AI Paper Atlas

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

Variational Neural Cellular Automata

Rasmus Berg Palm, Miguel González Duque, Shyam Sudhakaran, Sebastian Risi

ICLR 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 6 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
Use the doubling VNCA decoder instead of the deep convolutional PixelCNN decoderBinarized MNIST · Binarized MNIST testlog likelihood (nats): -84.23 vs -81.3Hurt
Set β=100 to prioritize better samples over reconstructions (ablation)VNCA · CelebA 64×64 testbits per dimension: 4.42 -> 5.40Hurt
Remove doubling layers and train with pool-based damage recovery (ablation)VNCA · MNISTlog likelihood (nats): -84.23 -> -90.97Hurt
Remove doubling layers and train with pool-based damage recovery (ablation)VNCA · CelebA 32×32bits per dimension: 5.03 bits per dimensionHurt
Increase update-network depth or width (ablation)VNCA · VNCA model variationsgenerative modeling performanceNo clear effect
Increase latent-space size to 512 (ablation)VNCA · VNCA model variationsgenerative modeling performanceNo clear effect
Increase NCA hidden-state size to 512 (ablation)VNCA · VNCA model variationsgenerative modeling performanceNo clear effect
Use L=1 rather than L=4 logistic mixture components (ablation)VNCA · VNCA model variationsgenerative modeling performanceImproved
Replace 1×1 convolution layers with 3×3 convolutions (ablation)VNCA · VNCA model variationsgenerative modeling performanceNo clear effect
Use a separate update network at each scale (ablation)VNCA · VNCA model variationsgenerative modeling performanceImproved
Reduce batch size to 4 (ablation)VNCA · VNCA trainingtraining qualityHurt
Replace the update function with a GRU (ablation)VNCA · VNCA model variationsgenerative modeling performanceNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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