Prompting a Pretrained Transformer Can Be a Universal Approximator

Aleksandar Petrov; Philip Torr; Adel Bibi

2024 ICML ICML 2024

Prompting a Pretrained Transformer Can Be a Universal Approximator

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Aleksandar Petrov, Philip Torr, Adel Bibi

Topics

Artificial Intelligence > Core AI > Foundation Models Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Architectures > Transformers

Keywords

transformer attention head universal approximator prefix tuning continuous function prompting

Download PDF