Junhao Zhuang

Junhao Zhuang

Auto-generated profile, based on publicly available information

Junhao Zhuang

Tsinghua University, Hong Kong, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 July 2025
Verified
Conference Paper
Open access
SZShiyi Zhang
Shiyi Zhang
JZJunhao Zhuang
Junhao Zhuang
ZZZhaoyang Zhang
Zhaoyang Zhang
YSYing Shan
Ying Shan
YTYansong Tang
Yansong Tang

27 July 2025
Verified
Conference Paper
Open access
JZJunhao Zhuang
Junhao Zhuang
LLLingen Li
Lingen Li
XJXuan Ju
Xuan Ju
ZZZhaoyang Zhang
Zhaoyang Zhang
YCYuan Chun
Yuan Chun
YSYing Shan
Ying Shan

19 May 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYaowei Li
Yaowei Li
YBYuxuan Bian
Yuxuan Bian
XJXuan Ju
Xuan Ju
ZZZhaoyang Zhang
Zhaoyang Zhang
JZJunhao Zhuang
Junhao Zhuang
QXQiang Xu
Qiang Xu
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or removing objects) due to the structured nature of inversion noise, which hinders substantial changes. Meanwhile, instruction-based methods often constrain users to black-box operations, limiting direct interaction for specifying editing regions and intensity. To address these limitations, we propose BrushEdit, a novel inpainting-based instruction-guided image editing paradigm, which leverages multimodal large language models (MLLMs) and image inpainting models to enable autonomous, user-friendly, and interactive free-form instruction editing. Specifically, we devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model in an agentcooperative framework to perform editing category classification, main object identification, mask acquisition, and editing area inpainting. Extensive experiments show that our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics including mask region preservation and editing effect coherence.

12 September 2026
Verified
Book Chapter
Closed access
PDF file
YLYawen Luo
Yawen Luo
XSXiaoyu Shi
Xiaoyu Shi
JZJunhao Zhuang
Junhao Zhuang
YCYutian Chen
Yutian Chen
QLQuande Liu
Quande Liu
TXTianfan Xue
Tianfan Xue