Saved in:
Bibliographic Details
Main Authors: You, Zuyao, Yu, Zhesong, Liu, Mingyu, Zhu, Bilei, Wan, Yuan, Wu, Zuxuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.00371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917452639633408
author You, Zuyao
Yu, Zhesong
Liu, Mingyu
Zhu, Bilei
Wan, Yuan
Wu, Zuxuan
author_facet You, Zuyao
Yu, Zhesong
Liu, Mingyu
Zhu, Bilei
Wan, Yuan
Wu, Zuxuan
contents 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 training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00371
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
You, Zuyao
Yu, Zhesong
Liu, Mingyu
Zhu, Bilei
Wan, Yuan
Wu, Zuxuan
Sound
Artificial Intelligence
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 training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.
title GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2605.00371