Date：2025/12/3 14:30-15:30
Location：R103, CSIE
Speakers：Dr. Min-Hung Chen 陳敏弘
Host：羅紹元教授
Abstract:
Artificial Intelligence (AI) is a pivotal research area, with significant interest in how various data modalities (e.g., image, language, speech, etc.) influence AI development. In this talk, Min-Hung will first briefly introduce what the NVIDIA Research Taiwan Lab is doing in overall, and go deeper to introduce his specific research focus including efficient deep learning and video understanding. Finally, Min-Hung will conclude the talk with career opportunities within the team.
Biography:
Min-Hung Chen is currently a Senior Research Scientist at NVIDIA, working on Vision+X Multi-Modal AI. He obtained the Ph.D. degree from Georgia Institute of Technology in 2020. He received his Bachelor's and Master's degrees in 2010 and 2012, respectively, both from National Taiwan University. Before joining NVIDIA, he worked at Microsoft and MediaTek on AI Research for Vision Transformer. Min-Hung's main research interest is Multi-Modal AI, including Vision-Language, Video Understanding, and Efficient Deep Learning. He is also interested in Learning beyond Fully Supervision, including domain adaptation, transfer learning, continual learning, X-supervised learning, etc. Min-Hung has published several papers at top conferences, including CVPR, ICCV, ICML, NeurIPS, etc. He also obtained outstanding reviewer awards and co-organized workshops at various top conferences, such as CVPR, ICCV, and ICML. Finally, Min-Hung also engages in mentoring students for academic collaboration with NTU, NYCU, and NTHU.