Qiucheng Wu
I am a 2nd year Ph.D. student in Computer Science at University of California, Santa Barbara, under supervision of Prof. Shiyu Chang. I received my bachelor and master's degrees from University of Michigan College of Engineering. I also receivied another bachelor degree from and Shanghai Jiao Tong University UM-SJTU Joint Institute.
My current research focuses on generative models in computer vision. Particularly, I am interested in controllable generation leveraging high-quality pretrained generative models. Besides, my general research interests span natural language processing, trustworthy and scalable machine learning, and reinforcement learning. Some of my projects and publications related to these fields are demonstrated below.
Email: qiucheng@ucsb.edu / 
CV  / 
|
|
|
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
Qiucheng Wu*, Yujian Liu*, Handong Zhao, Trung Bui, Zhe Lin, Yang Zhang, Shiyu Chang
Arxiv, 2023 [Code]
We propose a new text-to-image algorithm with explicit control over cross-attention in diffusion models from spatial and temporal views. This alleviates inconsistencies between images and text and helps to fix errors like missing objects, mismatched attributes, and mislocated objects.
|
|
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Qiucheng Wu, Yujian Liu, Handong Zhao, Ajinkya Kale, Trung Bui, Tong Yu, Zhe Lin, Yang Zhang, Shiyu Chang
CVPR, 2023 [Code] [Demo]
Based on a fixed stable diffusion model, we disentangle target attributes from a single training image. The learned parameters can then be applied to unseen images and achieve same edits. This finding leads to a lightweight image editing framework with only 50 learnable parameters.
|
|
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
Qiucheng Wu*, Yifan Jiang*, Junru Wu*, Kai Wang, Gong Zhang, Humphrey Shi, Zhangyang Wang, Shiyu Chang
Arxiv, 2022 [Code] [Demo]
|
|
Temporal Frame Filtering with Near-Pixel Compute for Autonomous Driving
Wantong Li, Qiucheng Wu, Janak Sharda, Shiyu Chang, Shimeng Yu
IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2022
|
|
Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Yimeng Zhang*, Akshay Karkal Kamath*, Qiucheng Wu*, Zhiwen Fan*, Wuyang Chen, Zhangyang Wang, Shiyu Chang, Sijia Liu, Cong Hao
Proceedings of the 28th Asia and South Pacific Design Automation Conference, 2023
|
|
Learning Action Translator for Meta Reinforcement Learning on Sparse Rewards Tasks
Yijie Guo, Qiucheng Wu, Honglak Lee
AAAI, 2022
Meta reinforcement learning requires substantial amounts of data. To improve the sample efficiency and performance of metal-RL algorithms on sparse-reward tasks, we introduce a novel objective function to learn an action translator among training tasks.
|
|
DataSifterText: Partially Synthetic Text Generation for Sensitive Clinical Notes
Nina Zhou, Qiucheng Wu, Zewen Wu, Simeone Marino, and Ivo Dinov
Journal of Medical Systems, 2022
We propose DataSifter-Text to protect privacy of sensitive textual dataset. The DataSifter-Text obfuscates identifiable information in the dataset. It effectively balances between privacy and utility.
|
|
Compressive Big Data Analytics: An ensemble meta-algorithm for high-dimensional multisource datasets
Simeone Marino, Yi Zhao, Nina Zhou, Yiwang Zhou, Arthur W. Toga, Lu Zhao, Yingsi Jian, Yichen Yang, Yehu Chen, Qiucheng Wu, Jessica Wild, Brandon Cummings, Ivo D. Dinov
PLOS One, 2020
We apply the compressive big data analytics (CBDA) to analyze sailent features and key biomarkers of a high-dimensional dataset.
Most Likely Health Impact in 4th Annual Symposium Poster Competition in Michigan Institute for Data Science, University of Michigan.
|
|
DataSifter: Statistical Obfuscation of Electronic Health Records and Other Sensitive Datasets
Simeone Marino, Nina Zhou, Yi Zhao, Lu Wang, Qiucheng Wu, Ivo D. Dinov
Journal of Statistical Computation and Simulation, 2019
We propose the DataSifter to obfuscate sensitivie dataset while preserve the utility for other researches.
Most Interesting Methodological Advances in 4th Annual Symposium Poster Competition in Michigan Institute for Data Science, University of Michigan.
|
UC Santa Barbara
2nd year Ph.D. student, Sep 2021 - Current
|
University of Michigan
Masters, Computer Science and Engineering, Sep 2019 - May 2021
Bachelor, Computer Science, Sep 2017 - May 2019
GPA: 3.94/4.00
Major Focuses
Natrual Language Processing
Deep Learning for Vision
Data Mining & Advanced Data Mining
|
Shanghai Jiao Tong University
Bachelor, Electircal and Computer Engineering, Sep 2015 - Aug 2019
GPA: 3.67/4.00
Undergraduate Capstone Team Gold Prize (2019)
|
Graduate Student Instructor: Intro to AI (EECS 492)
College of Engineering, University of Michigan, FA 2020 and WN 2021
Leading discussions, design homework, grade exams, help students in office hours.
|
Instructor Assistant: Applied Honors Calculus (Vv156, equivalent to MATH 156 in umich)
UM-SJTU Joint Institute, Shanghai Jiao Tong University, FA 2016
Leading discussions, design and grade homework/exams, help students in office hours.
|
Also I was a grader on Data Mining (EECS 476), Deep Learning (EECS 498), Intro to AI (EECS 592), Applied Linear Algebra (MATH 214), Intro to Computer Organization (EECS 370) for at least 1 semester.
|
|
Fitly Inc.
Machine Learning Intern
Nov. 2019 - Apr. 2020
In this internship, I was responsible for designing a personalized model to provide more accurate food classification results for users. My code is now deployed in the real product.
|
|
Intel Akraino: Edge Cloud Game Architecture
Undergraduate Capstone Team Gold Prize
UM-SJTU Joint Institute, Shanghai Jiao Tong University,
August 2019
In this capstone project, we designed a framework to boost web communications between terminal devices and servers by introducing edge servers. We use kubernets to organize edge servers as different containers. The edge servers are responsible for computing and sending information to terminal devices, leading to more efficient performance.
|
|