@TechReport{Cai_2026_MASS,
author = {Cai, Ziqi and Yang, Siqi and Wang, Yimu and Gao, Zixian and Liu, Yunheng and Weng, Shuchen and Wu, Erwin and Zhang, Kaipeng and Shi, Boxin},
title = {{MASS}: Multiplayer World Models with Authoritative Shared State},
institution = {Technical Report},
year = {2026},
eprint = {2608.06257},
url = {https://arxiv.org/abs/2608.06257},
}
Ziqi Cai蔡子祺
Ph.D. Student · School of Computer Science, Peking University
About
I'm a third-year Ph.D. student at the Camera Intelligence Lab, Peking University, advised by Prof. Boxin Shi. I work at the intersection of 3D vision and generative models, with a focus on physically grounded visual generation: I want image and video models to understand how light really behaves, so they can estimate it, control it, and render it faithfully.
Before coming to Peking University, I received my bachelor's degree from Beijing Jiaotong University and was a research intern at the Institute of Computing Technology, Chinese Academy of Sciences, where I had the good fortune to work with Prof. Lin Gao, Prof. Hongbo Fu, Prof. Yu-Kun Lai, Prof. Shu-Yu Chen, and Kaiwen Jiang. I received the President's Scholarship at Peking University, and I am currently a visiting scholar at Science Tokyo.
Publications
@InProceedings{Cai_2026_ECCV_Lighting,
author = {Cai, Ziqi and Weng, Shuchen and Liu, Kaiqi and Wang, Zifeng and Zhang, Zhiquan and Teng, Minggui and Jiang, Han and Shi, Boxin},
title = {Video Generation Models Are Inherent Lighting Estimators},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2026},
eprint = {2607.04674},
url = {https://arxiv.org/abs/2607.04674},
}@InProceedings{Cai_2026_CVPR,
author = {Cai, Ziqi and Yang, Taoyu and Chang, Zheng and Li, Si and Jiang, Han and Weng, Shuchen and Shi, Boxin},
title = {Lighting-grounded Video Generation with Renderer-based Agent Reasoning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2026},
}@InProceedings{Liu_2026_ECCV_MAVIN,
author = {Liu, Kaiqi and Mao, Yunyao and Cai, Ziqi and Geng, Zheng and Wang, Jing and Wang, Qiulin and Wang, Xintao and Wan, Pengfei and Gai, Kun and Weng, Shuchen and Shi, Boxin},
title = {MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2026},
eprint = {2606.29473},
url = {https://arxiv.org/abs/2606.29473},
}@InProceedings{Zhang_2026_ACL,
author = {Zhang, Peixuan and Jia, Zijian and Cai, Ziqi and Weng, Shuchen and Li, Si and Shi, Boxin},
title = {ReContraster: Making your posters stand out with regional contrast},
booktitle = {Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL)},
year = {2026},
eprint = {2604.10442},
url = {https://arxiv.org/abs/2604.10442},
}@InProceedings{Cai_2025_CVPR,
author = {Cai, Ziqi and Weng, Shuchen and Xia, Yifei and Shi, Boxin},
title = {PhyS-EdiT: Physics-aware semantic image editing with text description},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2025},
}@InProceedings{Gao2025Unified,
author = {Qiyao Gao and Peiqi Duan and Hanyue Lou and Minggui Teng and Ziqi Cai and Xu Chen and Boxin Shi},
title = {Unified Reconstruction of Static and Dynamic Scenes from Events},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2025},
}@InProceedings{Cai_2024_CVPR,
author = {Cai, Ziqi and Jiang, Kaiwen and Chen, Shu-Yu and Lai, Yu-Kun and Fu, Hongbo and Shi, Boxin and Gao, Lin},
title = {Real-time 3{D}-aware Portrait Video Relighting},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
pages = {6221-6231},
eprint = {2410.18355},
url = {https://arxiv.org/abs/2410.18355},
}@misc{cheng2024dreampolish,
title = {Dream{P}olish: Domain Score Distillation With Progressive Geometry Generation},
author = {Yean Cheng and Ziqi Cai and Ming Ding and Wendi Zheng and Shiyu Huang and Yuxiao Dong and Jie Tang and Boxin Shi},
year = {2024},
eprint = {2411.01602},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2411.01602},
}