Learning When to Think While Listening in Large Audio-Language Models 文章

ArXiv CS.CL2026-05-27NEWSen作者: Zhiyuan Song, Weici Zhao, Yang Xiao, Suhao Yu, Cheng Zhu, Jiatao Gu
大语言模型
查看原文 →
关系图谱

Learning When to Think While Listening in Large Audio-Language Models · 相关技术

相关技术

ORMODElanguage modelrsadivide-and-conquer partitioningUCTTeraStraight-Through EstimatorSupervised Fine-TuningSFTReferring expression comprehension (REC)Narrative Abstraction BenchmarkNATMITHISForDPOCLICISAudio-language modelsARGANN