NIPS Proceedingsβ

Josh Tenenbaum

24 Papers

  • 3D-Aware Scene Manipulation via Inverse Graphics (2018)
  • End-to-End Differentiable Physics for Learning and Control (2018)
  • Flexible neural representation for physics prediction (2018)
  • Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction (2018)
  • Learning to Exploit Stability for 3D Scene Parsing (2018)
  • Learning to Infer Graphics Programs from Hand-Drawn Images (2018)
  • Learning to Reconstruct Shapes from Unseen Classes (2018)
  • Learning to Share and Hide Intentions using Information Regularization (2018)
  • Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (2018)
  • Visual Object Networks: Image Generation with Disentangled 3D Representations (2018)
  • Learning to See Physics via Visual De-animation (2017)
  • MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017)
  • Self-Supervised Intrinsic Image Decomposition (2017)
  • Shape and Material from Sound (2017)
  • Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (2016)
  • Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (2016)
  • Probing the Compositionality of Intuitive Functions (2016)
  • Sampling for Bayesian Program Learning (2016)
  • Deep Convolutional Inverse Graphics Network (2015)
  • Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning (2015)
  • Softstar: Heuristic-Guided Probabilistic Inference (2015)
  • Unsupervised Learning by Program Synthesis (2015)
  • Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs (2013)
  • One-shot learning by inverting a compositional causal process (2013)