All Reports
Total Links
Assets · eval
Assets · test
GitHub
arXiv
arXiv
Qwen-Music Technical Report (Qwen Team, 2026) — *NEW THIS WEEK (v2)*
https://arxiv.org/abs/2607.11699
arXiv
MulTTiPop — Multitrack Transcription Dataset for Pop Music (Pruyne et al., 2026) — *NEW THIS WEEK*
https://arxiv.org/abs/2607.08756
arXiv
MuseAgent-1 — Interactive Grounded Multimodal Understanding of Music Scores + Performance Audio
https://arxiv.org/abs/2601.11968
arXiv
VocalParse — Singing-Voice Transcription with a Large Audio Language Model
https://arxiv.org/abs/2605.04613
arXiv
HeartMuLa v3 — Open-Source Music Foundation Model Family (Yang et al., 2026) — *v3 dropped 7 Jul 2026*
https://arxiv.org/abs/2601.10547
arXiv
Advancing Multi-Instrument Music Transcription — 2025 AMT Challenge Results
https://arxiv.org/abs/2603.27528
arXiv
"Evaluating Multimodal Large Language Models on Core Music Perception Tasks" (Carone, Roman, Ripollés, 2025) — *NEW THIS WEEK*
https://arxiv.org/abs/2510.22455