I am a postdoctoral researcher at the RITMO Centre for Interdisciplinary Studies of Rhythm, Time and Motion at the University of Oslo.
With a background in music production and an MSc. and PhD in Informatics, my academic interests lie in the cross-section between art and science.
My current research is centered around expressive movement with 3D motion capture, generative machine learning and the use of AI as a tool for pursuing and understanding creativity.
Full paper: https://www.tandfonline.com/doi/pdf/10.1080/14626268.2024.2327006
What role does deviation from realism play in the potential for generative artificial intelligence (AI) as a creative tool? This paper presents a deep case-study exploring interactions with AI-generated dance sequences as an inspiration source in dance composition and improvisation. This work challenges existing notions of the importance of realism in dance generation models, exemplifies the importance of close collaboration with practitioners in evaluating AI-generated artefacts and proposes glitch as a potential use case for dance ideation as it encourages dancers to embody unfamiliar movement qualities and break from ingrained patterns.
Full details: https://diegomarin.art/portfolio/dancing-embryo/
This dance performance presents a real-time collaborative performance between a human and an AI dancer. Using motion tracking technologies, an AI-generative dance model transforms the avatar’s movement in response to the human dance. The dancer follows a specific methodology: not only shaping the movements of the AI, but also allowing himself to be shaped in return by the behavior of the avatar.
What emerges is a human–AI kinematic relationship that exists only through the act of dancing.
Toured internationally in Europe and Latin America between 2022-2026
