Scholar
Hang Hua
Google Scholar ID: K9aLTwUAAAAJ
University of Rochester
Citations & Impact
Citations
714
H-index
13
i10-index
14
Publications
20
Co-authors
18
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'MMComposition: Revisiting the Compositionality of Pre-trained Vision-Language Models' (ArXiv 2024) and 'PROMPTCAP: Prompt-Guided Image Captioning for VQA with GPT-3' (ICCV 2023). Also involved in multiple projects, such as developing new diagnostic benchmarks to assess MLLMs' capabilities and designing new MLLMs with enhanced competencies.
Research Experience
- Currently a research scientist at MIT-IBM Watson AI Lab. Conducted research under the guidance of Prof. Jiebo Luo during his PhD studies at the University of Rochester.
Education
- PhD from the University of Rochester, advised by Prof. Jiebo Luo (Fellow of ACM/AAAI/IEEE/NAI/AIMBE/IAPR/SPIE); Master's degree from Peking University; Bachelor’s degree from South China University of Technology.
Background
- Research Interests: Generative AI, particularly Multimodal LLMs (MLLMs) and Pre-trained Language Models (PLMs). Focuses on addressing core limitations such as Compositionality, Fine-grained Visual Perception, Robustness, and Reasoning.
Miscellany
- Contact: hhua2 [A-T] cs.rochester [D-O-T] edu. Find more information on Google Scholar, GitHub, and LinkedIn.
