Modern software increasingly relies on distributed systems to provide accessible, scalable, and reliable services. Choreographic programming brings a global perspective to distributed system development: programmers write a single program that describes the behavior of a whole system, and a compiler projects that global description into local programs run by each node. By making distributed control […]
Edge computing and distributed AI systems increasingly operate under heterogeneous resources, dynamic workloads, and frequent failures, requiring both adaptivity and fault tolerance for efficient execution. In heterogeneous edge clusters, nodes differ significantly in CPU throughput, memory capacity, and network bandwidth, while modern distributed GPU clusters supporting agentic LLM inference must recover large amounts of runtime […]
Real-time monitoring of infectious disease outbreaks calls for statistical models that recover interpretable quantities such as the time-varying reproduction number from noisy count data, track posterior uncertainty, and run on […]
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 […]
Modern AI systems are rapidly moving beyond static text generation toward capable models and agents that reason, use tools, store memories, and update persistent state, yet safety methods still often assume a fixed model whose behavior can be controlled by output-level refusal. This leaves critical gaps in understanding why aligned models fail under adversarial pressure, […]
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 […]
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 expression produce the functional differences that give rise to different cell types and, in some cases, result in disease. Long-read RNA sequencing has transformed our […]
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 several related problems in statistical inference for multivariate and network-indexed time series. First, we develop a weighted multivariate $U$-statistic procedure for detecting a single changepoint […]
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 do next. Yet the measures a game’s logs are usually reduced to (completion time, error counts, mastery estimates) render the three identical. This proposal takes […]
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 brain-inspired computational principle to address both. We first establish a framework for evaluating small language model construction methods, using the next-token logit distribution 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 coexistence and interaction between inter- and intra-datacenter traffic are the differences in their QoS requirements, link utilization, and round-trip times. To the best of […]
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 disruptions, and limited access to energy resources introduce challenges that conventional power system planning and operation frameworks were not designed to address. Wildfires provide a […]