Intuitive Physics

NIPS Workshop, 09 December 2016, Barcelona, Spain

Accepted papers

Oral Presentations

Imagination-Based Decision Making with Physical Models in Deep Neural Networks
Jessica B Hamrick, Razvan Pascanu, Oriol Vinyals, Andy Ballard, Nicolas Heess, Peter Battaglia

Deep Visual Foresight for Planning Robot Motion
Chelsea Finn, Sergey Levine

Visual Stability Prediction and Its Application to Manipulation
Wenbin Li, Ales Leonardis, Mario Fritz


A Differentiable Physics Engine for Deep Learning
Jonas Degrave, Joni Dambre, Francis wyffels

Predicting the Dynamics of 2D Objects with a Deep Residual Network
Francois Fleuret

Machine Solver for Physics Word Problems
Megan Leszczynski, Jose Moreira

Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt

Long Term Boundary Extrapolation for Deterministic Motion
Apratim Bhattacharyya, Mateusz Malinowski, Mario Fritz

Rapid Physical Predictions from Convolutional Neural Networks
Filipe de A B Peres, Kevin A Smith, Joshua B Tenenbaum

Probabilistic Simulation Predicts Human Performance on Viscous Fluid-Pouring Problem
James Kubricht, Chenfanfu Jiang, Yixin Zhu, Song-Chun Zhu, Demetri Terzopoulos, Hongjing Lu

A Compositional Object-Based Approach to Learning Physical Dynamics
Michael Chang, Tomer Ullman, Antonio Torralba, and Joshua B Tenenbaum

Extrapolation and Learning Equations
Georg Martius, Christoph H Lampert

Supervised Learning for Controlling Fluids
Zherong Pan, Dinesh Manocha

Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
Ashvin Nair, Pulkit Agrawal, Dian Chen, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine

Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
Russell Stewart, Stefano Ermon

Learning to Perform Physics Experiments via Deep Reinforcement Learning
Misha Denil, Pulkit Agrawal, Tejas Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

A Physically-Grounded and Data-Efficient Approach to Motion Prediction Using Black-Box Optimization
Shaojun Zhu, Abdeslam Boularias