Abstract: In general, an M-objective continuous optimization problem has an (M - 1)-dimensional Pareto front in the objective space. If its dimension is smaller than (M - 1), it is called a degenerate ...

This repository implements Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF). Instead of training the target model with a single preference model representing "all human preferences", ...

This project replicates the content of Chapter 11 on Transformers in Dive into Deep Learning. It builds an English-French machine translation model using C++. The project develops its own automatic ...