mlsanityData to 7 Oct 2026

Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance

arXiv 2307.16463 ↗First posted 31 Jul 2023cs.LG stat.MLcited by 6

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Score-based diffusion models are a powerful class of generative models, widely utilized across diverse domains. Despite significant advancements in large-scale tasks such as text-to-image generation, their application to constrained domains has received considerably less attention. This work addresses model learning in a setting where, in addition to the training dataset, there further exists side-information in the form of an oracle that can label samples as being outside the support of the true data generating distribution. Specifically we develop a new denoising diffusion probabilistic modeling methodology, Gen-neG, that leverages this additional side-information. Gen-neG builds on classifier guidance in diffusion models to guide the generation process towards the positive support region indicated by the oracle. We empirically establish the utility of Gen-neG in applications including collision avoidance in self-driving simulators and safety-guarded human motion generation.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 59 of its 83 references that are in the map. First posted on arXiv 31 Jul 2023.

Builds on

59 of 83 references.

Closest ancestors · 14

Same direction, newest first

  1. 2023Understanding and Mitigating Copying in Diffusion Models31 May
  2. 2023Diffusion Models for Constrained Domains11 Apr
  3. 2023Reflected Diffusion Models10 Apr
  4. 2023Universal Guidance for Diffusion Models14 Feb
  5. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models28 Nov
  6. 2022Graphically Structured Diffusion Models20 Oct
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2018Self-Attention with Relative Position Representationscited by 1,112
  10. 2022Human Motion Diffusion Modelcited by 1,062
  11. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  12. 2017A Closer Look at Memorization in Deep Networkscited by 936
33 more
  1. 2018Image Transformercited by 770
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  3. 2023Extracting Training Data from Diffusion Modelscited by 723
  4. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  5. 2023Erasing Concepts from Diffusion Modelscited by 530
  6. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 501
  7. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
  8. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  9. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  10. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2023Human Motion Diffusion as a Generative Priorcited by 354
  13. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  14. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  15. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  16. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  17. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 218
  18. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  19. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 189
  20. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  21. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  22. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 83
  23. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  24. 2018Discriminator Rejection Samplingcited by 48
  25. 2021Negative Data Augmentationcited by 46
  26. 2020Refining Deep Generative Models via Discriminator Gradient Flowcited by 45
  27. 2021Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulationcited by 32
  28. 2022Data Redaction from Pre-trained GANscited by 18
  29. 2018Actively Avoiding Nonsense in Generative Modelscited by 12
  30. 2023Constraining Generative Models for Engineering Design with Negative Datacited by 11
  31. 2022Conditional Permutation Invariant Flowscited by 6
  32. 2019Amortized Rejection Sampling in Universal Probabilistic Programmingcited by 5
  33. 2020Coping With Simulators That Don't Always Returncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2025Constrained Generative Modeling with Manually Bridged Diffusion Modelscited by 8
  2. 2024TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characterscited by 6
  3. 2025Diffusion-based Planning with Learned Viability Filterscited by 2
  4. 2026Improved Constrained Generation by Bridging Pretrained Generative Modelscited by 2
  5. 2026Histogram-constrained Image Generationcited by 0
  6. 2026Integration Matters: Rollout-Based Training for Constrained Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints
  2. 2026Where the Score Lives: A Wavelet View of Diffusion
  3. 2022How Much is Enough? A Study on Diffusion Times in Score-based Generative Models
  4. 2024A Score-Based Density Formula, with Applications in Diffusion Generative Models
  5. 2024Discrete vs. Continuous Trade-offs for Generative Models
  6. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
  7. 2024Evaluating the design space of diffusion-based generative models
  8. 2024Diffusion Models for Generating Ballistic Spacecraft Trajectories