Borui Zhang (张博睿)
About me: I am a final-year Ph.D. candidate at the i-VisionGroup, Department of Automation, Tsinghua University, advised by Prof. Jiwen Lu. I received my B.E. degree from the Department of Automation and a second B.A. degree from the School of Economics and Management at Tsinghua University in 2021. My research philosophy focuses on bridging the gap between theoretical interpretability and practical efficiency in deep learning.
Research: My primary research interests lie at the intersection of Computer Vision and Deep Learning Theory. Currently, I am focused on the following pillars:
-
Explainable AI (XAI):
- Black-box XAI: Axiomatic interpretation & Neural visualization.
- White-box XAI: Concept alignment & White-box architecture design.
-
Neural Network Theory:
- Optimization: Efficient optimization strategies & Convergence analysis.
- Inductive Bias: Frequency bias exploration & Piece-wise linear modeling.
-
Large Multimodal Models:
- Visual tokenizers & Native multimodal architectures.
- Efficient VLM training/inference & GUI Agents.
- Safety alignment & Model interpretability.
Email / Google Scholar / Github / Xiaohongshu / CV