Publications

  • GPT-4 Technical Report
    OpenAI
    arXiv, 2023
      [paper]

  • Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
    Filipe de Avila Belbute-Peres, J. Zico Kolter
    ICLR 2023
      [paper]

  • HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
    Filipe de Avila Belbute-Peres, Yifan Chen, Fei Sha
    Symbiosis of Deep Learning and Differential Equations Workshop, NeurIPS 2021 (Spotlight)
      [paper]

  • Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
    Filipe de Avila Belbute-Peres, Thomas D. Economon, J. Zico Kolter
    ICML 2020
      [paper]   [code]

  • Assessing the similarity of cortical object and scene representations through cross-validated voxel encoding models
    Nicholas M Blauch, Filipe de Avila Belbute-Peres, Juhi Farooqui, Alireza Chaman Zar, David Plaut, Marlene Behrmann
    Journal of Vision
      [poster]   [link]

  • End-to-End Differentiable Physics for Learning and Control
    Filipe de Avila Belbute-Peres, Kevin Smith, Kelsey Allen, Josh Tenenbaum, J. Zico Kolter
    NeurIPS 2018 (Spotlight)
    [paper]   [code]

  • A Modular Differentiable Rigid Body Physics Engine
    Filipe de Avila Belbute-Peres, J. Zico Kolter
    Deep Reinforcement Learning Symposium, NIPS 2017
    [paper]   [code]

  • Thinking inside the box: Motion prediction in contained spaces uses simulation
    Kevin A. Smith, Filipe de Avila Belbute-Peres, Edward Vul, Joshua B. Tenenbaum
    CogSci 2017
    [paper]   [poster]