01

About me

Sipeng Chen

I am a Ph.D. student in Computer Science at Florida State University. I received my bachelor's degree from Nanjing University of Posts and Telecommunications and my master's degree from Florida International University, both in Electrical Engineering.

My research interests center on how machine learning represents functions and models probability distributions, especially in computer vision. I am particularly interested in generative modeling, implicit neural representations, and the mathematical ideas behind representation learning and optimization. I enjoy connecting intuition with practical experiments to understand how learning algorithms work.

02

News

  1. I am an invited reviewer for the ICLR 2027 Conference.

  2. My first-authored paper, “Closing the Capacity–Convergence Gap: Globally Optimal Configuration of Implicit Neural Representations,” has been accepted at ECCV 2026.

  3. My co-authored paper, “Uncovering Insights of Compound Flooding with Data-Driven AI,” has been accepted at KDD 2026, AI for Sciences Track.

  4. My co-authored paper, “Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes,” has been accepted at ICML 2026.

  5. My first-authored paper, “Adaptive Dice Loss for Extremely Imbalanced Segmentation in Wetland Delineation,” has been accepted at the ICLR 2025 Workshop on Tackling Climate Change with Machine Learning.

03

Selected
publications

  1. Preprint2026

    Refresh or Realize? Compute Allocation in Drifting Models

    Sipeng Chen, Xu Zheng, Shibo Li

    arXivPDF
  2. ECCV 20262026

    Closing the Capacity–Convergence Gap: Globally Optimal Configuration of Implicit Neural Representations

    Sipeng Chen, Yan Zhang, Shibo Li

    arXivPDFCode
  3. ICML 20262026

    Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes

    Yan Zhang, Xuefeng Liu, Sipeng Chen, Sascha Ranftl, Chong Liu, Shibo Li

    ProceedingsarXivCode
  4. KDD 2026 · AI for Sciences2026

    Uncovering Insights of Compound Flooding with Data-Driven AI

    Xu Zheng, Chaohao Lin, Sipeng Chen, Zhuomin Chen, Jimeng Shi, Jayantha Obeysekera, Jingchao Ni, Wei Cheng, Jason Liu, Dongsheng Luo

    Earlier version: SF²Bench: Evaluating Data-Driven Models for Compound Flood Forecasting in South Florida.

    ProceedingsarXivPDF
  5. Preprint2026

    Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions

    Sipeng Chen, Junliang Liu, Hewei Tang, Shibo Li

    arXivPDF
  6. Preprint2025 / 2026

    LM²otifs: An Explainable Framework for Machine-Generated Texts Detection

    Xu Zheng, Zhuomin Chen, Esteban Schafir, Sipeng Chen, Hojat Allah Salehi, Haifeng Chen, Farhad Shirani, Wei Cheng, Dongsheng Luo

    Latest version: Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework (2026).

    Latest versionOriginal PDF
  7. ICLR 2025 Workshop · Climate Change ML2025

    Adaptive Dice Loss for Extremely Imbalanced Segmentation in Wetland Delineation

    Sipeng Chen, Xu Zheng, Zeda Yin, Qiang Chen, Yuepeng Li, Jason Liu, Dongsheng Luo

    Paper & poster