Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM

1 code implementation • 6 Oct 2023 • Changhun Lee, Chiehyeon Lim

We study the theoretical aspects of Reinforced Language Models (RLMs) from a bi-objective optimization perspective.

Layer-level activation mechanism

1 code implementation • 8 Jun 2023 • Kihyuk Yoon, Chiehyeon Lim

In this work, we propose a novel activation mechanism aimed at establishing layer-level activation (LayerAct) functions.

Image Classification