Jaehun Kim (2021), Increasing trust in complex machine learning systems: Studies in the music domain, PhD Thesis Delft University of Technology.

Hyemin Ahn, Jaehun Kim, Kihyun Kim, Songhwai Oh (2020), Generative autoregressive networks for 3d dancing move synthesis from music, In IEEE Robotics and Automation Letters Volume 5 p.3501-3508.

Jaehun Kim, Julián Urbano, Cynthia C.S. Liem, Alan Hanjalic (2019), Are Nearby Neighbors Relatives?: Testing Deep Music Embeddings, In Frontiers in Applied Mathematics an Statistics Volume 5 p.1-17.

Jaehun Kim, Sandy Manolios, Andrew Demetriou, Cynthia Liem (2019), Beyond Explicit Reports: Comparing Data-Driven Approaches to Studying Underlying Dimensions of Music Preference, In ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization p.285-293, Association for Computing Machinery (ACM).

Jaehun Kim, Julián Urbano, Cynthia C.S. Liem, Alan Hanjalic (2019), One deep music representation to rule them all? A comparative analysis of different representation learning strategies, In Neural Computing and Applications Volume 32 (2020) p.1067-1093.

Jaehun Kim, Minz Won, Cynthia C.S. Liem, Alan Hanjalic (2018), Towards Seed-Free Music Playlist Generation: Enhancing collaborative Filtering with Playlist Title Information, In RecSys Challenge '18 p.1-6, Association for Computing Machinery (ACM).

Jaehun Kim, Minz Won, Xavier Serra, Cynthia C. S. Liem (2018), Transfer Learning of Artist Group Factors to Musical Genre Classification, In WWW'18 Companion Proceedings of the The Web Conference 2018 p.1929-1934, International World Wide Web Conferences Steering Committee.