Encypher - v1 - Shared Agency and Social Presence in Collaborative Music Generation for Dance Cyphers

Oct 22, 2026

Music and dance express social connection, yet most human-computer interaction research emphasizes solo performers. Encypher is a collaborative generative music system that converts collective movement qualities into text prompts, conditioning real-time music for dance cyphers. Across co-design with local dancers, a user study with newcomers, a public museum event, and a live performance, participants developed shared agency, treating the music as responsive to room energy. The system fostered social presence by encouraging mutual cue-following, and offers a design framework for embodied collaborative expression.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Abstract

1 Introduction

Motivation: from solo performance to social encounters

System overview and inspiration

Development process and findings

Key contributions

arXiv : 2609 . 18062v 1 [cs .HC] 16 Sep 2026 Encypher: Shared Agency and Social Presence in Collaborative Music Generation for Dance Cyphers Zhixing Chen [zhixingc@mit.edu](zhixingc@mit.edu)[ ](zhixingc@mit.edu)Massachusetts Institute of Technology Cambridge, USA Cheng-Zhi Anna Huang [huangcza@mit.edu](huangcza@mit.edu)[ ](huangcza@mit.edu)Massachusetts Institute of Technology Cambridge, USA Figure 1: Dancers in an Encypher cypher, each standing in a colored pool of light projected onto the floor of their zone; the screen has been replaced by light on the dancers themselves. Abstract Music and dance are social practices of expression and connection, yet most HCI work in human-AI co-creation centers the solo performer. As generative music matures, we ask not only what AI can compose but what social encounters it can organize around sound. We present Encypher, a collaborative generative music system that translates collective movement qualities into text prompts conditioning real-time music generation for dance cyphers. Through five weeks of co-design with local dancers, a user study with unacquainted participants, a public museum event, and a live performance, we found that users developed shared agency, perceiving the music as a response to the room’s energy. While newcomers felt uncertain, the system fostered social presence by prompting them to look to each other for cues. By treating sociality as a design concern rather than a downstream effect, we offer a framework and design implications for AI systems for collaborative, embodied expression. CCS Concepts • Human-centered computing → Empirical studies in HCI; Collaborative and social computing; Interactive systems and tools; Interaction techniques; • Applied computing → Sound and music computing; Performing arts. Keywords generative music, live music models, dance cypher, shared agency, social presence, embodied interaction, co-design, human-AI interaction, movement mapping 1 Introduction Music and dance are ways people coordinate attention, express identity, and meet one another through the body. From early instruments to turntables and contemporary sampling devices, technology has continually reshaped how we create, perceive, and share Chen and Huang rhythm and movement. Artificial intelligence (AI) extends this lineage: once limited to narrowly structured tasks, AI is now a creative medium capable of perceiving, generating, and co-creating with humans across modalities. Multimodal systems can now capture the gestures of the body and the intricacies of music together, opening new ways of communicating through movement [12] . Yet as generative music becomes more musically usable, most HCI work in this space still centers the solo performer. We see an opportunity to ask not only what AI can compose, but what kinds of social situations it helps create—facilitating human-to-human connection rather than only human-AI interaction. We present Encypher1 , a collaborative generative music system that translates collective movement qualities into text prompts to condition real-time music generation for dance cyphers (Figure 2) . In Hip-Hop culture, a cypher is a circular freestyle practice defined by energy sharing, exchange, and communal response. The name Encypher plays on encipher, reflecting the system’s role in translating embodied movement into a generative musical process. Encypher builds on Con Moto [13], which used inference-time steering of a symbolic music transformer for dyadic dance improvisation. Where Con Moto operated on note-level MIDI manipulation between two dancers, Encypher pivots to high-fidelity neural audio and expands the interaction into a true cypher, where all participants collectively steer music generation in real time. We developed Encypher through autobiographical design based on the first author’s own dance practice, five weeks of co-design with local dancers (n=15), a user study with unacquainted participant

FAQs

What problem does Encypher address in collaborative generative music research?

It addresses the tendency of human-AI co-creation work to center the solo performer, instead aiming to create social situations around sound in dance cyphers.

How does Encypher connect dancers’ movement to real-time music generation?

It translates collective movement qualities into text prompts that condition real-time music generation, based on kinematic features extracted from dancers’ joint movements.

What did the study find about users’ sense of control?

Users reported shared agency, perceiving the music as responding to the room’s energy rather than only their own movements.

Oct 22, 2026

Uploaded by Quinn Holloway