I am working on video generation and image generation. I am currently seeking opportunities in AI Engineering or PhD research. Please contact me at zhengboxu_pku@outlook.com!
🔥 News
- 2026.01: Release the paper for MoCha!
- 2025.10: Try MoCha with ComfyUI workflow!
- 2025.10: Release the inference code for MoCha.
📝 Publications
- Frequency-controlled Diffusion Model for Versatile Text-guided Image-to-Image Translation. X. Gao, Zhengbo Xu, J.H. Zhao, J.Y. Liu. Proceedings of the AAAI Conference on Artificial Intelligence. 2024.
- Awe fosters positive attitudes toward solitude. T.L. Jiang, Y.G. Yin, W.Y. Yuan, C.X. Hao, Y.H. Du, Zhengbo Xu, Joshua Hicks. Nature Mental Health (2024): 1-11.
- Self-aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation. W.J. Wang, Zhengbo Xu, H.F. Huang, J.Y. Liu. Proceedings of the 30th ACM international conference on multimedia. 2022.
🎄 Projects
Virtual 3D Layout Generation and Edition by LLM
Generate and edit a complete 3D virtual layout using a text prompt.
Large Language Model | Blender
Non-Photorealistic Rendering
Anime shading and post-processing in the style of Honkai: Star Rail
Unity | Shader Language (HLSL)
3D Modeling
Collection of modeling projects by Digital Content Creation (DCC) software.
Maya | Blender
🎖 Honors and Awards
- 2023.07 University-Level Scholarship for three years.
- 2018.11 Second Prize in China Mathematical Olympiad (CMO).
- 2017.11 First Prize in National Olympiad in Informatics in Provinces (NOIP).
📖 Educations
- 2024.09 - 2025.12, MSc in Advanced Computer Science, Oxford University, United Kingdom.
- 2019.09 - 2023.07, BSc in Intelligent Science (Turing Class), Peking University, China.