# HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields

arXiv: https://arxiv.org/abs/2510.18122 · HTML: https://mlsanity.com/paper/2510.18122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 47 of its 73 references that are in the map.
- First posted on arXiv 20 Oct 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, 30 of 47)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation](https://mlsanity.com/paper/2203.02923/) (2022)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [GEOM: Energy-annotated molecular conformations for property prediction and molecular generation](https://mlsanity.com/paper/2006.05531/) (2020)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [Structure-based Drug Design with Equivariant Diffusion Models](https://mlsanity.com/paper/2210.13695/) (2022)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [Learning Gradient Fields for Molecular Conformation Generation](https://mlsanity.com/paper/2105.03902/) (2021)
- [MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation](https://mlsanity.com/paper/2302.09048/) (2023)
- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [Learning Neural Generative Dynamics for Molecular Conformation Generation](https://mlsanity.com/paper/2102.10240/) (2021)
- [Transformers as Meta-Learners for Implicit Neural Representations](https://mlsanity.com/paper/2208.02801/) (2022)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [Molecular generative model based on conditional variational autoencoder for de novo molecular design](https://mlsanity.com/paper/1806.05805/) (2018)
- [A Generative Model for Molecular Distance Geometry](https://mlsanity.com/paper/1909.11459/) (2019)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)

## Abstract (arXiv)

We introduce HyperDiffusionFields (HyDiF), a framework that models 3D molecular conformers as continuous fields rather than discrete atomic coordinates or graphs. At the core of our approach is the Molecular Directional Field (MDF), a vector field that maps any point in space to the direction of the nearest atom of a particular type. We represent MDFs using molecule-specific neural implicit fields, which we call Molecular Neural Fields (MNFs). To enable learning across molecules and facilitate generalization, we adopt an approach where a shared hypernetwork, conditioned on a molecule, generates the weights of the given molecule's MNF. To endow the model with generative capabilities, we train the hypernetwork as a denoising diffusion model, enabling sampling in the function space of molecular fields. Our design naturally extends to a masked diffusion mechanism to support structure-conditioned generation tasks, such as molecular inpainting, by selectively noising regions of the field. Beyond generation, the localized and continuous nature of MDFs enables spatially fine-grained feature extraction for molecular property prediction, something not easily achievable with graph or point cloud based methods. Furthermore, we demonstrate that our approach scales to larger biomolecules, illustrating a promising direction for field-based molecular modeling.