AI Paper Atlas

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

Navigating the Latent Space Dynamics of Neural Models

Marco Fumero, Luca Moschella, Emanuele Rodolà, Francesco Locatello

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hierarchical VAEs and posterior collapse

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
score OOD by latent trajectory distance to training attractors instead of KNN on featuresViT-MAE OOD detection · iNaturalistFPR95: 86.40 -> 29.90Improved
score OOD by trajectory distance to attractors instead of MahalanobisViT-MAE OOD detection · TextureFPR95: 43.00 -> 25.90Improved
use attractor trajectory score instead of reconstruction errorViT-MAE OOD detection · SUN397AUROC: 49.50 -> 91.20Improved
increase bottleneck dimension k from 2 to 16 (stronger regularization) (ablation)convolutional AEs · MNIST/CIFAR/FashionMNISTmemorization vs test errorMixed
use noise-derived attractors as dictionary instead of random orthonormal basisStable Diffusion AE · six datasets OMP reconstructionMSEImproved
train longer (ablation)AE k=128 on MNIST · memorization coefficient vs test errormemorization / test errorMixed

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