Publications
News
- 2026.05: The Paper “CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction” has been accepted by ICML 2026.
Featured Publication
Randomized Scores and Diverse Timbres: Augmenting Automatic Music Transcription with Online-Generated Data
Haiwen Xia, Chao Zhang, Qiuqiang Kong
- Moderate score randomization preserves or improves transfer to new domains.
- Broader timbre coverage consistently improves cross-domain transcription.
- Online-generated examples complement real and existing synthetic training data.
ICML 2026
CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
Yinghao Ma*, Haiwen Xia*, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos
- Introduced a new task for evaluating generated audio from compositional music instructions.
- Created the CMI-Pref dataset using 23 music generation models, with 110k LLM-labeled preferences, 797 hours of generated audio, and a human-labeled subset containing 4027 preference labels.
- Built CMI-RewardBench to evaluate preference learning methods on compositional multimodal music instructions.
- Trained a parameter-efficient reward model that reaches near-SOTA correlation with human labels across multiple evaluation protocols and supports inference-time scaling for music generation models.
You can also find my articles on My Google Scholar profile.