mlsanityData to 14 Oct 2026

Constrained Generative Modeling with Manually Bridged Diffusion Models

arXiv 2502.20371 ↗First posted 27 Feb 2025cs.LGcited by 8

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form so-called diffusion bridges. We develop a mechanism for combining multiple such constraints so that the resulting multiply-constrained model remains a manual bridge that respects all constraints. We also develop a mechanism for training a diffusion model that respects such multiple constraints while also adapting it to match a data distribution. We develop and extend theory demonstrating the mathematical validity of our mechanisms. Additionally, we demonstrate our mechanism in constrained generative modeling tasks, highlighting a particular high-value application in modeling trajectory initializations for path planning and control in autonomous vehicles.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 26 of its 42 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

26 of 42 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Constrained Synthesis with Projected Diffusion Models5 Feb
  2. 2023Mirror Diffusion Models for Constrained and Watermarked Generation2 Oct
  3. 2023Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance31 Jul
  4. 2023Metropolis Sampling for Constrained Diffusion Models11 Jul
  5. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov

Other references · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2018Self-Attention with Relative Position Representationscited by 1,120
  7. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  9. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  10. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 219
  11. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  12. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 190
8 more
  1. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  2. 2021Deep Generative Learning via Schr"odinger Bridgecited by 104
  3. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 84
  4. 2021Simulating Diffusion Bridges with Score Matchingcited by 52
  5. 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rolloutcited by 48
  6. 2022Data Redaction from Pre-trained GANscited by 18
  7. 2023A Diffusion-Model of Joint Interactive Navigationcited by 16
  8. 2018Actively Avoiding Nonsense in Generative Modelscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planningcited by 10
  2. 2025Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generationcited by 7
  3. 2025Score-based constrained generative modeling via Langevin diffusions with boundary conditionscited by 2
  4. 2026Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraintscited by 2
  5. 2026Improved Constrained Generation by Bridging Pretrained Generative Modelscited by 2
  6. 2025Softly Constrained Denoisers for Diffusion Models Applied to Partial Differential Equationscited by 1
  7. 2025Neural Bridge Processescited by 0
  8. 2026Integration Matters: Rollout-Based Training for Constrained Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
  2. 2025When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTS
  3. 2025Aligning Diffusion Model with Problem Constraints for Trajectory Optimization
  4. 2023Generative Modeling with Phase Stochastic Bridges
  5. 2025Projected Coupled Diffusion for Test-Time Constrained Joint Generation
  6. 2024Constrained Diffusion with Trust Sampling
  7. 2024Constraint-Aware Diffusion Models for Trajectory Optimization
  8. 2026Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing