Incoming PhD Student, Imperial College London

Research Intern, ByteDance Seed

Contact: oliveryanzuolu AT gmail DOT com

<- Click my avatar to find me :)

👋 Hi, this is Yanzuo Lu, an incoming PhD student at Imperial College London supervised by Prof. Jiankang Deng. Currently I am also a research intern at ByteDance Seed, mentored by Yuxi Ren & Jie Wu and led by Xuefeng Xiao.

Now my research focus on the efficiency of both generative diffusion models (DMs) and multimodal large language models (MLLMs). For DMs, I develop diffusion distillation algorithms to reduce sampling steps while maintaining the quality of generated images or videos. For MLLMs, I develop speculative decoding algorithms to train a draft model for faster inference losslessly with target model verification.

Previously, I received both my MEng and BS degree from Sun Yat-Sen University (SYSU) advised by Prof. Andy J Ma, Xiaohua Xie, and Jianhuang Lai, where I have some experience with customized diffusion models, domain adaptation and person re-identification.

My Chinese name is 卢彦作, and you may also want to call my English name as Oliver. Feel free to explore my works below and reach out via email for any discussion.

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
Yanzuo Lu, Yuxi Ren, Xin Xia, Shanchuan Lin, Xing Wang, Xuefeng Xiao, Andy J Ma, Xiaohua Xie and Jianhuang Lai
International Conference on Computer Vision (ICCV), 2025 (Highlight)
arXiv

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
Yanzuo Lu, Manlin Zhang, Andy J Ma, Xiaohua Xie and Jianhuang Lai
Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Highlight)
arXiv     Publication     Code     Talk

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Yuxi Ren, Xin Xia, Yanzuo Lu, Jiacheng Zhang, Jie Wu, Pan Xie, Xing Wang and Xuefeng Xiao
Conference on Neural Information Processing Systems (NeurIPS), 2024
arXiv     Publication     Project     HuggingFace     PR

ByteEdit: Boost, Comply and Accelerate Generative Image Editing
Yuxi Ren, Jie Wu, Yanzuo Lu, Huafeng Kuang, Xin Xia, Xionghui Wang, Qianqian Wang, Yixing Zhu, Pan Xie, Shiyin Wang, Xuefeng Xiao, Yitong Wang, Min Zheng and Lean Fu
European Conference on Computer Vision (ECCV), 2024
arXiv     Publication     Project

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
Yanzuo Lu, Meng Shen, Andy J Ma, Xiaohua Xie and Jian-Huang Lai
AAAI Conference on Artificial Intelligence (AAAI), 2024
arXiv     Publication     Code

Collaborative Learning of Diverse Experts for Source-free Universal Domain Adaptation
Meng Shen, Yanzuo Lu, Yanxu Hu and Andy J Ma
ACM International Conference on Multimedia (ACMMM), 2023
Publication