Zichen Miao
Contact:
MSEE 289, Purdue University
West Lafayette, IN 47907
miaoz [at] purdue.edu
I am a 4th year PhD student in Elmore Family School of Electrical and Computer Engineering at Purdue University, advised by Prof. Qiang Qiu. My current research interests are machine learning and computer vision.
Previously, I got my B.S. from School of Automation and Electrical Engineering, Beihang University in 2019.
Experiences
Microsoft GenAI (2024.05-2024.08)
Research Intern
Mentors: Zhengyuan Yang, Lijuan Wang
Microsoft Research & Azure (2023.05-2023.08)
Research Intern
Mentors: Jiang Wang, Zicheng Liu
Publications (* means equal contribution.)
Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
Zichen Miao*, Wei Chen*, Qiang Qiu
CVPR 2025
Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
Zichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang, Zicheng Liu, Lijuan Wang, Qiang Qiu
ICLR 2025
[pdf] [code]
Large Convolutional Model Tuning via Filter Subspace
Wei Chen, Zichen Miao, Qiang Qiu
ICLR 2025
[pdf] [code]
Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning
Zichen Miao, Jiang Wang, Ze Wang, Zhengyuan Yang, Lijuan Wang, Qiang Qiu, Zicheng Liu
CVPR 2024
[pdf]
Training Bayesian Neural Networks with Sparse Subspace Variational Inference
Junbo Li, Zichen Miao, Qiang Qiu, Ruqi Zhang
ICLR 2024
[pdf] [code]
Inner Product-based Neural Network Similarity
Wei Chen*, Zichen Miao*, Qiang Qiu
NeurIPS 2023
[pdf]
Continual Learning With Filter Atom Swapping
Zichen Miao, Ze Wang, Wei Chen, Qiang Qiu
ICLR 2022 (Spotlight)
[pdf] [code]
Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks
Zichen Miao, Ze Wang, Xiuyuan Cheng, Qiang Qiu
NeurIPS 2021
[pdf]
Learning to Learn Dense Gaussian Processes for Few-Shot Learning
Ze Wang*, Zichen Miao*, Xiantong Zhen, Qiang Qiu
NeurIPS 2021
[pdf]
Image Generation using Continuous Filter Atoms
Ze Wang, Seunghyun Hwang, Zichen Miao, Qiang Qiu
NeurIPS 2021 (Spotlight)
[pdf]