the one most critical of the paper, felt that the fundamental method we introduce here (that of constructing explicitly

We also appreciate that the reviewers, especially Reviewer 2, had some concerns with aspects of the papers as well. To each of these points, we'd like to make the following comments: We're happy to include the traditional (e.g., Tanh or LSTM) RNN for comparison, and will add this to the We didn't include Embed2Control-style comparisons, We can include a discussion and illustration of this in the revision. The "simple" model always refers to a simple feedforward network (with the same structure as We'll fully describe the video texture setup in the text (e.g., the source videos are actual videos of physical fire from Thanks for pointing out the confusion here, we'll clarify all of these. However, we'll certainly discuss this point more. We'll include all these details for the experiments (lack of space to desribe them all here).