Tianyun Yang
Scholar

Tianyun Yang

Google Scholar ID: 4u_oHeEAAAAJ
Shenzhen Research Institute of Big Data
Mechanistic InterpretabilityLarge Vision-Language ModelAI Safety
Citations & Impact
All-time
Citations
787
 
H-index
8
 
i10-index
6
 
Publications
10
 
Co-authors
9
list available
Resume (English only)
Academic Achievements
  • First-authored paper 'Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention' accepted at ICLR 2025
  • First-authored paper 'Model Synthesis for Zero-shot Model Attribution' published in IEEE Transactions on Multimedia (TMM), 2025
  • First-authored paper 'Pruning for Robust Concept Erasing in Diffusion Models' accepted at NeurIPS 2024 Workshop on Safe Generative AI
  • First-authored paper 'Progressive Open Space Expansion for Open-Set Model Attribution' accepted at CVPR 2023
  • Co-first-authored paper 'Deepfake Network Architecture Attribution' accepted at AAAI 2022
  • First Prize of Academic Award, University of Chinese Academy of Sciences (2022)
  • Director's Excellence Scholarship, Institute of Computing Technology (2021)
  • 1st Prize in Chinese AI Competition, Deepfake Identification (2021)
  • 1st Prize in China Undergraduate Mathematical Contest in Modeling, Hubei Province (2018)
  • Reviewer for top-tier venues including ICML'25, ICLR’25, NeurIPS’24/23/22, CVPR’23, T-MM, TMLR’24