Journal Club

A cumulative seminar archive for in-semester paper discussions on uncertainty quantification, scientific machine learning, and related statistical methodology.

  1. From EHVI to Diffusion Models: Pareto Set Learning for Expensive Multi-Objective Bayesian Optimization

    Dayeon YoonJun 16, 2026

    Multi-objective Bayesian optimization (MOBO) is a framework for expensive black-box problems with multiple competing objectives, where each evaluation may require costly simulations or experiments.

    Open Session
  2. FourCastNet: a weather forcasting model using Neural Operators

    Jikwang KimJun 1, 2026

    FourCastNet 1 casts global weather forecasting as a learned, resolution-invariant neural operator: an Adaptive Fourier Neural Operator (AFNO) with a ViT backbone, trained on ERA5 at 0.250.25^\circ and rolled out autoregressively.

    Open Session
  3. An Introduction to PINNs and Their Convergence

    Yoonseo ChoiMay 18, 2026

    Physics-Informed Neural Networks (PINNs) are a framework for approximating partial differential equation (PDE) solutions by embedding governing physical laws directly into the neural network’s loss function via automatic differentiation.

    Open Session
  4. Tabular Foundation Models - From Tree-based Methods to TabPFN

    Sungwoo ParkMay 4, 2026

    From GBDTs to TabPFN: how deep learning finally started to competing on tabular data through in-context-learning foundation models, and where this new paradigm still breaks.

    Open Session
  5. Marginal Tail-Adaptive Normalizing Flows

    Juyoung HwangApr 20, 2026

    TBA

    Open Session
  6. Uncertainty Quantification in Vision Transformer

    Gunwoo ChoApr 6, 2026

    Likelihood-guided Regularization in Attention Based Models.

    Open Session
  7. Introduction to Flow Matching

    Heejoon ByunMar 23, 2026

    Flow matching is a framework for generative modeling that learns a vector field transporting a simple reference distribution to a complex target via an ODE.

    Open Session