Ph.D. Presentations

Events

Events Search and Views Navigation

Event Views Navigation

Filters

Changing any of the form inputs will cause the list of events to refresh with the filtered results.

Today

  • Three silhouetted figures talking, overlaid with graphics of digital data, charts, and technology interfaces.

    Scott, J. (CSE) – Mechanistic Specialization Does Not Guarantee Performance: Evidence from Dual AttentionTransformers

    Virtual Event

    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 […]

  • Close-up abstract image of a circuit board with glowing lines and interconnected pathways.

    Kembay, A. (ECE) – Sparse and Continual Foundations for Adaptive General Intelligence

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    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 […]

  • Three silhouetted figures talking, overlaid with graphics of digital data, charts, and technology interfaces.

    Calicchio, A. (BMEB) – Comparison of long-read sequencing and analysis methods for transcriptome analysis

    Biomedical Sciences Building 575 McLaughlin Drive
    Hybrid Event

    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 […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Holmes, J. (CM) – Towards a Multi-dimensional Model of User Load

    Virtual Event

    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 available tools to measure user load are coarse, one-dimensional, and often aggregated. The more dominant instruments, such as the Cognitive Load Scale (CLS) and the […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Chen, X. (STAT) – Changepoint Detection and Clustering Methods for Multivariate Time Series and Attributed Networks

    Virtual Event

    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 silhouetted figures talking, overlaid with graphics of digital data, charts, and technology interfaces.

    Li, J. (CM) – Detecting Failure to Adapt: Reading Self-Regulated Learning Breakdowns from Game Telemetry through Plan Recognition

    Virtual Event

    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 […]

  • Close-up abstract image of a circuit board with glowing lines and interconnected pathways.

    Gholami, K. (ECE) – Efficient Language Model Construction and Inference via Sparsity

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    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 […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Fontana, J. (STAT) – When We’re Always Wrong: Scalable Variable Selection in M-Open Settings

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    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 of observations have become increasingly common, new theoretical and computational challenges for model selection have emerged. We consider the variable selection problem for linear models […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Zhao, Z. (CSE) – TOWARD VERIFIABLE REASONING IN LLMS

    Silicon Valley Campus 3175 Bowers Avenue, Santa Clara, CA, United States
    Hybrid Event

    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 reasoning more reliable by translating CoT rationales into Lean artifacts, checking the resulting theorem statements and proofs, and using compiler feedback to diagnose and repair […]

  • Three silhouetted figures talking, overlaid with graphics of digital data, charts, and technology interfaces.

    Krishnaswamy, L. (CSE) – Network Load Balancing for Geographically Distributed Datacenters

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    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 […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Condon, C. (BMEB) – Genomic conflict across scales

    Biomedical Sciences Building 575 McLaughlin Drive

    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 […]

  • Three silhouetted figures talking, overlaid with graphics of digital data, charts, and technology interfaces.

    Lupin-Jimenez, L. (AM) – Data-Driven Deep Learning for Turbulent Phenomena: Regional Ocean Prediction and Assimilation, Spectral Bias in Diffusion Models, and Equation Discovery

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    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 […]

  • Abstract digital illustration featuring gears and interconnected technology elements.

    Nava, A. (AM) – Machine-Learning Methods for Prediction of Biological Systems

    Engineering 2 Engineering 2 1156 High Street, Santa Cruz, CA
    Hybrid Event

    Advances in microscopy have enabled the collection of high-quality single-cell datasets, providing new opportunities to identify the mechanisms underlying complex biological processes. In this work, we develop machine-learning frameworks using single-cell temporal data with the goal of predicting and providing insights into these mechanisms. We produce frameworks for two biological systems, bacterial spore germination, the […]

  • Close-up abstract image of a circuit board with glowing lines and interconnected pathways.

    Huang, X. (CSE) – Scalable and Verifiable Reasoning for Medical Foundation Models

    Virtual Event

    This PhD research focuses on developing reliable medical foundation models capable of reasoning across textual, visual, and interactive clinical information. The work investigates three complementary directions: improving medical reasoning through test-time scaling, training multimodal medical models with verifiable rewards, and synthesizing high-quality visual question-answering data from biomedical literature using generator-verifier frameworks. Building on these efforts, […]

  • Close-up abstract image of a circuit board with glowing lines and interconnected pathways.

    Pawar, M. (CSE) – Understanding Representations, Reasoning, and Decision-Making in Autonomous Driving Models

    Virtual Event

    Modern autonomous-driving models increasingly rely on learned representations and generated reasoning to interpret complex scenes and produce predictions or actions. However, it remains unclear what information these models encode, how that information is exposed through common interpretation methods, and whether their stated reasoning meaningfully influences their behavior. This research investigates these questions across motion-forecasting and […]