Bio
Daniel Stoller is a Senior Research Scientist (Manager, Research) in the Artist-First AI Music lab at Spotify. He previously received his PhD in machine learning for music information retrieval from Queen Mary University of London.
His research focuses on generative modeling - diffusion models, flow matching, VAEs, and their controllability - as well as representation learning. He applies these methods to audio generation, music information retrieval, and multimodal music understanding tasks.
SAUNA: Song-Level Audio & User-Listening Data Neural Alignment
Morgan Buisson, Juan José Bosch, Daniel Stoller
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2026
Efficient Representation Learning for Music Via Likelihood Factorisation of a Variational Autoencoder
Ningzhi Wang, Daniel Stoller, Simon Dixon
IEEE International Workshop on Machine Learning for Signal Processing (MLSP) • 2025
LLark: A Multimodal Instruction-Following Language Model for Music
Joshua P. Gardner, Simon Durand, Daniel Stoller, Rachel M. Bittner
International Conference on Machine Learning (ICML) • 2024