arXiv AI October 31, 2026 By Di Zhu, Zihan Chen, Zixuan Li

MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation

MuQ-Eval is an open‑source per‑sample quality metric for AI‑generated music that uses frozen MuQ‑310M features and a lightweight prediction head trained on the MusicEval dataset. The simplest model—attention‑pooled frozen features plus a two‑layer MLP—achieves high correlation with human judgments (system‑level SRCC = 0.957, utterance‑level SRCC = 0.838). The metric is real‑time on a single consumer GPU, outperforms existing open per‑sample metrics, and supports personalized evaluators via LoRA adaptation on as few as 150 clips.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 12

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.

By Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos

reinforcement-learning multimodal benchmarks safety

arXiv AI

Sep 2

TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data

TUTTI is a new pre‑training framework for audio‑to‑score transcription that uses a large, fully synthetic multi‑instrument dataset generated by a symbolic music model. The approach trains a standard Transformer encoder‑decoder on these synthetic audio‑score pairs, producing a stronger foundational representation than single‑instrument training. When fine‑tuned on real datasets, TUTTI surpasses prior methods, achieving state‑of‑the‑art results and demonstrating strong cross‑instrument transferability.

By Jianhuai Hu, Yashan Wang, Shangda Wu, Zhancheng Guo, Shijie Liang, Wuna Meng, Chuanqi Yang, Xiaobing Li, Feng Yu, Maosong Sun

llms fine-tuning benchmarks

arXiv AI

Aug 7

Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset

arXiv:2608. 06165v1 Announce Type: cross Abstract: Existing audio-to-score (A2S) systems primarily focus on classical music, and the application to popular music remains underexplored.

By Eoin Cummins, Zhongyi Huang, Alexandre D'Hooge, Zhuoro Mo, Yaolong Ju

multimodal benchmarks

Hugging Face Trending Papers

Sep 1

TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data

Generalizable Audio-to-Score (A2S) transcription is fundamentally constrained by the severe scarcity of high-quality, real-world paired data. Relying solely on existing human-annotated datasets often...

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 31

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances

arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.

By Dmitrii Gavrilev, Ilya Borovik, Vladimir Viro

rag safety

arXiv AI

Jun 9

APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music

arXiv:2605. 03395v2 Announce Type: replace-cross Abstract: Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems.

By Jaavid Aktar Husain, Dorien Herremans

rag

One email a morning, machine-written

Related stories

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data

Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset

TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances

APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music