drawing connections to Feldman's work (L36), but we agree that the relation between the three topics should be

Thank you all for your thoughtful comments; we address your concerns below. The MDL principle formalizes Occam's razor and is a We will add the discussion of such relevant studies to section 1. We will add these results and accompanying visualizations to appendix. Model (solver) MAC DAFT MAC (euler) DAFT MAC (rk4) DAFT MAC (dopri5; used in training)Time (ms) 153. We found that during evaluation, rk4 solves all the dynamics generated from CLEVR dataset.