Category Research

Work from AIM researchers was presented on June 25th at the PreTrain 2025 pre-conference presentation event. The event, hosted by the King’s College London NLP Group in the Department of Informatics at King’s College London, aimed to showcase accepted work in the ACL 2025, ICML 2025, and ICLR 2025 conferences and foster discussions.

AIM PhD student Yinghao Ma presented the following paper he coauthored with, among others, academic Emmanouil Benetos:

MuPT: A Generative Symbolic Music Pretrained Transformer, Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, Xinrun Du, Shuyue Guo, Yiming Liang, Yizhi Li, Shangda Wu, Junting Zhou, Tianyu Zheng, Ziyang Ma, Fengze Han, Wei Xue, Gus Xia, Emmanouil Benetos, Xiang Yue, Chenghua Lin, Xu Tan, Stephen W. Huang, Jie Fu, Ge Zhang, accepted at ICLR 2025.

On 30 June – 5 July 2025, AIM researchers will participate at the IEEE International Joint Conference on Neural Networks (IJCNN 2025), the flagship conference of the IEEE Computational Intelligence Society and the International Neural Network Society.

The following papers authored/co-authored by AIM members will be presented at IJCNN 2025:

• ImprovNet – Generating Controllable Musical Improvisations with Iterative Corruption Refinement, by Keshav Bhandari, Sungkyun Chang, Tongyu Lu, Fareza Rahman Enus, Louis Bradshaw, Dorien Herremans, Simon Colton
• Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks, by Christos Plachouras, Julien Guinot, George Fazekas, Elio Quinton, Emmanouil Benetos, Johan Pauwels

The following presentation from an AIM PhD student will also be made at IJCNN 2025:

• Split Fine-Tuning of BERT-based Music Models in the Edge-Cloud Continuum: An Empirical Analysis, by Bradley Aldous, Wai Fong Tam, Ahmed M. A. Sayed

See you in Rome!

The 14th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART), part of Evostar, took place in Trieste, Italy, between 23 and 25 April 2025.

We are pleased to announce that the following paper, authored by AIM PhD student Keshav Bhandari, received the best paper award!

Yin-Yang: Developing Motifs With Long-Term Structure And Controllability, Keshav Bhandari, Geraint A. Wiggins, Simon Colton

Yin-Yang is a neuro-symbolic framework that combines three transformer models to generate structured melodies with coherent long-term development, while allowing user control over musical themes and variations.