About Me(CV)
Hello! I am Jing Lu, a Research Assistant at The University of Hong Kong. My research intersects large language models (LLMs), computer vision, and societal impacts, with a focus on social media and fairness evaluation.
Experiences
Education
- The University of Hong Kong
Master in AI, Ethics and Society (STEM), Sep 2023 – Nov 2024 - Beijing Normal University
B.S. in Computer Science and Technology, Sep 2017 – June 2019
B.A. in Communication (Minor in Computer Science), Sep 2019 – June 2022
Research Experience
- AI Research Assistant, Urban Big Data Lab, The University of Hong Kong
Dec 2024 – Jun 2025
Conducted 5+ studies on LLMs and engineering applications, leading benchmarking research comparing zero-shot vision-language models with computer vision methods for construction waste recognition. Optimized models via fine-tuning. - Data and Governance Research Assistant, Tsinghua University
Aug 2022 – Jul 2023
Contributed to 10+ policy studies using text classification, semantic segmentation, and BERT-based sentiment analysis to evaluate government responsiveness during COVID-19. Co-translated Text as Data.
Programming & Engineering
Benchmarking Large Language Models and Computer Vision for Automated Construction Waste Recognition & The Impacts of Inputting Data on Visual-Language Models in Automated Construction Waste Recognition (HKU)
Primarily utilized API techniques, prompt engineering, and few-shot techniques to evaluate the potential of LLM/LVM in image recognition tasks.
Developing a LLM for Social Science Research (Oxford)
Primarily employed fine-tuning and RAG on social science databases (WVS and ESS mapping), comparing the trained model against its default aligned equivalent.
Official Media as Emotional Valves: How Official Media Guides Nationalism on Chinese Social Media
Contributed to research by utilizing supervised text classification and topic models, along with BERT-based sentiment analysis, evaluating the government’s responsiveness to citizen complaints during the COVID-19 pandemic.
Topics and Sentiment Analysis of International Communication Related to Chinese Handicrafts on TikTok
As an early adopter of data collection via the TikTok API and web scraping techniques, I conducted research in 2022 when academic studies on the TikTok platform were still scarce. I employed the VADER and LDA models to investigate sentiment polarization and dynamic topic distribution.
Benchmarking Large Language Models and Computer Vision for Automated Construction Waste Recognition
Benchmarked computer vision models trained with CNN, Attention, and Transformer on 500 labeled waste disposal images, achieving model accuracy above 90.40%.
China Artificial Intelligence and Future Media Innovation and Entrepreneurship Competition
Created a smart health monitoring system with wearable health units using foot pressure and heart rate analysis models based on MobileNet and CNN deep learning models, secured a grant of $1,400.
Hong Kong Housing Authority Android App: e-InStar
Independently developed an app using the Flutter framework, deployed for practical use by over 10,000 users in Hong Kong’s engineering industry. The app implements NFC communication, QR code scanning for uploading on-site report images and engineering reports, and real-time collaboration features for multiple user groups to review project progress based on uploaded images.
Mitigating or Exacerbating Polarization? An Intervention Study on Alleviating Online Misogyny Through Generative AI Dialogues
Completed a Master’s dissertation developing a conversational AI model and integrating an Internalized Misogyny Scale to measure participants’ misogyny levels through an online controlled experiment. Created an AI chat assistant using the GPT-4 API within a Flutter app, hosted on Tencent Cloud with Firebase for data storage, aimed at mitigating misogyny in conversations.
National First Prize(1st/800 teams)2021 China Data Journalism Competition：They Tried to Melt an Iceberg
This project is a self-developed and coded(with HTML/CSS/JavaScript/D3.js) data journalism piece that combines
dynamic visualization with in-depth reporting to bring to light the situation of rare diseases, much like an iceberg.
The output of this project can be viewed at RareDisease .
Publications
[1] The Impacts of Inputting Data on Visual-Language Models in Automated Construction Waste Recognition
J Chen, W Lu, Jing Lu (Student First Author), Y Zhang, Z Dong, B Yang, Z Peng, and L Yuan
Under Review, Resources, Conservation & Recycling, SCI Q1
[Preprint PDF] (Draft version, under review)
[2] Benchmarking Large Language Models and Computer Vision for Automated Construction Waste Recognition
W Lu, Z Dong, Jing Lu, J Chen, L Yuan, B Yang, Z Peng, and Y Zhang
Under Review, Environmental Impact Assessment Review, SCI Q1
[Preprint PDF] (Draft version, under review)
[3] Domain-Specific Fine-Tuning of Vision-Language Models for Waste Composition Recognition
Jing Lu
Manuscripts in Preparation
[C1] Exploring Large Language Models for Automated Recognition of Construction Waste Composition
J Chen, Z Dong, Jing Lu
20th International Symposium on Waste Management, Italy, Oct. 2025
[C2] Competing in Shopping Games: Modelling Gamification Effects of Social Livestreaming Shopping and Chinese Undergraduates’ Impulsive Buying
Jing Lu, Y Zhu
American Association for Education in Journalism and Mass Communication (AEJMC), Virtual, Aug. 2021
[Preprint PDF]
Honors and Awards
- National First Prize, 6th China Data Journalism Competition (1st/800 teams), 2021
- Oxford LLM Workshop Grant ($600), 2024
- Microsoft Research Asia Grant ($28,000), 2023
- Honorable Mention, American ICM Contest, 2021
Academic Activities
- Oxford Large Language Models Workshop, 2024 (1 of 30 global participants)
- Summer Institute of Computational Social Science (SICSS) Iceland, 2024 (1 of 20 global researchers)
Professional Experience
- Full Stack Developer Intern, Inclusive Business Lab & Foundation（Hong Kong Tech Start-up）
Jul 2024 – Sep 2024
Developed 20+ web pages using React.js and AWS Amplify for an NGO. - Digital Marketing Intern, FansWiFi（Hong Kong Tech Start-up）
May 2024 – Jul 2024
Created 100+ marketing materials with generative AI, enhancing ESG visibility.
Contact
📧Email: jinglu0@outlook.com
💡Don't hesitate to connect me in LinkedIn | GitHub | Twitter