Biography

I am currently a Ph.D. student in Computer Science and Technology at Zhejiang University, fortunately advised by Prof. Chunhua Shen and Prof. Hao Chen. Before that, I pursued my master's degree under the supervision of Prof. Xiaofei He and Prof. Deng Cai, and received my B.Eng. degree from the University of Electronic Science and Technology of China.

Research Interests

  • Generative models
  • Autoregressive video generation
  • World model
  • Customization and editing

News

  • [2026.03] Two papers were accepted by CVPR.

Selected Publications

Arxiv

From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping

Zekai Luo*, Yuwei Liang*, Ruiqi Ma, Haoyu Huang, Xuehao Wang, Huanyi Zheng, Mingyu Liu, Linhao Zhong, Chenchen Jing, Yuling Xi, Hao Chen

StreamingSwap enables real-time, long-form video face swapping with identity-aware supervision and efficient generation.

[paper] [project]
CVPR 2026

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

Zekai Luo, Zongze Du, Zhouhang Zhu, Hao Zhong, Muzhi Zhu, Wen Wang, Yuling Xi, Chenchen Jing, Hao Chen, Chunhua Shen

LivingSwap explores high-fidelity and temporally consistent face swapping for cinematic long videos.

[paper] [project]
CVPR 2026

Exploring Spatial Intelligence from a Generative Perspective

Muzhi Zhu, Shunyao Jiang, Huanyi Zheng, Zekai Luo, Hao Zhong, Anzhou Li, Kaijun Wang, Jintao Rong, Yang Liu, Hao Chen, Tao Lin, Chunhua Shen

Introduces GSI-Bench for evaluating and improving generative spatial intelligence in multimodal models.

[paper]
NeurIPS 2024

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation

Muzhi Zhu*, Yang Liu*, Zekai Luo*, Chenchen Jing, Hao Chen, Guangkai Xu, Xinlong Wang, Chunhua Shen

DiffewS adapts diffusion-model priors to few-shot and in-context semantic segmentation through KV fusion.

[paper]
AAAI 2025

Local Conditional Controlling for Text-to-Image Diffusion Models

Yibo Zhao, Liang Peng, Yang Yang, Zekai Luo, Hengjia Li, Yao Chen, Zheng Yang, Xiaofei He, Wei Zhao, Qinglin Lu, Boxi Wu, Wei Liu

Studies training-free local conditional control for text-to-image diffusion models.

[paper]
IJCVUnder Review

Exploring the Potential of Diffusion Models for In-Context Segmentation

Zekai Luo*, Yang Liu*, Muzhi Zhu, Chenchen Jing, Hao Chen, Bo Feng, Hao Wang, Shiyu Li, and Chunhua Shen

DiffICS extends diffusion-based in-context segmentation to image, video, and geometry-prompt settings.

Education

Zhejiang University
Ph.D. in Computer Science and Technology, 2025 - Present
Advisors: Prof. Chunhua Shen and Prof. Hao Chen

Zhejiang University
M.S. in Computer Science and Technology, 2022.09 - 2025
Transferred to the Ph.D. program in 2025
Advisors: Prof. Xiaofei He and Prof. Deng Cai

University of Electronic Science and Technology of China
B.Eng. in Software Engineering, 2018.09 - 2022.06

Honors

  • Outstanding Graduate Student, Zhejiang University x2
  • Excellent Graduate of Sichuan Province
  • First-class Scholarship, UESTC x3
  • National Third Prize, Computer Design Competition