AI RESEARCH
GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
arXiv CS.AI
•
ArXi:2605.00371v1 Announce Type: cross In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive.