1 code implementation • 25 Apr 2024 • Nico Schiavone, Xingyu Li
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.
1 code implementation • 24 Oct 2023 • Nico Schiavone, Jingyi Wang, Shuangzhi Li, Roger Zemp, Xingyu Li
To this end, we introduce an active few shot learning framework, Myriad Active Learning (MAL), including a contrastive-learning encoder, pseudo-label generation, and novel query sample selection in the loop.