# Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

arXiv: https://arxiv.org/abs/2503.15567 · HTML: https://mlsanity.com/paper/2503.15567/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 3 of its 70 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 3 of 3)

- [All-atom Diffusion Transformers: Unified generative modelling of molecules and materials](https://mlsanity.com/paper/2503.03965/) (2025)
- [MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space](https://mlsanity.com/paper/2404.12141/) (2024)
- [Language-Enhanced Representation Learning for Single-Cell Transcriptomics](https://mlsanity.com/paper/2503.09427/) (2025)

## Built on by (most cited first, 11 of 11)

- [Mofasa: A Step Change in Metal-Organic Framework Generation](https://mlsanity.com/paper/2512.01756/) (2025)
- [MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching](https://mlsanity.com/paper/2512.12198/) (2025)
- [PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs](https://mlsanity.com/paper/2507.05101/) (2025)
- [MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax](https://mlsanity.com/paper/2512.10991/) (2025)
- [Autoregressive latent diffusion for 3D molecule generation](https://mlsanity.com/paper/2607.09277/) (2026)
- [SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems](https://mlsanity.com/paper/2607.12380/) (2026)
- [3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding](https://mlsanity.com/paper/2510.16780/) (2025)
- [Learning 3D Anisotropic Noise Distributions Improves Molecular Force Field Modeling](https://mlsanity.com/paper/2510.22123/) (2025)
- [Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design](https://mlsanity.com/paper/2605.27413/) (2026)
- [Smoothing Dark Areas in Molecular Latent Diffusion](https://mlsanity.com/paper/2606.13955/) (2026)
- [GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generation](https://mlsanity.com/paper/2609.37158/) (2026)

## Abstract (arXiv)

3D molecule generation is crucial for drug discovery and material science, requiring models to process complex multi-modalities, including atom types, chemical bonds, and 3D coordinates. A key challenge is integrating these modalities of different shapes while maintaining SE(3) equivariance for 3D coordinates. To achieve this, existing approaches typically maintain separate latent spaces for invariant and equivariant modalities, reducing efficiency in both training and sampling. In this work, we propose Unified Variational Auto-Encoder for 3D Molecular Latent Diffusion Modeling (UAE-3D), a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space, while maintaining near-zero reconstruction error. This unified latent space eliminates the complexities of handling multi-modality and equivariance when performing latent diffusion modeling. We demonstrate this by employing the Diffusion Transformer--a general-purpose diffusion model without any molecular inductive bias--for latent generation. Extensive experiments on GEOM-Drugs and QM9 datasets demonstrate that our method significantly establishes new benchmarks in both textitde novo and conditional 3D molecule generation, achieving leading efficiency and quality. On GEOM-Drugs, it reduces FCD by 72.6% over the previous best result, while achieving over 70% relative average improvements in geometric fidelity. Our code is released at https://github.com/lyc0930/UAE-3D/.