activity
20242026
collaborators

7 papers

stat.ML2026

StrTransformer: Source-Wise Structured Transformers for Unsupervised Blind Source Recovery

Yuan-Hao Wei

This paper proposes StrTransformer, a source-wise structured Transformer framework for blind source recovery and branch-wise latent modeling. Instead of using an encoder to infer l…

stat.ML2026

StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation

Yuan-Hao Wei

This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and nonlinear mixing. The framework treats…

stat.ML2026

PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA

Yuan-Hao Wei, Yan-Jie Sun

Independent component analysis is a core framework within blind source separation for recovering latent source signals from observed mixtures under statistical independence assumpt…

stat.ML2025

Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA

Yuan-Hao Wei, Fu-Hao Deng, Lin-Yong Cui +1

The interpretability of generative models is considered a key factor in demonstrating their effectiveness and controllability. The generated data are believed to be determined by l…

stat.ML2025

Half-AVAE: Adversarial-Enhanced Factorized and Structured Encoder-Free VAE for Underdetermined Independent Component Analysis

Yuan-Hao Wei, Yan-Jie Sun

This study advances the Variational Autoencoder (VAE) framework by addressing challenges in Independent Component Analysis (ICA) under both determined and underdetermined condition…

cs.LG2025

VAEs and GANs: Implicitly Approximating Complex Distributions with Simple Base Distributions and Deep Neural Networks -- Principles, Necessity, and Limitations

Yuan-Hao Wei

This tutorial focuses on the fundamental architectures of Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN), disregarding their numerous variations, to highl…