Yiting Chen

myself.jpg

sjtucyt@sjtu.edu.cn

Shanghai, China

I am a fourth-year Ph.D. candidate in Computer Science at Shanghai Jiao Tong University. I am very fortunate to be advised by Prof. Junchi Yan. Prior to that, I received my bachelor degree in Computer Science and Engineering at Shanghai Jiao Tong University.

My research interests lie in exploring the underlying mechanisms of deep learning to uncover the fundamental principles that govern model behavior. I am particularly focused on promoting the efficiency of deep neural networks by developing innovative methodologies that enhance interpretability and reduce computational costs. Through a phenomenon-driven approach, I aim to bridge the gap between theoretical insights and practical applications, ultimately contributing to the advancement of robust and efficient AI systems.

I welcome discussions with fellow researchers, practitioners, and anyone interested in deep learning and AI. Please feel free to reach out if you would like to exchange ideas.

news

Sep 26, 2024 Two papers are accepted by NeurIPS 2024!
May 02, 2024 One paper is accepted by ICML2024!
Jan 16, 2024 One paper is accepted by ICLR2024!
Jan 23, 2023 Two papers are accepted by ICLR2023!
Sep 15, 2022 One paper is accepted by NeurIPS2022 (spotlight)!

selected publications

  1. paper_shapley.png
    Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
    Yiting Chen, Qibing Ren, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2022
  2. paper_rope.png
    What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
    Yiting Chen, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
  3. paper_matthew.jpg
    Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
    Yiting Chen, Jiazi Bu, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
  4. paper_going.png
    Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
    Yiting Chen, Zhanpeng Zhou, and Junchi Yan
    In International Conference on Learning Representations (ICLR), 2024