New website is up! It has better project tagging, although it is still populated in blog and press pages, and some issues in publications listing.
News
I am giving my docent lecture as the final step of my promotion to Associate Professor on March 20th, 2026 at 13:00 at the Analysen Room in the EDIT building, at Chalmers Johanneberg Campus.
I am giving a tutorial on machine learning for sound and music computing at the workshop titled Anything but Text! on March 3-4, 2026 at Lineaus University in Växjö Sweden, organized by Dariah Sweden.
Upcoming full day workshop The Culture Code. Register by February 4th, end of the day ->
Selected current projects
View all projectsRecent publications
View bibliographyARIA: A Diagnostic Framework for Music Training Data Attribution
Han, C., Panahi, A., and Tatar, K. 2026. ARIA: A Diagnostic Framework for Music Training Data Attribution. arXiv. arXiv:2605.16181 [cs.SD]. DOI:10.48550/arXiv.2605.16181.
Expanding the machine: Notating generative synthesis with a state-based representation and a navigable timbre space
Madaghiele, V., Lund, L., Holzer, D., Kelkar, T., Tatar, K., and Holzapfel, A. 2026. Expanding the machine: Notating generative synthesis with a state-based representation and a navigable timbre space. Organised Sound. DOI:10.1017/S1355771825100915.
Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints
Liu, H. X. and Tatar, K. 2026. Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints. arXiv. arXiv:2603.07101 [cs]. DOI:10.48550/arXiv.2603.07101.
Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate
Liu, H. X. and Tatar, K. 2026. Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate. arXiv. arXiv:2605.07342 [cs.LG]. DOI:10.48550/arXiv.2605.07342.