{"ID":2861780,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00395","arxiv_id":"2510.00395","title":"SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing","abstract":"Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We propose Attribute-Specialized Key-Value Head Sharing (AS-KVHS), adapted to music's structured symbolic representation, achieving about 30% inference speedup with only a negligible (about 0.4%) quality drop in objective evaluations and slight improvements in subjective listening tests. Our main contributions are (1) the first systematic study of BPE's generalizability in multi-track symbolic music, and (2) the introduction of AS-KVHS for low-latency symbolic music generation. Beyond these, we also release SAGE-Music, an open-source benchmark that matches or surpasses state-of-the-art models in generation quality.","short_abstract":"Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently p...","url_abs":"https://arxiv.org/abs/2510.00395","url_pdf":"https://arxiv.org/pdf/2510.00395v2","authors":"[\"Jiaye Tan\",\"Haonan Luo\",\"Linfeng Song\",\"Shuaiqi Chen\",\"Yishan Lyu\",\"Zian Zhong\",\"Roujia Wang\",\"Daniel Jiang\",\"Haoran Zhang\",\"Jiaming Bai\",\"Haoran Cheng\",\"Q. Vera Liao\",\"Hao-Wen Dong\"]","published":"2025-10-01T01:11:43Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"cs.LG\",\"eess.AS\"]","methods":"[\"Transformer\"]","has_code":false}