Archive |

FOLDS seminar: TBA

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

FOLDS seminar: TBA

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

FOLDS seminar: TBA

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

FOLDS seminar: TBA

Please note important updates on date an location to this seminar: The session will not take place on its usual Thursday, but has been rescheduled to Monday, March 23, at noon. The new […]

FOLDS seminar: Coherence Mechanisms for Provable Self-Improvement

Zoom link: https://upenn.zoom.us/j/98220304722 Large language models are increasingly trained to improve themselves, yet the mechanisms driving this, such as self-reflection or RLAIF, rely almost entirely on empirical heuristics. Is it possible […]

FOLDS seminar & PENN AI seminar: Optimization Challenges in Physics-Informed Neural Networks

Zoom link: https://upenn.zoom.us/j/98220304722   Physics-informed neural networks (PINNs) minimize composite losses that penalize PDE residuals alongside boundary and initial conditions. While this resembles multi-task learning, the optimization landscape is fundamentally different. […]

FOLDS seminar: Multi-step reasoning via curriculum learning

Zoom link: https://upenn.zoom.us/j/98220304722   Can multi-step reasoning be learned from data? We investigate this question in the context of a simple function composition task. We prove that this task is […]

FOLDS seminar: Fast Convergence of High-Order ODE Solvers for Diffusion Models

Zoom link: https://upenn.zoom.us/j/98220304722   Score-based diffusion models can be sampled efficiently by reformulating the reverse dynamics as a deterministic probability flow ODE and integrating it with high-order solvers. Since the […]

FOLDS seminar: Transformers Meet In-Context Learning: A Universal Approximation Theory

Zoom link: https://upenn.zoom.us/j/98220304722   Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. […]

FOLDS seminar: Provably Efficient Learning in Nonlinear Dynamical Systems via Spectral Transformers

Zoom link: https://upenn.zoom.us/j/98220304722   Learning in dynamical systems is a fundamental challenge underlying modern sequence modeling. Despite extensive study, efficient algorithms with formal guarantees for general nonlinear systems have remained elusive. This […]

1 2 3
Archive |