Lanjun Wang bio photo

Researcher/Doctoral Supervisor, Tianjin University

Email

Google Scholar

About Me

Lanjun received her Ph.D. in Electronic Engineering from Tsinghua University in 2011, and in the same year, she joined IBM Research-China. Before that, she was a member of Academic Talent Program 2001 at Tsinghua University and received B.S. degree in Math and Physics in 2005. After 10 year working in the industry, Lanjun was back to academia in 2021. Now she is a Researcher and Doctoral Supervisor at the School of New Media and Communication, Tianjin University.

Her scholarly pursuits are anchored in the realm of Responsible Artificial Intelligence. Lanjun is committed to crafting interpretable, robust, fair, privacy-preserving, and transparent artificial intelligence systems. Additionally, she delves into the realm of data valuation and pricing, aiming to harness data as a pivotal factor of production.

[Recruiting]: Looking for prospective PhD students and Master students (enroll in 2026). Ideal candidates are expected to be responsible, organized, and creative. Strong programming skills, solid mathematics knowledge as well as good communication skills are preferred. Please send your CV, Transcript and a brief Summary of your experience (in email) to wanglanjun AT tju.edu.cn.

[NOTE]: So far I do not have any plan on supervising foreign students funded by Chinese Government Scholarship.

Work Experience

  • 2021.10-Present: Tianjin University, Researcher/Doctoral Supervisor
  • 2017.5-2021.10: Huawei Technologies, Technical Expert
  • 2016.2-2017.5: University of Waterloo, Postdoctoral Research Fellow
  • 2011.7-2016.1: IBM Research-China, Research Staff Member

Education Experience

  • 2005-2011: Tsinghua University, EE, PhD
  • 2001-2005: Tsinghua University, Math & Physics, B.S.
  • 2008-2009: University of California, Berkeley, Visiting student

News

  • Mar 21, 2025: Our paper Culture-based Adversarial Attack on Text-to-Image Models is accepted by ICME (CCF-B). Congrats to Fuyi and Chenyu! This study is to jailbreak T2I models by leveraging cultural knowledge.
  • Mar 5, 2025: Our paper Few-Shot In-Context Learning for Implicit Semantic Multimodal Content Detection and Interpretation is accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, JCR:Q1). Congrats to Xiuxian. This study is about hateful memes detection.
  • Jan 6, 2025: Our paper MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining is accepted by IEEE Transactions on Multimedia (TMM, JCR:Q1). Congrats to Guokai! This is our first paper on generation watermark.
  • Dec 21, 2024: Our paper Aesthetic Perception Prompting for Interpretable Image Aesthetics Assessment with MLLMs is accepted by ICASSP’25 (CCF-B). Appreciate supports from Meituan.
  • Dec 10, 2024: Collaborated paper Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation is accepted by AAAI’25 (CCF-A). Congrats to Zili and his team.
  • Nov 30, 2024: Talk on Vulnerability Pattern of Text-to-Image Diffusion Models (文生图模型鲁棒性缺陷模式挖掘) at CIPS-LMG’24 in Jiaxing. [Link]
  • Sept 13, 2024: Our paper Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey is accepted by Information Fusion (JCR:Q1). Congrats to Chenyu. [Link]
  • July 26, 2024: Talk on Multimedia Information Propagation Control with Social Bots（基于社交机器人的多媒体传播安全可控） at ChinaMM’24 in Yinchuan. [Slides]
  • July 16, 2024: Our paper Bots Shield Fake News: Adversarial Attack on User Engagement based Fake News Detection is accepted by CIKM (CCF-B). Congrats to Zehao! Appreciate supports from SMP-IDATA Open Youth Fund.
  • May 26, 2024: Talk on Review on the progress of the AIGC visual content generation and traceability (AIGC视觉内容生成与溯源研究进展) at CSIG’24 in Xi’an. [Link] [Slides]
  • May 17, 2024: Our paper Certified Robustness on Visual Graph Matching via Searching Optimal Smoothing Range is accepted by KDD (CCF-A). Congrats to Huaqing!
  • Mar 25, 2024: Our paper Toward Chinese Food Understanding: a Cross-Modal Ingredient-Level Benchmark is accepted by IEEE Transactions on Multimedia (TMM, JCR:Q1). Congrats to Chenyu and the team! Appreciate supports from Meituan.
  • Mar 13, 2024: Our paper Rumor Detection Framework Based on Multi-source Knowledge Adaptation is accepted by ICME (CCF-B). Congrats to Jingqiu! This is an upgraded version on her previous study (MM’23).
  • Feb 27, 2024: Our paper AnyScene: Customized Image Synthesis with Composited Foreground is accepted by CVPR (CCF-A). Congrats to Ruidong! This is our first paper on controlable image generation.
  • Feb 24, 2024: Our paper MCDAN: a Multi-scale Context-enhanced Dynamic Attention Network for Diffusion Prediction is accepted by IEEE Transactions on Multimedia (TMM, JCR:Q1). Congrats to Xiaowen! This is our first paper on information diffusion prediction.