X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Di, Fu, Dongjie, Yu, Hai, Zheng, Siqi, Tan, Xu, Jin, Tao
Format:	Preprint
Published:	2026
Subjects:	Audio and Speech Processing 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/2603.24596