Papers with Code paper Sep 27

SMAT: Simple and Efficient Merge-Aware Training

Model merging integrates the capabilities of multiple experts without joint retraining, but standard expert training optimizes task loss alone and does not guarantee good performan...

Papers with Code paper Sep 27

Diffusion Reward Models

Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate or to a distribution from a fixed para...