Research map / Image generation / Autoregressive and latent generation

Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders

ICLR 2024 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a multimodal VAE with a clustering-extended latent space and diffusion-based decoders for deep generative clustering across heterogeneous modalities.

Problem

Clustering with multiple heterogeneous modalities using generative models, where multimodal VAEs and VAE-based clustering have been studied separately.

Approach

Extends the multimodal VAE latent space to learn data clusters, combining a shared latent with diffusion-based multimodal decoding so that clustering and generation are learned jointly.

Experimental setup

Builds on: multimodal VAE variational autoencoder

Closest papers by meaning

• Diffusion Models for Multi-Task Generative Modeling (ICLR 2024 · similarity 0.87)
• Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders (ICML 2025 · similarity 0.87)
• Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis (ICLR 2025 · similarity 0.86)
• Clustering via Self-Supervised Diffusion (ICML 2025 · similarity 0.86)
• Unity by Diversity: Improved Representation Learning for Multimodal VAEs (NeurIPS 2024 · similarity 0.86)
• Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces (ICML 2025 · similarity 0.86)