Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
- 2026-01-24
- 0
@misc{shan2026latentspace,
title = {Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning},
author = {Li Shan and Han Chen and Yixuan Wang and Zhenjie Liu and Wei Li},
year = {2026},
eprint = {2601.17275},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2601.17275},
}