Cave Dance
Generative Art
Biocentric Art
Generative Art
7th -10th centuries
Gansu Province, China

One of the most significant cultural heritage sites in the world, Dunhuang preserves more than 400 embellished Buddhist cave shrines dating from the fifth century to the fourteenth century. Covered with murals and sculptures, these cave shrines enclose visitors with an imaginary landscape of Buddhist legends and paradises. Standing out from the rich visual culture of the Dunhuang caves, scenes of celestial dance performances in Buddhist paradises are widely acclaimed as the most representative of artistic achievements at Dunhuang. Held within Duhuang’s grand repository of ancient documents are textual records of annotated movements for the wine dance, which combined performance and game to enact intoxicated transcendence at banquets.

Based upon multi-year interdisciplinary research on the Buddhist culture of dance in Dunhuang, the Cave Dance project harnesses the power of machine learning to bring new insights into the ancient dance forms.

Data from static mural drawings and motion capture of professional dancers were used to train a machine-learning model, which generated a human-computer collaborative choreography of animated movement sequences. Through this process, Cave Dance breathes new life into static dance paintings and translates ancient texts; it presents a contemporary reconstruction—and imagination—of these ancient dances.
Flowering from the diverse body of research of this interdisciplinary project, Cave Dance manifests as a set of digital installations that elucidate the multifold culture of dance in Buddhist cave shrines. The exhibition not only immerses the audiences in a dynamic world of Dunhuang dance, but also leads them into the deeper cultural dimension of Buddhist dance—where audiences are invited to contemplate the themes of body, life, and spiritual transcendence embodied by the celestial dance in the cave.


Born from the largest project team at CAMLab, Cave Dance brings together art historians, A.I. scientists, data scientists, musicologists, choreographers, Buddhist scholars, architects, and digital artists in a joint effort to bring the ancient Buddhist dance culture to life.

DIRECTORS Eugene Wang, Chenchen Lu
ADMINISTRATION Lorna Desiree Campos
RESEARCH Chenchen Lu, April Peng, Sophie Lei, Muyun Zhou, Ting-Ning Wen, Anna Borou Yu, Tiange Zhou, Xiaoyu Yang, Yanyue Li, Xiangyi Sun, Ziming Su, Icey Lin, Zhining Xia
TECH RESEARCH Anna Borou Yu, Chengan He, Jiashun Wang, Amo Zeng, Betty Wang, Junhua Liu, Angela Shen, Ningjing Tang, Diana Yue, Rachel Ai
SCREENWRIGHT Eugene Wang, Chenchen Lu
CHOREOGRAPHY Anna Borou Yu, Ting-Ning Wen, Yanyue Li, Xiangyi Sun
PERFORMANCE Anna Borou Yu, Ting-Ning Wen, Shuqi Cong, Teng Shi, Shumeng A, Qingyuan Hu, Hansong Wang
VISUAL ARTISTS Jam Jianyu Mo(3d), Reraner Yetong Xin(3d), Amo Mengying Zeng(3d), Jake Xi Wang(3d), Haofan Liu(3d,TD), Du Ren (3d), Chao Zhou(3d), Erica Yuhan Song(3d)
EDITING Suki Yi Su, Curry Sicong Tian, Anna Borou Yu, Jiajian Min, Yihan Yin, Chenchen Lu, Ziming Su
3D DESIGN Jiajian Min, Wenbo Xiang, Danlei Huang, Yingxuan Ma
VISUAL DESIGN Wanni Xu, Jianyu Zhang, Lily Li, Sijia Chen, Zhifei Xu, Jintong Duan
LIVE ACTION Fletcher Liujiyi Zuo, Jiajian Min, Shuyi Wang, Joseph Weingrad/ Xiuxing Wang
SOUND DESIGN Tiange Zhou, Leon Hangfeng Sun
WEBSITE DESIGN Chun Wang, Amo Zeng
PUBLIC PROGRAM Alina Yijia Yang, Elaine Yilin Huang, Sabrina Mingjia Chen
EXHIBITION DESIGN Jiajian Min, Anna Borou Yu
EXHIBITION MANAGEMENT Simone Levine, Jiajian Min
EXHIBITION AV SYSTEM dbpc (Dan and Ben Production Company)
EXHIBITION INSTALLATION DCL (Design Communications Ltd.), EPS Painting and Services
MOTION CAPTURE Beijing TenYoun 3D Technology Co., Ltd, The MIT.nano Immersion Lab, Barnard College Movement Lab
TECH SUPPORT Shujia Yun, Tianlin Yan, Bowei Li
TECH CONSULTANT Huazhe Xu, Zeyu Wang, Renju Li
PRODUCTION CONSULTANT Jeff Grantz, Wenhua Shi, Oliver Radford, Sean Stewart
SPECIAL THANKS Beijing Dance Academy
Dunhuang Academy
Shing-Tung Yau, Yingying Wu, Yuting Zhang