Scholar
Ting-Yao (Edward) Hsu
Google Scholar ID: rewH-4oAAAAJ
TSMC
Citations & Impact
Citations
242
H-index
7
i10-index
6
Publications
15
Co-authors
15
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Paper, 'Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization', accepted by INLG 2023
- - Attending ACL 2023 in Toronto
- - Organizing the Scientific Figure Captioning (SciCap) Challenge, to be hosted at the CLVL workshop at ICCV 2023
Research Experience
- - Final-year Ph.D. candidate working across Vision-to-Language, NLP, and HCI
- - Launched the 1st Scientific Figure Captioning (SciCap) Challenge, inviting AI/NLP/CV researchers to build systems that caption all types of figures in arXiv papers
Education
- - Ph.D. Student, School of Electrical Engineering and Computer Science, Penn State University, Advised by: Dr. Ting-hao (Kenneth) Huang and Dr. C. Lee Giles
- - B.S. in CS, National Tsing Hua University, Worked with Dr. Shang-Hong Lai in CVLAB and Dr. Yuan-Hao Chang (Johnson Chang) at Academia Sinica
Background
- - Research Interests: Vision-to-Language models (VLMs) and large language models (LLMs) for a wide range of downstream applications, with a particular emphasis on improving text generation, refining evaluation methodologies, and exploring post-training techniques
- - Dedicated to developing LLM-based agents that are aligned with human preferences
Miscellany
- - Currently on the job market and looking for full-time industry positions
