AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Controllable and Compositional Generation with Latent-Space Energy-Based Models

Weili Nie, Arash Vahdat, Anima Anandkumar

NeurIPS 2021 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 20 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 ODE sampler in latent space instead of LD sampler (needs fewer steps at similar quality) (ablation)LACE · CIFAR-10 hyperparameter gridmin average steps for ACC>=95%, FID<=10: 200 -> 41.8Improved
use ODE sampler instead of LD sampler (best tuned performance) (ablation)LACE · CIFAR-10ACC-FID trade-offNo clear effect
use ODE sampler instead of PC sampler (ablation)LACE · FFHQ glassesACC (glasses): 0.943 -> 0.998Improved
train classifier in w-space rather than z-space or pixel space (ablation)LACE · CIFAR-10ACC/FIDImproved
use first-order Euler solver instead of adaptive dopri5 (ablation)LACE-ODE · CIFAR-10ACC/FIDHurt
LACE-ODE latent EBM vs StyleFlowFFHQ sequential editing · FFHQ yaw_smile_age_glassesDES: 0.569 -> 0.735Improved
LACE-ODE vs StyleFlow on unseen attribute combinationsFFHQ zero-shot · FFHQ zero-shot (b) smileACC: 0.408 -> 0.906Improved
LACE-ODE vs StyleFlow on image qualityFFHQ glasses · FFHQ glassesFID: 43.55 -> 24.52Improved

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