Amy Gutmann Hall, Room 414

Address
3333 Chestnut Street
Philadelphia, 19104 United States Get Directions

Events at this venue

Today

    • Penn AI Seminar featuring Mayur Naik (University of Pennsylvania)

    Penn AI Seminars /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States
    Hybrid Event

    MathDuels: A Self-Play Benchmark That Grows As frontier language models attain near-ceiling performance on static mathematical benchmarks, existing evaluations are increasingly unable to differentiate model capabilities, largely because they cast models solely as solvers of fixed problem sets. I will present MathDuels, a self-play benchmark in which models occupy dual roles: each authors math problems […]

    ASSET Seminar: “Integrated Learning and Planning with Neuro-Symbolic Concepts”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States
    Virtual Event

    Jiayuan Mao aims to build intelligent agents that continually learn, reason, and plan: agents that can answer queries, infer human intentions, and pursue long-horizon goals spanning hours to days. In this talk, she will describe a general framework for learning and reasoning with neuro-symbolic concepts. Drawing inspirations from theories and studies in cognitive science, neuro-symbolic […]

    FOLDS seminar: Dynamics of large-step gradient descent near flat minima

    FOLDS seminar: /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

    Zoom link: https://upenn.zoom.us/j/98220304722 Classically, convergence guarantees for gradient descent (GD) require that the step size be sufficiently small compared to the local curvature ("sharpness") of the objective. This "small-step" condition is routinely violated in the practical training of deep learning models, wherein the favoured  "large-step" GD is  observed to converge with intriguing oscillatory dynamics and an […]

    Fall 2026 GRASP/CIS Seminar: Jean Gallier, University of Pennsylvania, “The Math Behind Equivariant CNNs: Group Representations”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

    This event will be held in-person in AGH 414 and virtually via Zoom. ABSTRACT Convolutional neural networks (CNNs) are tools used in computer vision for template matching in an image. An image f can be viewed as a function from a domain, typically a grid, to the set of reals, where f(t) is the color […]

    ASSET Seminar: “Trust Substrates for AI-Driven Mathematics”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States
    Virtual Event

    The recent autonomous solution to the Navier-Stokes millennium problem was an extraordinary breakthrough. Yet, equally remarkable is how the global community accepted this solution without traditional, years-long peer review. This speed was possible because the proof included an autoformalized Lean certificate, allowing it to be mechanically verified. Lean was the foundational trust substrate beneath the […]

    Schlein Center for Cybersecurity Seminar: “Limber: Low overhead SNARKs for Integers from Any PCS”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

    Abstract: In real-world applications of SNARKs, non-native arithmetic is a key bottleneck. It introduces large overheads, and proof system designers often resort to non-standard SNARK-friendly hash-functions or other means like elliptic curve cycles to mitigate its costs. Besides performance concerns, non-native circuit arithmetization is also a major cause of implementation errors. In a collection of […]

    CIS Colloquium Series: “From Potential to Promise: Developing Scholars, one Eureka moment at a time”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

    Abstract: In this talk, I will share the story of our work with some truly remarkable students, who -- despite many odds -- have achieved extraordinary success. These students come from diverse backgrounds -- some have been first-generation college students, some belong to underrepresented minority groups, and many faced significant financial challenges. Many of these […]

    ASSET Seminar: “Safe, Robust, and Generalizable Machine Learning for Power Systems”

    /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States
    Virtual Event

    Power grids must be managed at greater speed, scale, and physical fidelity to enable decarbonization and improve resilience. Methods from machine learning (ML) have the potential to play an important role by providing fast, scalable approximations for foundational power system optimization problems, but often struggle to enforce hard physical constraints, maintain robustness in the face […]

    FOLDS seminar:

    FOLDS seminar: /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

    Zoom link: https://upenn.zoom.us/j/98220304722  

    • Penn AI Seminar featuring Kayhan Batmanghelich (Boston University)

    Penn AI Seminars /
    Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States
    Hybrid Event

    Generalist vs. Specialist: A Case for Specialist Foundation Models in Medical Imaging How should domain knowledge shape the architecture, training objectives, and evaluation of foundation models for medical imaging? In this talk, I will make the case for specialist foundation models that support multiple tasks within a clinical domain by incorporating its imaging characteristics, clinical […]