Scholar
Henry Hengyuan Zhao
Google Scholar ID: QLSk-6IAAAAJ
Ph.D. student at National University of Singapore
Citations & Impact
Citations
1,093
H-index
10
i10-index
10
Publications
14
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models via Human Feedback' accepted to EMNLP 2025 Findings and presented at ICLR 2025 Bi-Align Workshop (Oral).
- Paper 'WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point' accepted to ACL 2025 @ REALM Workshop.
- Paper 'LOVA3: Learning to Visual Question Answering, Asking and Assessment' accepted to NeurIPS 2024.
- Paper 'Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator' accepted to ECCV 2024.
- Paper 'SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels' accepted to IJCV 2023.
- Paper 'Evaluating the Generalization Ability of Super-Resolution Networks' accepted to TPAMI 2023.
- Paper 'ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic' accepted to CVPR 2021.
- Paper 'Efficient Image Super-Resolution Using Pixel Attention' accepted to ECCVW 2020, with over 400 citations.
Research Experience
- Involved in multiple research projects such as WorldGUI, Genixer, LOVA3, and InterFeedback.
Education
- PhD - National University of Singapore, Advisor: Prof. Mike Zheng Shou
Background
- PhD student in the Show Lab at the National University of Singapore, advised by Prof. Mike Zheng Shou. Research interests include training Large Multimodal Models (LMMs) and developing agents/benchmarks for GUI automation and chart-to-code.
Miscellany
- Personal interests not mentioned
