mlsanityData to 14 Oct 2026

ProxelGen: Generating Proteins as 3D Densities

arXiv 2506.19820 ↗First posted 24 Jun 2025q-bio.BM cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We develop ProxelGen, a protein structure generative model that operates on 3D densities as opposed to the prevailing 3D point cloud representations. Representing proteins as voxelized densities, or proxels, enables new tasks and conditioning capabilities. We generate proteins encoded as proxels via a 3D CNN-based VAE in conjunction with a diffusion model operating on its latent space. Compared to state-of-the-art models, ProxelGen's samples achieve higher novelty, better FID scores, and the same level of designability as the training set. ProxelGen's advantages are demonstrated in a standard motif scaffolding benchmark, and we show how 3D density-based generation allows for more flexible shape conditioning.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

17 of 32 references.

References · 17

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  8. 2021Score-based Generative Modeling in Latent Spacecited by 636
  9. 2023SE(3) diffusion model with application to protein backbone generationcited by 219
  10. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 150
  11. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 54
  12. 2024Improved motif-scaffolding with SE(3) flow matchingcited by 43
5 more
  1. 20233D molecule generation by denoising voxel gridscited by 40
  2. 2024Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2cited by 35
  3. 2023A Latent Diffusion Model for Protein Structure Generationcited by 28
  4. 2024Generating Highly Designable Proteins with Geometric Algebra Flow Matchingcited by 7
  5. 2024E(3)-equivariant models cannot learn chirality: Field-based molecular generationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matchingcited by 30
  2. 2025InertialAR: Autoregressive 3D Molecule Generation with Inertial Framescited by 3
  3. 2026Adaptive Protein Tokenizationcited by 2
  4. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Protein generation with embedding learning for motif diversification
  2. 2025ProtPainter: Draw or Drag Protein via Topology-guided Diffusion
  3. 2026Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards
  4. 2025ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
  5. 2026Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
  6. 2024BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
  7. 2025Protein-SE(3): Benchmarking SE(3)-based Generative Models for Protein Structure Design
  8. 2024Structure-based drug design by denoising voxel grids