Xintong Wu

Xintong Wu

Auto-generated profile, based on publicly available information

Xintong Wu

Department of Automation, Tsinghua University, Beijing, 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 September 2025
Verified
Conference Paper
Open access
WDWenjing Deng
Wenjing Deng
SHSisi He
Sisi He
XWXintong Wu
Xintong Wu
YWYiran Wan
Yiran Wan
CXChenzhuo Xiang
Chenzhuo Xiang
HMHaipeng Mi
Haipeng Mi

13 April 2026
Verified
Conference Paper
Open access
RYRuotong Yu
Ruotong Yu
XWXintong Wu
Xintong Wu
LSLily Sheng
Lily Sheng
ZDZihao Dong
Zihao Dong
YWYuntao Wang
Yuntao Wang
YSYuanchun Shi
Yuanchun Shi

13 April 2026
Verified
Conference Paper
Open access
WDWenjing Deng
Wenjing Deng
ZYZhihao Yao
Zhihao Yao
XKXinhui Kang
Xinhui Kang
QSQirui Sun
Qirui Sun
XWXintong Wu
Xintong Wu
HMHaipeng Mi
Haipeng Mi
Repair is a valuable yet challenging activity, especially when product manuals are missing or outdated. Augmented Reality (AR) has been widely explored for repair tasks, but most systems rely on CAD models or pre-constructed assets, which escalate authoring costs and constrain scalability. We introduce RePairAR, a system that leverages multimodal large language models (MLLMs) to generate interactive AR reassembly guidance derived directly from user-recorded egocentric disassembly videos. RePairAR deduces step-part-relation structures, reverses these for reassembly planning, and delivers the guidance through mixed-media AR visualizations. In a user study with repair novices, RePairAR significantly reduced perceived temporal demand compared to traditional how-to videos. Both media improved self-efficacy, with RePairAR providing greater gains. Follow-up interviews revealed the mechanisms behind these effects. We contribute a validated MLLM-driven pipeline and highlight design implications for scalable, situated support in everyday repair practices.

23 June 2025
Verified
Conference Paper
Open access
WDWenjing Deng
Wenjing Deng
MHMinxuan He
Minxuan He
XWXintong Wu
Xintong Wu
PSPeixi Sheng
Peixi Sheng
SYShuzi Yin
Shuzi Yin
HMHaipeng Mi
Haipeng Mi

13 April 2026
Verified
Conference Paper
Open access
RYRuotong Yu
Ruotong Yu
LSLily Sheng
Lily Sheng
XWXintong Wu
Xintong Wu
JTJiankai Tang
Jiankai Tang
YWYuntao Wang
Yuntao Wang
YSYuanchun Shi
Yuanchun Shi