ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yitong, Yao, Yue
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910019779297280
author Wang, Yitong
Yao, Yue
author_facet Wang, Yitong
Yao, Yue
contents We present ReTracing, a multi-agent embodied performance art that adopts an archaeological approach to examine how artificial intelligence shapes, constrains, and produces bodily movement. Drawing from science-fiction novels, the project extracts sentences that describe human-machine interaction. We use large language models (LLMs) to generate paired prompts "what to do" and "what not to do" for each excerpt. A diffusion-based text-to-video model transforms these prompts into choreographic guides for a human performer and motor commands for a quadruped robot. Both agents enact the actions on a mirrored floor, captured by multi-camera motion tracking and reconstructed into 3D point clouds and motion trails, forming a digital archive of motion traces. Through this process, ReTracing serves as a novel approach to reveal how generative systems encode socio-cultural biases through choreographed movements. Through an immersive interplay of AI, human, and robot, ReTracing confronts a critical question of our time: What does it mean to be human among AIs that also move, think, and leave traces behind?
format Preprint
id arxiv_https___arxiv_org_abs_2602_11242
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems
Wang, Yitong
Yao, Yue
Computer Vision and Pattern Recognition
We present ReTracing, a multi-agent embodied performance art that adopts an archaeological approach to examine how artificial intelligence shapes, constrains, and produces bodily movement. Drawing from science-fiction novels, the project extracts sentences that describe human-machine interaction. We use large language models (LLMs) to generate paired prompts "what to do" and "what not to do" for each excerpt. A diffusion-based text-to-video model transforms these prompts into choreographic guides for a human performer and motor commands for a quadruped robot. Both agents enact the actions on a mirrored floor, captured by multi-camera motion tracking and reconstructed into 3D point clouds and motion trails, forming a digital archive of motion traces. Through this process, ReTracing serves as a novel approach to reveal how generative systems encode socio-cultural biases through choreographed movements. Through an immersive interplay of AI, human, and robot, ReTracing confronts a critical question of our time: What does it mean to be human among AIs that also move, think, and leave traces behind?
title ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.11242