Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Causal Discovery in Physical Systems from Videos

Authors: Yunzhu Li, Antonio Torralba, Anima Anandkumar, Dieter Fox, Animesh Garg

NeurIPS 2020 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that our model can correctly identify the interactions from a short sequence of images and make long-term future predictions.
Researcher Affiliation Collaboration Yunzhu Li MIT CSAIL EMAIL Antonio Torralba MIT CSAIL EMAIL Animashree Anandkumar Caltech, Nvidia EMAIL Dieter Fox University of Washington, Nvidia EMAIL Animesh Garg University of Toronto, Vector Institute, Nvidia EMAIL
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper provides a link to a project page (https://yunzhuli.github.io/V-CDN/) for additional results, but not explicitly to the source code for the methodology. The project page is considered a demonstration/overview page, not a direct code repository.
Open Datasets No The paper describes experiments conducted in custom-built environments (Multi-Body Interaction, Fabric Manipulation) and does not provide concrete access information or citations for publicly available datasets.
Dataset Splits No The paper mentions using 'training set' and 'test set' but does not provide specific details on dataset splits (e.g., percentages, sample counts, or references to predefined splits).
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for the experiments.
Software Dependencies No The paper mentions software components and techniques like "graph neural networks" and "Gumbel-Softmax" but does not list specific software names with version numbers.
Experiment Setup No The paper mentions general training aspects like using reconstruction loss and stochastic gradient descent but does not provide specific hyperparameters such as learning rate, batch size, or number of epochs.