Mengqi Huang 

Ph.D Candidate

School of Cyber Science and Technology
University of Science and Technology of China

443 Huangshan Road, Hefei, China 230027

Email: huangmq@mail.ustc.edu.cn


Mengqi Huang is now pursuing his doctoral degree at the University of Science and Technology of China (USTC).
His research interests include image/video generation and deep generative models (e.g., generative adversarial nets, autoregressive models, and diffusion models).
He has won the Best Student Paper Award of ACM Multimedia 2022 as the first author and has multiple publications appeared in the top conferences such as CVPR, AAAI, and ACM MM.
He has received the funding of The First National Natural Science Foundation of China for Youth Student Fundamental Research (Ph.D. candidate), with a grant amount of ¥300,000.

Funding


The National Natural Science Foundation of China for Youth Student Fundamental Research (Ph.D. candidate)
首届国家自然科学基金青年学生基础研究项目(博士研究生)
Research on Text-guided Long Video Generation based on Spatiotemporal Native Collaboration
《基于时空原生协同的文本指导长视频生成技术研究》
¥300,000
May 2024 - December 2026

Education


University of Science and Technology of China
Ph.D. in Cyber Security
July 2020 - now, Hefei & Beijing
Advisor: Prof. Zhendong Mao

University of Science and Technology of China
B.Eng in Automation
September 2016 - June 2020, Hefei
Advisor: Prof. Zhendong Mao

Selected Paper Publications [Google Scholar]


PDF
RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
CVPR 2024 , CCF-A [Project Page]
Mengqi Huang, Zhendong Mao, Mingcong Liu, Qian He, Yongdong Zhang

PDF
Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
AAAI 2024 , CCF-A, 23.75% acceptance rate
Hao Li, Mengqi Huang, Lei Zhang, Bo Hu, Yi Liu, Zhendong Mao

PDF
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
AAAI 2024 , CCF-A, 23.75% acceptance rate [Project Page]
Zhuowei Chen, Shancheng Fang, Wei Liu, Qian He, Mengqi Huang, Yongdong Zhang, Zhendong Mao

PDF
Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization (Highlight, 2.6% of submitted papers)
CVPR 2023 , CCF-A, 25.8% acceptance rate [Github] [Video]
Mengqi Huang, Zhendong Mao, Zhuowei Chen, Yongdong Zhang

PDF
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
CVPR 2023 , CCF-A, 25.8% acceptance rate [Github] [Video]
Mengqi Huang, Zhendong Mao, Quan Wang, Yongdong Zhang

PDF
DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation (Best Student Paper Award, 1/3009 of submitted papers)
ACM Multimedia 2022 , CCF-A, 27.9% acceptance rate
Mengqi Huang, Zhendong Mao, Penghui Wang, Quan Wang, Yongdong Zhang

Internships


ByteDance Inc.
Research Intern, Intelligent Creation Department.
Beijing
July 2023 - Now

Kuaishou Technology
Research Intern, Search Technology Department.
Beijing
March 2022 - Novemeber 2022

McMaster University
Research Intern, Computing & Software School (Department)
Hamilton, Canada
June 2019 - September 2019

Competitions

第二届粤港澳大湾区国际算法算例大赛-高效可控的文生图方法
指导老师,第二名(奖金20万元人民币).
August 2023 - Novemeber 2023

首届兴智杯全国人工智能应用创新大赛-多模态技术创新赛-基于文本的图像生成
第一完成人,二等奖.
August 2022 - Novemeber 2022

ACM Multimedia 2020 Social Media Prediction Challenge
Team Leader, Top Performance Award. [Github]
March 2020 - June 2020

ICIP 2020 Image Popularity Prediction Challenge
Team Leader, Reach Fourth Grade.
March 2020 - June 2020

Patents

基于迭代优化策略的多模态信息社交媒体流行度预测方法: 毛震东; 张勇东; 黄梦琪

Last update: 18 May, 2023. Webpage template borrows from Weinan Zhang.

News


27 February 2024
One papers is accepted by CVPR 2024!

09 December 2023
Two papers are accepted by AAAI 2024!

21 March 2023
Our paper "Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization" is selected as a highlight at CVPR 2023!

27 February 2023
Two papers are accepted by CVPR 2023!

13 October 2022
Our paper "DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation" receives the Best Student Paper Award at ACM Multimedia 2022!

30 June 2022
One paper is accepted by ACM Multimedia 2022!