mlsanityData to 7 Oct 2026

Trans-Dimensional Generative Modeling via Jump Diffusion Models

arXiv 2305.16261 ↗First posted 25 May 2023stat.ML cs.CV cs.LGcited by 33

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an effective way of sampling data of varying dimensionality by jointly generating state values and dimensions. We demonstrate our approach on molecular and video datasets of varying dimensionality, reporting better compatibility with test-time diffusion guidance imputation tasks and improved interpolation capabilities versus fixed dimensional models that generate state values and dimensions separately.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 27 of its 47 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

27 of 47 references.

Closest ancestors · 10

Same direction, newest first

  1. 2022Dimensionality-Varying Diffusion Process29 Nov
  2. 2022From Denoising Diffusions to Denoising Markov Models7 Nov
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  4. 2022A Continuous Time Framework for Discrete Denoising Models30 May
  5. 2022Subspace Diffusion Generative Models3 May
  6. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Video Diffusion Modelscited by 2,280
  7. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2018Model Cards for Model Reportingcited by 1,068
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  11. 2021E(n) Equivariant Graph Neural Networkscited by 951
  12. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
5 more
  1. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  2. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  3. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  4. 2023A Control-Centric Benchmark for Video Predictioncited by 25
  5. 2023Towards Controllable Diffusion Models via Reward-Guided Explorationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 17; 2026: 12.

33 papers.

Sort:

By area:

  1. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  2. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 91
  3. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  4. 2025Edit Flows: Flow Matching with Edit Operationscited by 53
  5. 2025Any-Order Flexible Length Masked Diffusioncited by 48
  6. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Designcited by 29
  7. 2025OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flowscited by 17
  8. 2026DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvascited by 16
  9. 2025Multi-domain Distribution Learning for De Novo Drug Designcited by 15
  10. 2025Insertion Language Models: Sequence Generation with Arbitrary-Position Insertionscited by 11
  11. 2025Scalable Autoregressive 3D Molecule Generationcited by 7
  12. 2025Compositional Flows for 3D Molecule and Synthesis Pathway Co-designcited by 6
21 more
  1. 2025A Diffusion Model to Shrink Proteins While Maintaining Their Functioncited by 6
  2. 2025Generative modelling with jump-diffusionscited by 4
  3. 2025Graph Diffusion that can Insert and Deletecited by 4
  4. 2025Pyramidal Patchification Flow for Visual Generationcited by 4
  5. 2025Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletionscited by 4
  6. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulationcited by 4
  7. 2026PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inferencecited by 3
  8. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generationcited by 2
  9. 2025A Jump-Diffusion Framework for Irregular Time Series Generationcited by 2
  10. 2025NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generationcited by 2
  11. 2026Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transportcited by 2
  12. 2025Discrete Bayesian Sample Inference for Graph Generationcited by 0
  13. 2026Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusioncited by 0
  14. 2026Unified Number-Free Text-to-Motion Generation Via Flow Matchingcited by 0
  15. 2026A Continuous-Time Markov Chain Framework for Insertion Language Modelscited by 0
  16. 2026Variable-Length Generative Protein Design via Generalized Poisson Flowcited by 0
  17. 2026Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusioncited by 0
  18. 2026Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinalitycited by 0
  19. 2026HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RLcited by 0
  20. 2026RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesiscited by 0
  21. 2026Grand Canonical Generatorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions
  2. 2024GUD: Generation with Unified Diffusion
  3. 2025A solvable model of learning generative diffusion: theory and insights
  4. 2023Infinite-Dimensional Diffusion Models
  5. 2025Diffusion Models with Double Guidance: Generate with aggregated datasets
  6. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
  7. 2026Entropy-Based Dimension-Free Convergence and Loss-Adaptive Schedules for Diffusion Models
  8. 2025Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models