metadata
library_name: transformers
tags:
- rm
- latent
datasets:
- openai/gsm8k
base_model:
- openai-community/gpt2
pipeline_tag: token-classification
LatentRM
The Latent Reward Model (LatentRM) is a learned scorer designed for latent reasoning models that reason in continuous hidden space. LatentRM provides the missing aggregation signal for parallel test-time scaling in latent models, enabling techniques such as best-of-N and beam search without explicit token-level probabilities.
Citation
@misc{you2025paralleltesttimescalinglatent,
title={Parallel Test-Time Scaling for Latent Reasoning Models},
author={Runyang You and Yongqi Li and Meng Liu and Wenjie Wang and Liqiang Nie and Wenjie Li},
year={2025},
eprint={2510.07745},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2510.07745},
}