Scholar
Yiming Huang
Google Scholar ID: E4Blpr8AAAAJ
M.Phil. student@HKUST(GZ)
Citations & Impact
Citations
38
H-index
3
i10-index
2
Publications
9
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Co-first authored paper “Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?” accepted by Findings of EMNLP '25
- Collaborative work “MSV-PCT” accepted by AAAI '25
- Paper “SDformer” accepted by IJCAI '24
- Undergraduate representative work “Generic Attention-model Explainability by Weighted Relevance Accumulation” published at MMAsia '23
- Accepted into the Red Bird Master of Philosophy Program at HKUST(GZ) in May 2024
Background
- Research interests focus on Trustworthy AI
- Long-term goal is to analyze and control state-of-the-art AI algorithms, models, and systems
- Specifically exploring interpretability, robustness, granularity, and generalizability of AI to address explainability (XAI), safety, privacy, fairness, refined controllability, and human-interactivity
- Currently working on mechanistic interpretability for safe AI and societal AI
- Actively seeking Ph.D. positions for Fall 2026, Spring 2027, or Fall 2027
