Zhanpeng Zhou (周展鹏)
Ph.D. candidate in Computer Science at Shanghai Jiao Tong University.
My research interests focus on uncovering nontrivial phenomena that shed light on the underlying mechanisms of Deep Learning.
I am a member of ReThinkLab, Department of Computer Science & Engineering and advised by Prof. Junchi Yan.
Prior than that, I also obtained my Bachelor's Degree in Electrical and Computer Engineering at Shanghai Jiao Tong University.
Email: zzp1012 [at] sjtu.edu.cn  /  1012zzphh [at] gmail.com
CV  / 
Google Scholar  / 
GitHub  / 
|
|
Publications
(* indicates equal contributions; † indicates correspondence.)
|
Going Richer and Sparser: The Learning Dynamics of Label Noise SGD
[arXiv]
Tongcheng Zhang*, Zhanpeng Zhou*†, Mingze Wang, Andi Han, Wei Huang, Taiji Suzuki, Junchi Yan
In Submission
|
On the Role of Label Noise in the Feature Learning Process
[OpenReview]
Andi Han*†, Wei Huang*†, Zhanpeng Zhou*†, Gang Niu, Wuyang Chen, Junchi Yan, Akiko Takeda, Taiji Suzuki
In Submission
|
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
[arXiv]
Jinbo Wang*, Mingze Wang*, Zhanpeng Zhou*, Junchi Yan, Weinan E, Lei Wu
In Submission
|
A Single Global Merging Suffices: Recovering Centralized Learning Performance in Decentralized Learning
[OpenReview]
Tongtian Zhu, Tianyu Zhang, Mingze Wang, Zhanpeng Zhou†, Can Wang
ICLR 2025 Workshop Weight Space Learning
|
On the Cone Effect in the Learning Dynamics
[arXiv]
Zhanpeng Zhou†, Yongyi Yang, Jie Ren, Mahito Sugiyama, Junchi Yan
ICLR 2025 Workshop DeLTa
|
SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
[arXiv]
Zijun Chen*, Zhanpeng Zhou*†, Bo Zhang, Weinan Zhang, Xi Sun, Junchi Yan
IJCNN 2025
|
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
[arXiv]
[GitHub]
[Slides]
Zhanpeng Zhou*†, Mingze Wang*, Yuchen Mao, Bingrui Li, Junchi Yan†
ICLR 2025 (Spotlight)
|
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
[arXiv]
Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen
ICLR 2025 (Spotlight)
|
On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm
[arXiv]
[GitHub]
[Slides]
Zhanpeng Zhou*, Zijun Chen*, Yilan Chen, Bo Zhang, Junchi Yan
ICML 2024
|
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
[arXiv]
[GitHub]
Yiting Chen, Zhanpeng Zhou, Junchi Yan
ICLR 2024
|
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
[arXiv]
[GitHub]
[Slides]
[Post]
Zhanpeng Zhou, Yongyi Yang, Xiaojiang Yang, Junchi Yan, Wei Hu
NeurIPS 2023
|
Defects of Convolutional Decoder Networks in Frequency Representation
[arXiv]
[GitHub]
Ling Tang*, Wen Shen*, Zhanpeng Zhou, Quanshi Zhang
ICML 2023
|
Batch Normalization Is Blind to the First and Second Derivatives of the Loss
[arXiv]
[GitHub]
Zhanpeng Zhou*, Wen Shen*, Huixin Chen*, Ling Tang, Quanshi Zhang
AAAI 2024 (Oral)
|
Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
[arXiv]
[GitHub]
Jie Ren, Zhanpeng Zhou, Qirui Chen, Quanshi Zhang
ICLR 2023
|
A Unified Game-Theoretic Interpretation of Adversarial Robustness
[arXiv]
[Github]
Jie Ren*, Die Zhang*, Yisen Wang*, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, Quanshi Zhang
NeurIPS 2021
|
[2024 Nov. ] National Scholarship (top ~0.2%), Ministry of Education
[2024 Mar. ] Top Internship Evaluation, National Institute of Informatics
[2022 May. ] Outstanding Graduate Student, Shanghai Jiao Tong University
[2021 Nov. ] Yu Liming Scholarship, Shanghai Jiao Tong University
[2020 Nov. ] John Wu & Jane Sun Scholarship, Shanghai Jiao Tong University
[2019 Aug. ] Best Technology Award in Summer Design Expo, Shanghai Jiao Tong University
|
[Conference Reviewer/PC Member] ICML ('22, '24-25), NeurIPS ('22-25), ICLR ('24-25), AISTATS '25
[Journal Reviewer] IEEE T-PAMI, Intelligent Computing (Science Partner)
|
[FA. 2021] Bayesian Analysis (VE414), Teaching Assistant, Shanghai Jiao Tong University.
[SU. 2021] Probabilistic Methods in Eng. (VE401), Teaching Assistant, Shanghai Jiao Tong University.
|
|