léo Chédin

PhD Student in HCI,
ExSitu, Paris-Saclay University

Digital Performance

Music

I am currently a PhD student in the Extreme Situated Interaction team at Paris-Saclay University, studying movement generation for choreographic creativity under the supervision of Sarah Fdili Alaoui and Jules Françoise. I work at the intersection of artistic practices (music, dance, and digital art) and human-machine interaction. I’m interested in everything dance related, including choreography, creativity-support tools, annotation and transmission of dance. I come from a music technology background and I am also a musician and composer.

Research

Motion capture and movement generation for choreography

Léo Chédin, Jules Françoise, Sarah Fdili Alaoui

Korai is an interactive system that enables direct interaction with AI-based movement generation models. It allows practitioners to visualize, edit, and manipulate 3D motion data. It also enables practitioners to interact directly with movement generation models, which is critical to understand the models' behavior. Korai also features several tools that support learning movements - including a loop function and a playback rate modifier - and choreography.

See the tool

Designing Movement Generation Models in Collaboration With Voguing and Dancehall Dancers

Léo Chédin, Jules Françoise, Baptiste Caramiaux, Sarah Fdili Alaoui

Recent advances in Artificial Intelligence have enabled powerful generative models, yet few are tailored to dancers’ practices. We present a long-term collaboration with a Voguing and Dancehall collective to design movement generation models trained on their repertoire.

PDF to come after the conference. | CHI' 26

Brain signals for real-time musical applications

Léo Chédin, Giorgia Cantisani, Benoît Montigné, Daniel Pressnitzer

Using electroencephalographic signals (EEG) for music creation has a long and distinguished history. Here, we introduce MaxMuse, an open-source streamlined system combining a low-cost, consumer-grade EEG headset (Muse2, InteraXon) and a widely used real-time graphical programming language (Max/MSP, Cycling'74). Pilot benchmarks show that the system is appropriate to process so-called "alpha waves", often used in brain-computer interfaces, but also auditory-evoked responses. Overall, we suggest that MaxMuse may facilitate novel interactive musical applications for which EEG signals can easily be collected from the composer, performer, or even from the audience.

Source code for MaxMuse (Max/MSP objects)

Source code for Muse Tools

Source Separation of Computer Assisted Orchestration

Luke Dzwonczyk, Léo Chédin, Alejandro Saldarriaga-Fuertes, Max Sherr, Hélène-Camille Crayencour, Carmine Emanuele Cella

Adding source separation as a pre-processing step for computer assisted-orchestration.

Paper (PDF) | AIMC 2022

Projects

This Is Unreal

Dance piece by Pierre Godard and Liz Santoro, 2025

This Is Unreal creates a hybrid world where the authentic and the synthetic contaminate each other. The music slides from romantic piano to algorithmic variations and pop music. It is an autobiographical pact gone awry — an autofiction for the age of deepfakes, a dizzying and unsettling game. Where does the body end? Where does the machine begin? And what if it’s precisely this indeterminacy that defines us today?

Learn more

Le mécanisme de Scarpa

Installation by Baptiste Leroux, 2025

Le Mécanisme de Scarpa is an automated multimedia installation. The work explores the migration of tree species due to climate change. More broadly, it examines the complex relationship between technology and nature conservation.

See video

For Patricia

Dance piece by Sarah Fdili Alaoui and John Sullivan, 2024

“For Patricia” is an ode to postmodernism in Dance. “For Patricia”, or for Trisha, is in honor of one of the inventors of postmodernism Trisha Brown (1936-2017) whose choreographic style challenged traditional notions of dance and pushed the boundaries of dance by expanding what movement and choreography meant. Just like Brown explored choreographic structures such as accumulation, repeating, and reversing, etc., we explore ways to use compositional structures generated through Artificial Intelligence (AI) to organize simple choreographic and sonic patterns.

Learn more