# ShaLa: Multimodal Shared Latent Space Modelling

arXiv: https://arxiv.org/abs/2508.17376 · HTML: https://mlsanity.com/paper/2508.17376/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)
- [Visually Indicated Sounds](https://mlsanity.com/paper/1512.08512/) (2015)
- [DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents](https://mlsanity.com/paper/2201.00308/) (2022)
- [Joint Multimodal Learning with Deep Generative Models](https://mlsanity.com/paper/1611.01891/) (2016)
- [Generalized Multimodal ELBO](https://mlsanity.com/paper/2105.02470/) (2021)
- [A Contrastive Learning Approach for Training Variational Autoencoder Priors](https://mlsanity.com/paper/2010.02917/) (2020)
- [Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence](https://mlsanity.com/paper/2006.08242/) (2020)
- [RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model](https://mlsanity.com/paper/2309.00810/) (2023)
- [Generative Models of Visually Grounded Imagination](https://mlsanity.com/paper/1705.10762/) (2017)
- [One Diffusion to Generate Them All](https://mlsanity.com/paper/2411.16318/) (2024)
- [On the Limitations of Multimodal VAEs](https://mlsanity.com/paper/2110.04121/) (2021)
- [Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data](https://mlsanity.com/paper/1805.11264/) (2018)
- [Learning Multimodal Latent Generative Models with Energy-Based Prior](https://mlsanity.com/paper/2409.19862/) (2024)
- [Learning Latent Space Hierarchical EBM Diffusion Models](https://mlsanity.com/paper/2405.13910/) (2024)

## Built on by (most cited first, 1 of 1)

- [MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation](https://mlsanity.com/paper/2606.16408/) (2026)

## Abstract (arXiv)

This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across inputs, which can inadvertently obscure the high-level semantic concepts that are shared across modalities. Notably, Multimodal VAEs with low-dimensional latent variables are designed to capture shared representations, enabling various tasks such as joint multimodal synthesis and cross-modal inference. However, multimodal VAEs often struggle to design expressive joint variational posteriors and suffer from low-quality synthesis. In this work, ShaLa addresses these challenges by integrating a novel architectural inference model and a second-stage expressive diffusion prior, which not only facilitates effective inference of shared latent representation but also significantly improves the quality of downstream multimodal synthesis. We validate ShaLa extensively across multiple benchmarks, demonstrating superior coherence and synthesis quality compared to state-of-the-art multimodal VAEs. Furthermore, ShaLa scales to many more modalities while prior multimodal VAEs have fallen short in capturing the increasing complexity of the shared latent space.