11

Jan

Teaser image to Linear Structure of High-Level Concepts in Text-Controlled Generative Models

AI Keynote Series

Linear Structure of High-Level Concepts in Text-Controlled Generative Models

Victor Veitch, University of Chicago

   11.01.2024

   5:15 pm - 6:45 pm

   LMU Institute of AI in Management via zoom

Text controlled generative models (such as large language models or text-to-image diffusion models) operate by embedding natural language into a vector representation, then using this representation to sample from the model’s output space. This talk concerns how high-level semantics are encoded in the algebraic structure of representations.


Related

Link to Simplifying Debiased Inference via Automatic Differentiation and Probabilistic Programming

AI Keynote Series  •  13.02.2025  •  Online via Zoom

Simplifying Debiased Inference via Automatic Differentiation and Probabilistic Programming

13.02.25, 10-11:30 am: AI Keynote Series with Alex Luedtke from the University of Washington.


Link to A Novel Statistical Approach
to Analyze Image Classification

Colloquium  •  29.01.2025  •  LMU Department of Statistics and via zoom

A Novel Statistical Approach To Analyze Image Classification

29.01.25, 4-6 pm: LMU Statistics Colloquium with Sophie Langer (University of Twente).


Link to Additive Density-on-Scalar Regression in Bayes Hilbert Spaces with an Application to Gender Economics

Colloquium  •  15.01.2025  •  LMU Department of Statistics and via zoom

Additive Density-on-Scalar Regression in Bayes Hilbert Spaces With an Application to Gender Economics

15.01.25, 4-6 pm: LMU Statistics Colloquium with Sonja Greven (HU Berlin) introducing a novel approach to modeling densities.