Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Hanwen, Dong, Yuxin, Ning, Xia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!