Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kunde, Vishnu Teja, Doudi, Fatemeh, Farahbakhsh, Mahdi, Kalathil, Dileep, Narayanan, Krishna, Chamberland, Jean-Francois
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.12554