3 papers
cs.LG2025
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Keyon Vafa, Peter G. Chang, Ashesh Rambachan +1
Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the…
stat.ML2024
Bayesian Online Natural Gradient (BONG)
Matt Jones, Peter Chang, Kevin Murphy
We propose a novel approach to sequential Bayesian inference based on variational Bayes (VB). The key insight is that, in the online setting, we do not need to add the KL term to r…
cs.AI2023
Privacy Issues in Large Language Models: A Survey
Seth Neel, Peter Chang
This is the first survey of the active area of AI research that focuses on privacy issues in Large Language Models (LLMs). Specifically, we focus on work that red-teams models to h…