Lucas Here! π
Hi, Iβm Hung-Chun. My research focuses on conversational language models, information retrieval, and multimodal language models. I am interested in language models that hold a conversation, ground their answers in retrieved information, and work across text and images.
π I am actively seeking Ph.D. opportunities in the United States! my resume
Recent Research
LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured
Hung-Chun Hsu, Po-Jen Ko, Che-Cheng Wu, Li-Yang Chang, Chuan-Ju Wang
Yu-Cheng Chang, Guan-Wei Yeo, Quah Eugene, Fan-Jie Shih, Yuan-Ching Kuo, Tsung-En Yu, Hung-Chun Hsu, Ming-Feng Tsai, Chuan-Ju Wang
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
News
- May 2026I presented VLM: From Late Fusion to Early Fusion at the CFDA, CLIP & LKT Labs Joint Laboratory Seminar.
- Apr 2026I presented Dive into Qwen3.5 Key Techniques across three sessions of the CFDA, CLIP & LKT Labs Joint Laboratory Seminar.
- Dec 2025Our team achieved strong results in TREC iKAT 2025: 1st in Offline Generated Response (generation-only), 4th in Online Interactive Response Generation, and 5th in Offline Passage Ranking! See the rankings
- Apr 2024I was fortunate to join the CFDA Lab at Academia Sinica, Taiwan, as a research assistant, working with Prof. Chuan-Ju Wang and Prof. Ming-Feng Tsai.
- Aug 2023I graduated top of my class from the National Taiwan University Data Science M.S. program, with a thesis on imbalanced node classification in heterogeneous graph neural networks! I was fortunate to work with Prof. Chiu-Yu Wang at Academia Sinica and Prof. Che Lin at NTU.