Flexible neural representation for physics prediction
Authors: Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F. Fei-Fei, Josh Tenenbaum, Daniel L. Yamins
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we examine the HRN s ability to accurately predict the physical state across time in scenarios with rigid bodies, deformable bodies (soft bodies, cloths, and fluids), collisions, and external actions. We also evaluate the generalization performance across various object and environment properties. Finally, we present some more complex scenarios including (e.g.) falling block towers and dominoes. Prediction roll-outs are generated by recursively feeding back the HRN s one-step prediction as input. We strongly encourage readers to have a look at result examples shown in main text figures, supplementary materials, and at https://youtu.be/k D2U6lghy UE. |
| Researcher Affiliation | Academia | Department of Computer Science1, Psychology2, Electrical Engineering3, Pediatrics4 and Biomedical Data Science5, and Wu Tsai Neurosciences Institute6, Stanford, CA 94305 Department of Brain and Cognitive Sciences7, and Computer Science and Artificial Intelligence Laboratory8, MIT, Cambridge, MA 02139 |
| Pseudocode | Yes | See Algorithm 1 in the supplementary for details. |
| Open Source Code | Yes | HRN code and Unity Fle X environment can be found at https://neuroailab.github.io/physics/ |
| Open Datasets | No | All training data for the below experiments was generated via a custom interactive particle-based environment based on the Fle X physics engine [31] in Unity3D. The paper states the data was generated by the authors and does not provide public access information (link, DOI, citation with authors/year) for this generated dataset. |
| Dataset Splits | No | The paper describes training and testing procedures, but does not explicitly mention a "validation" dataset or how it was split. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU or CPU models, memory, or cloud computing instance types used for the experiments. |
| Software Dependencies | No | All training data for the below experiments was generated via a custom interactive particle-based environment based on the Fle X physics engine [31] in Unity3D. The paper mentions software used (Fle X physics engine, Unity3D) but does not provide specific version numbers for these or other dependencies. |
| Experiment Setup | No | Further details about the experimental setups and training procedure can be found in the supplement. The main text defers these details to supplementary materials and does not include them directly. |