Qiang Huang
Scholar

Qiang Huang

Google Scholar ID: y7q6ZxUAAAAJ
Harbin Institute of Technology (Shenzhen)
DatabasesSimilarity SearchMachine LearningNatural Language Processing
Citations & Impact
All-time
Citations
644
 
H-index
12
 
i10-index
14
 
Publications
20
 
Co-authors
17
list available
Resume (English only)
Academic Achievements
  • - Publications:
  • - 'Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning', AAAI 2026, Oral
  • - 'Partially Shared Concept Bottleneck Models', AAAI 2026
  • - 'A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone', NeurIPS 2025, Spotlight
  • - 'CMS-VAE: A Strategy-aware Variational AutoEncoder for High-Fidelity Crypto Market Simulation', NeurIPS 2025 Workshop
  • - 'CTBench: Cryptocurrency Time Series Generation Benchmark', NeurIPS 2025 Workshop
Research Experience
  • - Senior Research Fellow: School of Computing, National University of Singapore (NUS), working with Prof. Anthony K. H. Tung
  • - Member: NUS Artificial Intelligence Institute (NAII) and Centre for Trusted Internet and Community (CTIC)
Education
  • - B.Eng.: School of Computer Science and Engineering, Sun Yat-sen University, 2012, Advisor: Prof. Jianlin Feng
  • - Ph.D.: School of Computer Science and Engineering, Sun Yat-sen University, 2017, Advisor: Prof. Jianlin Feng
  • - Research Intern: School of Computer Science, University of Birmingham, Nov 2011 - May 2012, Advisor: Assoc. Prof. Shan He
Background
  • - Research Interests: Retrieval-Augmented Generation (RAG), Semantic Understanding and Embedding (SUE), Time Series Generation (TSG)
  • - Position: Professor at the School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen)
  • - Biography: Focuses on integrating large-scale retrieval systems with multimodal large models to improve generation quality and efficiency; develops effective semantic representations to support retrieval, recommendation, and generation; studies generative AI in low-resource scenarios for time series generation.