Concept

Fusion Networks for Combining Reward Models

A fusion network is a specialized neural network designed to learn the optimal way to combine predictions from multiple different models. This network takes the outputs from an ensemble of reward models as its input and is trained to produce a single, more accurate combined prediction.

0

1

Updated 2026-05-03

Contributors are:

Who are from:

Tags

Ch.4 Alignment - Foundations of Large Language Models

Foundations of Large Language Models

Computing Sciences

Foundations of Large Language Models Course