Scholar
Borui Zhang
Google Scholar ID: MUN3ZNgAAAAJ
Ph.D. student, Tsinghua University
Citations & Impact
Citations
408
H-index
8
i10-index
7
Publications
12
Co-authors
0
Publications
Resume
Academic Achievements
- Published papers include:
- - 2024-07: One paper on autonomous driving accepted to ECCV 2024.
- - 2024-04: One paper on salient object detection accepted to TGRS 2024.
- - 2024-02: Two papers on autonomous driving accepted to CVPR 2024.
- - 2024-01: One paper on explainable deep networks accepted to ICLR 2024.
- - 2023-01: One paper on explainable deep networks accepted to ICLR 2023.
- - 2022-07: One paper on dynamic metric learning accepted to ECCV 2022.
- - 2022-03: One paper on explainable metric learning accepted to CVPR 2022.
- - 2021-07: One paper on deep metric learning accepted to ICCV 2021.
- Preprints:
- - Preventing Local Pitfalls in Vector Quantization via Optimal Transport
- - Exploring Unified Perspective For Fast Shapley Value Estimation
- Selected publications:
- - Path Choice Matters for Clear Attribution in Path Methods
- - Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
Research Experience
- During his Ph.D., he mainly focused on research in explainable AI, neural network theory, and large multimodal models.
Education
- Earned BE degree from the Department of Automation and a second BA degree from the School of Economics and Management at Tsinghua University in 2021.
Background
- Research interests span across computer vision and deep learning theory. Specifically, explainable AI (black-box XAI: axiomatic interpretation, neural visualization; white-box XAI: concept alignment, white-box architecture), neural network theory (optimization: efficient optimization, convergence analysis; inductive bias: frequency bias, piece-wise linear model), and large multimodal models (visual tokenizer, native multimodal model, GUI agent, efficient VLM, safety & alignment). Currently a final-year Ph.D. student in the i-VisionGroup at the Department of Automation, Tsinghua University, under the guidance of Professor Jiwen Lu.
Miscellany
- Personal website: https://skylerhallinan.com/. Contact information available through email, Google Scholar, GitHub, Xiaohongshu, etc.