Learning Latent Space Hierarchical EBM Diffusion Models

no code implementations • 22 May 2024 • Jiali Cui, Tian Han

Such a prior model can be limited in modelling expressivity, which results in a gap between the generator posterior and the prior model, known as the prior hole problem.

Learning Energy-based Model via Dual-MCMC Teaching

no code implementations • NeurIPS 2023 • Jiali Cui, Tian Han

To address this issue, we present a joint learning framework that interweaves the maximum likelihood learning algorithm for both the EBM and the complementary generator model.

Learning Hierarchical Features with Joint Latent Space Energy-Based Prior

no code implementations • ICCV 2023 • Jiali Cui, Ying Nian Wu, Tian Han

In this paper, we propose a joint latent space EBM prior model with multi-layer latent variables for effective hierarchical representation learning.

Representation Learning

Learning Joint Latent Space EBM Prior Model for Multi-layer Generator

no code implementations • CVPR 2023 • Jiali Cui, Ying Nian Wu, Tian Han

To tackle this issue and learn more expressive prior models, we propose an energy-based model (EBM) on the joint latent space over all layers of latent variables with the multi-layer generator as its backbone.

Outlier Detection

Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling

no code implementations • NeurIPS Workshop ICBINB 2020 • Bo Pang, Erik Nijkamp, Jiali Cui, Tian Han, Ying Nian Wu

This paper proposes a latent space energy-based prior model for semi-supervised learning.