Reinforcement Learning with Generative Models for Compact Support Sets

arXiv:2404.16300v1 Announce Type: new
Abstract: Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a framework utilizing reinforcement learning as a control for foundation models, allowing for the granular generation of small, focused synthetic support sets to augment the performance of neural network models on real data classification tasks. We first …

abstract arts arxiv compact control cs.cv cs.lg extract foundation framework generative generative models however information prior reinforcement reinforcement learning sample samples small support training type vast wealth work