1
Variational lossy autoencoder
OpenAI提出的变分损失自编码器，结合VAE与有损压缩，优化潜在表示学习。
2
Isolating Nonlinear Independent Sources in fMRI with $\beta$-TCVAE Models
用β-TCVAE模型从脑功能磁共振数据中分离非线性独立源，揭示大脑网络隐藏信号。
arXiv:2605.16708v1 Announce Type: new Abstract: Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in…
3
Entropic Auto-Encoding via Implicit Free-Energy Minimization
提出熵自编码器框架，通过隐式自由能最小化解决VAE后验崩溃，理论创新显著。
arXiv:2605.16164v1 Announce Type: new Abstract: Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a f…