Scholar

Hui Jin

Google Scholar ID: eicCkOkAAAAJ

Bytedance

Large Language ModelMachine learningOptimization

Citations & Impact

All-time

Citations

165

H-index

i10-index

Publications

Co-authors

Contact

Resume

Academic Achievements

Paper: 'Towards understanding how transformer perform multi-step reasoning with matching operation', Authors: Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu, Submitted to ICML 2025.
Paper: 'Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers', Authors: Brian K Chen, Tianyang Hu, Hui Jin, Hwee Kuan Lee, Kenji Kawaguchi, Published in ICML 2024.
Paper: 'How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training', Authors: Yixin Ou, Yunzhi Yao, Ningyu Zhang, Hui Jin, Jiacheng Sun, Shumin Deng, Zhenguo Li, Huajun Chen, Submitted to ACL 2025.
Paper: 'Characterizing the Spectrum of the NTK via a Power Series Expansion', Authors: Michael Murray, Hui Jin, Benjamin Bowman, Guido Montufar, Published in ICLR 2023.
Paper: 'Learning curves for Gaussian process regression with power-law priors and targets', Authors: Hui Jin, Pradeep Kr Banerjee, Guido Montúfar, Published in ICLR 2022.
Paper: 'Implicit bias of gradient descent for mean squared error regression with wide neural networks', Authors: Hui Jin, Guido Montúfar, Published in JMLR 2023.
Paper: 'Noisy Subgraph Isomorphisms on Multiplex Networks', Authors: Hui Jin, Xie He, Yanghui Wang, Hao Li, Andrea L Bertozzi, Published in IEEE Big Data 2019.

Background

Currently an AI researcher at Huawei Noah’s Ark Lab. Research interests mainly focus on Large Language Models, Mechanistic Interpretability, and Deep Learning Theory.

Miscellany