Presenter: Dr. Danielle Robinson, AWS AI Description: In this talk, I will discuss the large impact of foundation models within the sciences with a particular focus on the importance of physical constraints and uncertainty quantification. First, I will detail our novel ProbConserv framework for enforcing hard constraints within black-box deep learning models. ProbConserv provides uncertainty […]
Not sure if graduate school is right for you? Join us to learn what graduate school is really about and explore whether it’s the right path for you. We’ll cover topics such as qualifying exams, funding options, common misconceptions, and more! Click the link below to register for the event: https://ucsc.zoom.us/webinar/register/WN_31OHhwc7QPqJ7nSyiuAUNg
Macroeconomics and International Finance Seminar: Dean Corbae
Applied Microeconomics and Trade Seminar: Olivia Bordeu
Economics Behavioral, Econometrics and Theory Seminar: Roberto Corrao
Presenter: Loris D’Antoni, UC San Diego Abstract: Language models excel at producing fluent text, but in domains like code and math, fluency isn’t enough — outputs must obey strict syntactic and semantic rules. A new wave of research is rethinking decoding itself: not as a process of sampling words, but as a negotiation between probability, structure, and […]
Applied Microeconomics and Trade Seminar: Guo Xu
Presenter: Grad Students Description: Rotation Talks Bio: N/A Hosted by: Professor Rebecca DuBois, BME Department
Presenter: Subhadeep Paul, Associate Professor, Ohio State University Description: In the first part of the talk, we consider the problem of Transfer Learning (TL) under heterogeneity from a source to a new target domain for high-dimensional regression with differing feature sets. Most homogeneous TL methods assume that target and source domains share the same feature […]
Presenter: Dr. Hannah Stuart, Associate Professor in the Department of Mechanical Engineering, University of California at Berkeley Description: Robot grippers typically include mechanical intelligence (e.g., underactuation, compliance) or computational intelligence (e.g., fully actuated with a wide array of sensors). Next generation grippers and hands will require both intelligences to work in concert across applications with […]
Presenter: Guannan Wang, Associate Professor, The College of William & Mary Description: Generative AI has emerged as a powerful tool for synthesizing biomedical images, offering new solutions to challenges such as data scarcity, privacy constraints, and modality imbalance. However, the reliable use of synthetic images in scientific analysis requires principled statistical frameworks that can assess […]
Presented by: Kai Lukoff Description: The Santa Clara University campus is adorned with symbols and monuments, including a Spanish Mission Church, that highlight its Catholic heritage. However, the presence and history of the Ohlone Native Americans, who have inhabited this land for thousands of years and continue to live in the region, receive little to […]
Presenter: Fabrizio Falasca, New York University Description: A central challenge in climate science and applied mathematics is developing data-driven models of multiscale systems that capture both stationary statistics and responses to external perturbations. Current neural climate emulators aim to resolve the atmosphere–ocean system in all its complexity but often struggle to reproduce forced responses, limiting […]
Presenter: Charilaos I. Kanatsoulis, Stanford University Abstract: Foundation models have transformed unstructured domains such as language and vision, yet relational datasets, where most enterprise knowledge lives, still rely on brittle, task-specific ML pipelines. I will begin by introducing Relational Deep Learning (RDL), a general framework for learning directly from heterogeneous multi-table data, capturing structure across entities, attributes, […]
Presenter: Yunyi Shen, Ph.D. Candidate, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology Description: Practitioners often aim to infer an unobserved population trajectory using sample snapshots at multiple time points. E.g. given single-cell sequencing data, scientists would like to learn how gene expression changes over a cell’s life cycle. But sequencing any […]
Presenter: Matt Franklin, Postdoctoral Researcher, Stanford University Description: Eukaryotic genomes contain large stretches of repetitive DNA called satellite DNA, often found near centromeres and ribosomal DNA regions. In humans, alpha satellite has well-established roles in centromere biology, however the functions of other human satellite DNAs remain largely unexplored. We recently identified the Hippo pathway effector […]
You are cordially invited to an event celebrating the life and research legacy of Allen van Gelder, who passed away in April 2025 after 37 years of dedicated service to the Computer Science and Engineering Department at UC Santa Cruz. Thursday, January 29, 2025 Reception begins 1pm, Program begins 1:30pm Alumni Room, University Center, UC […]
Presenter: Tolga Acikalin, System and Package Architect, Lumilens Description: The rapid rise of artificial intelligence and machine learning—most notably recent breakthroughs in large language models—is reshaping the trajectory of the semiconductor industry and ushering in a new era of system innovation. As performance scaling at the device level slows, heterogeneous integration (HI) has emerged as […]
Presenter: Jiaqi Li, William H. Kruskal Instructor, University of Chicago Description:Modern machine learning (ML) algorithms achieve remarkable empirical success, yet providing rigorous statistical guarantees remains a major challenge, particularly in distributional theory and online inference methods. In this talk, we will introduce a novel framework to provide mathematical foundations for ML by bringing powerful tools […]
Presenter: Seshadhri Comandur, Professor of Computer Science, UCSC Description: There has been a lot of literature on graph machine learning over the past few years, and a bewildering array of new methods. This talk is based on a series of results making a provocative argument. Maybe many graph machine learning methods are not really that […]