AI Paper Atlas

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

SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows

Qinyu Zhao, Guangting Zheng, Tao Yang, Rui Zhu, Xingjian Leng, Stephen Gould, Liang Zheng

ECCV 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hierarchical VAEs and posterior collapse · 8 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
make VAE encoder trainable (end-to-end) with fixed variance instead of frozen VAE (ablation)SimFlow · Variant study (80 epochs, gFID without CFG)gFID: 67.41 -> 16.97Improved
train end-to-end with noise augmentation instead of frozen encoder (ablation)NF with noise augmentation · Variant study (80 epochs, gFID without CFG)gFID: 39.33 -> 20.01Improved
fix variance instead of noise augmentation under end-to-end training (ablation)SimFlow · Variant study (80 epochs, gFID without CFG)gFID: 20.01 -> 16.97Improved
fix VAE variance instead of learnable variance (frozen VAE) (ablation)SimFlow · Variant study (80 epochs, gFID without CFG)gFID: 84.44 -> 67.41Improved
fix VAE variance instead of learnable variance (frozen VAE) (ablation)SimFlow · Variant study (80 epochs, gFID without CFG)rFID: 0.23 -> 0.40Hurt
add REPA-E alignment to SimFlowSimFlow · ImageNet 256x256 (class-conditional)gFID (with guidance): 2.15 -> 1.91Improved
raise latent dimension from 64 to 128 (ablation)SimFlow · Latent dimension sweep (gFID with CFG)gFID: 2.53 -> 3.62Hurt
lower latent dimension from 64 to 16 (ablation)SimFlow · Latent dimension sweep (gFID with CFG)gFID: 2.53 -> 3.55Hurt
change fixed variance from 0.5^2 to 0.1^2 (ablation)SimFlow · Fixed variance sweep (gFID with CFG)gFID: 2.53 -> 3.01Hurt
change fixed variance from 0.5^2 to 0.75^2 (ablation)SimFlow · Fixed variance sweep (gFID with CFG)gFID: 2.53 -> 2.39No clear effect
scale NF from S to XXL (ablation)SimFlow · NF model size sweep (gFID with CFG)gFID: 15.34 -> 2.53Improved
use additive noise instead of linear noise (ablation)SimFlow · Latent noise type (100K iterations, gFID without CFG)gFID: 71.0 -> 39.6Improved

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