AI Paper Atlas

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

Bi-Lipschitz Autoencoder With Injectivity Guarantee

Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Qi Long, Li Shen

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs · 0 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 BLAE instead of vanilla AE (add injective and bi-Lipschitz regularization)Vanilla AE · Swiss Rollk-NN recall: 5.18e-01 -> 9.61e-01Improved
use BLAE instead of vanilla AEVanilla AE · Swiss RollMSE: 4.14e-02 -> 9.36e-05Improved
use BLAE instead of vanilla AEVanilla AE · dSpritesk-NN recall: 4.89e-01 -> 7.39e-01Improved
use BLAE instead of strongest baseline SPAESPAE · Swiss Rollk-NN recall: 8.95e-01 -> 9.61e-01Improved
use BLAE instead of SPAESPAE · dSpritesKL 0.01: 2.95e-02 -> 6.42e-03Improved
use BLAE instead of SPAESPAE · dSpritesMSE: 1.72e-02 -> 1.69e-02No clear effect
use BLAE instead of SPAESPAE · MNIST (uniform sampling)k-NN recall: 8.59e-01 -> 9.03e-01Improved
use BLAE instead of SPAESPAE · MNIST (uniform sampling)MSE: 6.91e-03 -> 2.92e-03Improved

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