Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module
机构 * The University of Hong Kong, Fauclty of Science, Hong Kong(香港大学科学学院) ; Aix-Marseille University, Laboratoire Parole et Langage (LPL), France(艾克斯-马赛大学语言与言语实验室(LPL))
专题命中 其他推理 :reasoning(abstract)
Comments 5 pages, 1 figures. Code is available at: https://github.com/forfrt/SteerMoE. Submitted to ICASSP 2026