Author

Peixu Hou

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Mar 2026

Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models

This work introduces Fast-Slow Thinking Reward Models (F/S-RM), a hybrid RM architecture inspired by Dual Process Theory that achieves state-of-the-art accuracy with an average score of 84.3 across benchmarks, while reducing token consumption by 22.5%.

Jiayun Wu, Peixu Hou, Sha Qu et al. · arXiv.org · 1 citation