Jake Snell

Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

Making Predictors More Reliable with Selective Recalibration