Lucas Here! 👋
Hi, I’m Hung-Chun. I am a senior research assistant at Academia Sinica, Taiwan, working with Prof. Chuan-Ju Wang and Prof. Ming-Feng Tsai. My research interests lie in multimodal LLMs, information retrieval, conversational search, and graph neural networks. Currently, my research centers on developing multimodal LLMs to enable deeper human-AI interaction across diverse modalities and to generate personalized responses from multimodal feedback.
🎓 I received my M.S. in Data Science at National Taiwan University in 2023. During Master’s degree, I was fortunate to work with Prof. Chiu-Yu Wang at Academia Sinica and Prof. Che Lin at NTU.
🚀 I am actively seeking Ph.D. opportunities in the United States! my resume
News
- Dec 2025: Our team achieved strong results in TREC iKAT 2025: 5th in Offline Passage Ranking, 1st in Offline Generated Response (generation-only), and 4th in Online Interactive Response Generation!
- Sep 2025: We release our work in TREC iKAT 2025, “CFDA & CLIP at TREC iKAT 2025: Enhancing Personalized Conversational Search via Query Reformulation and Rank Fusion.”
- Aug 2025: Our paper “Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations” is available on arXiv.
- Aug 2025: We submitted our latest research to the AAAI 2026 main technical track!
- Nov 2024: Our paper “FlashGAN: Framework of Localized Node Augmentation via Semi-supervised Learning in Heterogeneous Graphs with Generative Adversarial Network” is available on arXiv.
- Apr 2024: I completed my Data Scientist R&D Intern position at Cathay Financial Holdings, where I gained valuable experience in building Traditional Chinese RAG pipelines using AWS platform and LangChain framework.
- Feb 2024: Our paper “FincGAN: A Gan Framework of Imbalanced Node Classification on Heterogeneous Graph Neural Network” has been accepted at IEEE ICASSP 2024.
- Aug 2023: I graduated top of my class from National Taiwan University’s Data Science Master program.
- Jul 2023: I successfully defended my master’s thesis titled “A Framework of Imbalanced Node Classification On Heterogeneous Graph Neural Network - Using GAN for Localized Sampling and Node Embedding”.
Publications
FincGAN: A Gan Framework of Imbalanced Node Classification on Heterogeneous Graph Neural Network
Hung-Chun Hsu*, Ting-Le Lin*, Bo-Jun Wu, Ming-Yi Hong, Che Lin, Chih-Yu Wang
In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
FlashGAN: Framework of Localized Node Augmentation via Semi-supervised Learning in Heterogeneous Graphs with Generative Adversarial Network
Hung-Chun Hsu, Bo-Jun Wu, Ming-Yi Hong, Che Lin, Chih-Yu Wang
arXiv preprint arXiv:2312.06519, 2024
Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
Hung-Chun Hsu, Yuan-Ching Kuo, Chao-Han Huck Yang, Szu-Wei Fu, Hanrong Ye, Hongxu Yin, Yu-Chiang Frank Wang, Ming-Feng Tsai, Chuan-Ju Wang
arXiv preprint arXiv:2508.18132, 2025