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. […]
MEAM / IDEAS Seminar: “Generative Constitutive Laws as Graphs and Trees”
Capturing path- and rate-dependent behaviors of solids, such as creeping, plastic deformation, damage, and fracture, often requires interpreting and quantifying relationships among the histories of variables, such as dislocation density […]
ASSET Seminar: “When do spectral gradient updates help in deep learning?”
Spectral gradient methods, such as the recently popularized Muon algorithm, are a promising alternative to standard Euclidean gradient descent for training deep neural networks and transformers, but it is still […]
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 […]
ASSET Seminar: “Better Algorithms for Better Neighbors”
Nearest neighbor search has a long history in theoretical computer science, and in the past decade has seen an explosion of usage. This has been primarily driven by embedding models […]
ASSET Seminar: “Formal Methods for Language Model Systems”
Formal methods are often dismissed as too rigid, complex, or unscalable for frontier language model systems (e.g., LLMs, VLMs, agentic systems). In this talk, I will challenge this assumption with […]
ASSET Seminar: “How can we enable LLM auditing?”
Oversight and auditing of AI systems is becoming increasingly difficult as people use systems in a wide variety of ways, with instructions expressed in natural language prompts. We can no […]
ASSET Seminar: “Towards discrete diffusion models for language and image generation”
We discuss discrete diffusion models that offer a unified framework for jointly modeling categorical data such as text and images. We present a new model that we have developed for […]
ASSET Seminar: “Beyond Photorealism: 3D Reconstruction and Generation with Multimodal and Physical Grounding”
Progress in 3D reconstruction and generation has accelerated rapidly, producing increasingly detailed geometry and photorealistic rendering. However, moving beyond photorealism requires models that not only look correct, but are also […]