Jiajun Zhu
Scholar

Jiajun Zhu

Google Scholar ID: mMPLH_kAAAAJ
Zhejiang University
geometric deep learninglarge multimodal modeltrustworthy machine learning
Citations & Impact
All-time
Citations
27
 
H-index
2
 
i10-index
1
 
Publications
5
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Publications:
  • - 'Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding', ICML 2025.
  • - 'Towards Unveiling Sensitive and Decisive Patterns in Explainable AI with a Case Study in Geometric Deep Learning', Nature Machine Intelligence.
Research Experience
  • Currently a PhD student at the University of Texas at Austin, focusing on explainable AI and large language model architectures.
Education
  • PhD: University of Texas at Austin, Advisors: Atlas Wang and Aditya Akella; Bachelor's: Zhejiang University, Major in Mathematics, Minor in Entrepreneurship.
Background
  • Research Interests: Explainable AI, large language model architectures, particularly diffusion language models. Aiming to advance trustworthiness (e.g., robustness, safety, alignment) and efficiency (e.g., MLSys, efficient architectures). Also interested in other cutting-edge technologies such as brain-computer interfaces and blockchain.
Miscellany
  • Aspires to be a compassionate yet influential individual. Besides academic interest in AI, fascinated by the traits of successful entrepreneurs and effective ways to promote social good. Role models include Charlie Munger, Stephen Curry, Jian Li, and many kind and intelligent peers.
Co-authors
0 total
Co-authors: 0 (list not available)