About Me

I am a 3^rd year M.Sc. student at Harbin Institute of Technology, supervised by Prof. Wangmeng Zuo. Previously, I received my B.Eng. degree (Honor) at HIT. My research lies in the area of Generative AI.

News

• [2026.03] 🎉 We have released the project page for DreamLite! You can find the code, demos, and more details here.
• [2025.09] One paper is accepted by WACV 2026.
• [2025.09] Started an internship at ByteDance.
• [2025.04] Started an internship at TAL.
• [2025.02] One paper is accepted by CVPR 2025.
• [2024.03] One paper is accepted by ICME 2024 Oral.
• [2023.01] One paper is accepted by ICLR 2023.

Experiences

• Sep.2025 - Present, Intelligent Creation Lab, Bytedance Ltd.
  - Research Intern (Efficient and on-device GenAI)
• Apr.2024 - Sep.2025, Beijing Century TAL Education Technology Co., Ltd.
  - Research Intern (Generative AI)
• Nov.2022 - Jul.2023, TikTok, Ltd.
  - Machine Learning Engineer Intern (TikTok's auto-moderation)
• Mar.2024 - Present, International Telecommunication Union (ITU)
  - Youth Envoy for Generation Connect

Publications

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

Kailai Feng, Y Wei, B Chen, Y Pan, H Ye, S Liu, C Yan, Y Gao, W Zuo

[Project Page][Paper][Code]

VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models

Kailai Feng, Y Zhang, H Yu, Z Ji, J Bai, H Zhang, W Zuo
The IEEE/CVF Winter Conference on Applications of Computer Vision, WACV2026
[Paper][Code]

MC²: Multi-concept Guidance for Customized Multi-concept Generation

J Jiang, Y Zhang, Kailai Feng, X Wu, W Zuo
IEEE Conference on Computer Vision and Pattern Recognition, CVPR2025
[Paper][Code]

Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model

Kailai Feng, M Ni, J Jiang, Z Zhang, W Zuo
IEEE Conference on Multimedia Expo, ICME2024 Oral
[Paper][Code]

Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models

M Ni, Y Zhang, Kailai Feng, X Li, Y Guo, W Zuo
Science China Information Sciences, IF=7.6
[Paper][Code]

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

M Ni, Z Huang, Kailai Feng, W Zuo
International Conference on Learning Representations, ICLR2023
[Paper][Code]

Awards

Sumsang Scholarship, 2024
Special Prize of School Scholarship, 2024
Tencent Scholarship, 2024
Special Prize of School Scholarship, 2023
Outstanding Graduates of Harbin Institute of Technology, 2023