AI Paper Atlas

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

[Re] Variational Neural Cellular Automata

Albert Sund Aillet, Simon Sondén

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Amortized and online variational inference

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
Use doubling NCA decoder instead of non-doubling variant (ablation)VNCA · Binarized MNISTlog p(x) (nats): -90.97 -> -84.23Improved
Use doubling NCA decoder instead of non-doubling variant (ablation)VNCA · CelebAbits per dimension: 5.03 -> 4.42Improved
Increase KL weight beta from 1 to 100 (ablation)VNCA · CelebAbits per dimension: 4.42 -> 5.40Mixed
Pool and damage recovery training with non-doubling VNCAVNCA · MNIST damage recoveryrecovery from damageImproved
Replace VNCA decoder with deep convolutional VAE decoder (ablation)VNCA · CelebA damage during growthdamage recoveryNo clear effect
Deeper (up to 8 residual layers) and wider (512) update network (ablation)VNCA · generative modelinglikelihoodNo clear effect
Latent size 512 and NCA hidden state 512 (ablation)VNCA · generative modelinglikelihoodNo clear effect
Use L=4 logistic mixtures instead of L=1 (ablation)VNCA · generative modelinglikelihoodHurt
Replace 1x1 convolutions with 3x3 (ablation)VNCA · generative modelinglikelihoodNo clear effect
Separate update network per scale (K networks) (ablation)VNCA · generative modelinglikelihoodNo clear effect
Increase batch size (batch 4 vs 32) (ablation)VNCA · trainingtrainabilityImproved
Use GRU update, gated residual update, or half-frozen hidden state (ablation)VNCA · generative modelinglikelihoodNo clear effect

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