Jingwen Yang

Jingwen Yang

Hong Kong Polytechnic University

✨ Welcome to My Website!

Hi there! 😊 I’m Jingwen Yang (Anita), an upcoming third-year undergraduate at The Hong Kong Polytechnic University, majoring in Data Science & Analytics in the Department of Applied Mathematics and minoring in Computer Science in the Department of Computing. I’m deeply grateful to be advised by Prof. Wanyu Lin and Prof. Hongxia Yang in my research journey.

🔬 Research Interests

  • My previous research experience includes work on an explainable multimodal framework for crystal property prediction and on building low-resource medical MLLMs with robust reasoning evaluation. These projects sparked my passion for tackling the challenges of multimodal learning and model interpretability in real-world scenarios.

  • My current research interests lie in multimodal reasoning, particularly within trustworthy and explainable large language models (LLMs). I’m especially excited about hallucination mitigation, multi-agent cognitive alignment, and the broader goal of human-centered AI.

I’m actively seeking research collaborations or internship opportunities related to multimodal reasoning, LLM alignment, and trustworthy AI. I’d truly appreciate the opportunity to connect, learn, and contribute! 🌷

📩 Get in Touch

I’m genuinely thankful for the mentorship and support I’ve received so far, and always happy to connect with others interested in AI and reasoning 🤍
If you’re open to chatting or collaboration, feel free to contact me via email 📧 jingwen.yang@connect.polyu.hk or add me on WeChat 💬 tiancaiygg666 — I’d truly appreciate the opportunity！

📝 Publications

† indicates corresponding author, * indicates equal contribution

arXiv preprint
Infi-Med teaser

🌟 Infi-Med: Low-Resource Medical MLLMs with Robust Reasoning Evaluation

Zeyu Liu*, Zhitian Hou*, Yining Di, Kejing Yang, Zhijie Sang, Congkai Xie, Jingwen Yang, Siyuan Liu, Jialu Wang, Chunming Li, Ming Li, Hongxia Yang †

• arXiv preprint, 2025    📄 arXiv

A robust and resource-efficient medical MLLM, systematically evaluated across reasoning, grounding, and hallucination dimensions on real-world clinical VQA datasets.

arXiv preprint
Crystal Canonicalization teaser

🔷 Revisiting the Canonicalization for Fast and Accurate Crystal Tensor Property Prediction

Haowei Hua, Jingwen Yang, Wanyu Lin†, Pan Zhou, Ming Yang, Yew-Soon Ong

• arXiv preprint, 2025    📄 arXiv

A polar decomposition-based canonicalization framework (GoeCTP) for O(3)-equivariant crystal tensor property prediction, achieving up to 13× speedup and SOTA accuracy.

💻 Internships

  • Jun 2025 – Aug 2025 · R&D Intern, Nokia
    Shanghai, China

🎖 Honors and Awards

  • Jun 2024 · Dr. Kong Footcare Minyin Hall Scholarship
    (Top 3 GPA among hall residents · Hall Academic Scholarship 2023/24)

  • Sep 2024 · Undergraduate Research and Innovation Scheme (URIS)
    PolyU Research Scholarship 2024/25 [Link]

📖 Education

  • Sep 2023 – Jun 2027 (expected) · BSc (Hons) in Data Science & Analytics, Minor in Computer Science
    The Hong Kong Polytechnic University

  • Jun 2024 – Aug 2024 · Summer Session
    Stanford University