Atkinson Hall, Fourth Floor

Events at this venue

Today

  • EnCORE Workshop

    EnCORE Series
    Atkinson Hall, Fourth Floor

    The goal of this EnCORE workshop is to bring together researchers working on different aspects of interpretability in modern AI systems to enable Trustworthy AI. We aim to discuss recent advancements, theoretical foundations, and emerging directions across topics such as automated interpretability methods, representation and concept-level analysis, next-generation interpretable model architectures, trustworthiness and limitations of explanations, and new tools for […]

  • Deep Learning: a Non-parametric Statistical Viewpoint

    Atkinson Hall, Fourth Floor

    ABSTRACT The advent of deep learning has completely revolutionized how we perceive data to obtain superhuman performance across all fields of modern science. However, despite the remarkable empirical successes of deep learners, the theoretical guarantees for their statistical accuracy remain rather pessimistic. In particular, the data distributions on which deep learners are generally applied, such […]

  • EnCORE : Theoretical Exploration of Foundation Model Adaptation, Kangwook Lee, UW Madison, Feb 9th, 1-2pm

    EnCORE Series
    Atkinson Hall, Fourth Floor

    Abstract: Due to the enormous size of foundation models, various new methods for efficient model adaptation have been developed. Parameter-efficient fine-tuning (PEFT) is an adaptation method that updates only a tiny fraction of the model parameters, leaving the remainder unchanged. In-context Learning (ICL) is a test-time adaptation method, which repurposes foundation models by providing them with labeled samples as part of the input context. Given the growing importance of this emerging paradigm, developing theoretical foundations for the new paradigm is of utmost importance.