AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling

Naoya Takeishi, Alexandros Kalousis

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Regularizing VAE latent information · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Pendulum testinferred ω MAE: 1.04 -> 0.229Improved
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Advection-diffusion testinferred a MAE: 0.258 -> 0.00951Improved
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Pendulum testreconstruction MAE: 0.370 -> 0.363Improved
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Advection-diffusion testreconstruction MAE: 0.0404 -> 0.0437Hurt
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Human gait testreconstruction error: 0.273 -> 0.259Improved
Add the PPC regularizer (α) (ablation)NN+phys+reg · Pendulum and advection-diffusion testinference MAE: 0.889 -> 0.229; 0.0444 -> 0.00951Improved
Add the physics data-augmentation regularizer R_DA,1 (β) (ablation)NN+phys+reg · Pendulum and advection-diffusion testinference MAE: 0.223 -> 0.229; 0.199 -> 0.00951Improved
Add the physics data-augmentation regularizer R_DA,2 (γ) (ablation)NN+phys+reg · Pendulum and advection-diffusion testinference MAE: 0.276 -> 0.229; 0.0548 -> 0.00951Improved
Add the full physics-integrated VAE regularizersPhysics-integrated VAE · Galaxy10 Disk, Edge-on, No Bulgequalitative generation realismImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy