networks still lack both. To bridge the gap between biological adaptivity and modern AI, we have established foundational work on sparsity as a computational principle at three levels of neural computation, through […]
Alternative splicing, the process generating different RNA isoforms from a single gene, is considered one of the main factors driving increased organism complexity in eukaryotes. Variations in isoform and gene […]
Games user researchers (GURs) use various methods to understand when a game is overloading its players. In games research where data-driven multimodal approaches are necessary to drive insights, the currently […]
Time series data with dependence arise across a wide range of scientific and engineering disciplines, often presenting challenging inferential problems related to structural change and clustering. This Ph.D. proposal addresses […]
Three learners who fail the same level of an educational game the same number of times can be failing in three different ways, and the difference determines what each should […]
While large language models can match or exceed human performance, they do so with memory and energy costs orders of magnitude greater than biological cognition. We investigate sparsity as a […]
A ubiquitous task in statistical practice is that of variable selection, identifying which of a large set of features are the relevant ones. As data sets with a large number […]
Many scientific applications produce repeated point pattern realizations across subjects, regions, or time. While such point patterns exhibit individual variation, we assume they arise from related point processes that share […]
Chain-of-thought (CoT) prompting can improve final-answer performance, but it does not guarantee that intermediate reasoning steps are faithful, valid, or checkable. This proposal studies how formal methods can make natural-language […]
As datacenters scale up and become more geographically distributed, wide-area network inter-datacenter traffic, which typically consists of data-heavy tasks, has become increasingly prevalent. Some of the noteworthy challenges raised by […]
The rapid electrification of transportation is creating new interdependencies between power and transportation systems, particularly during extreme events and disasters. As electric vehicle (EV) adoption increases, evacuation-related charging demand, infrastructure […]
Medical image representation has long been dominated by voxel-grid matrices. While their inherent structure and order work efficiently for various linear transformations and provide a seamless visualization method on monitors, […]
Genomes are often viewed as cooperative systems in which genes work together to support organismal function. Yet genetic elements can also act in ways that favor their own transmission or persistence, creating conflict within the genome. In this talk, I examine the evolutionary and functional consequences of such genomic conflict across three systems. First, I […]
This thesis explores iterative methods for solving elliptic partial differential equations (PDEs), which are used in computational fluid dynamics (CFD) to model a wide range of physical phenomena. The primary application of interest here is self-gravity, modeled by Poisson’s equation. Although many numerical approaches exist, including direct matrix inversion, FFT-based methods, and classical iterative methods […]
Deep learning models trained on simulation and reanalysis data can now emulate turbulent geophysical flows at a small fraction of the computational cost of numerical solvers. Their scientific utility depends on physical consistency, which for the systems studied here rests in large part on spectral fidelity, the accurate reconstruction of variance across spatial scales. This […]
Host-microbe systems are core to some of biology’s most consequential interactions, from the pathogens that drive infectious disease to symbionts affecting agricultural pest control and vector-borne disease transmission. Yet unlike the model organisms that have driven most of modern molecular biology, the microbes at the center of these interactions are rarely genetically tractable: many cannot […]