| title | TuneJury: An Open Metric for Improving Music Generation Preference Alignment |
|---|---|
| authors | Yonghyun Kim, Junwon Lee, Haiwen Xia, Yinghao Ma, Junghyun Koo, Koichi Saito, Yuki Mitsufuji, Chris Donahue |
| date | 2026-06-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.17006 |
| affiliation | TuneJury |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated on our held-out test split, supporting data filtering via a simple score threshold. TuneJury generalizes to both held-out test pairs and out-of-distribution benchmarks, remaining competitive with prior baselines on the latter. For generators released after training, we introduce anchor calibration, a post-hoc, per-system Bradley-Terry calibration that recovers agreement at substantially better data efficiency than from-scratch retraining. The same frozen reward drives consistent reward-axis gains across three downstream applications: inference-time best-of-N selection, DITTO-style latent optimization, and expert-iteration post-training. TuneJury is available at https://github.com/yonghyunk1m/TuneJury. |
cite
@misc{kim2026tunejury,
title={TuneJury: An Open Metric for Improving Music Generation Preference Alignment},
author={Yonghyun Kim and Junwon Lee and Haiwen Xia and Yinghao Ma and Junghyun Koo and Koichi Saito and Yuki Mitsufuji and Chris Donahue},
year={2026},
eprint={2606.17006},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.17006}
}