Conditional Diffusion with Less Explicit Guidance via Model Predictive Control
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guidance (e.g., a noised classifier, or a conditional diffusion model) that is restricted to a small number of time steps. We explore a model predictive control (MPC)-like approach to approximate guidance by simulating unconditional diffusion forward, and backpropagating explicit guidance feedback. MPC-approximated guides have high cosine similarity to real guides, even over large simulation distances. Adding MPC steps improves generative quality when explicit guidance is limited to five time steps.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 18 of its 21 references that are in the map. First posted on arXiv 21 Oct 2022.
Builds on
18 of 21 references.
Closest ancestors · 6
Same direction, newest first
- 2022Classifier-Free Diffusion Guidance26 Jul
- 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
- 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
- 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
- 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
- 2021Diffusion Models Beat GANs on Image Synthesis11 May
Other references · 12
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
- 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
- 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
- 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
- 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 99
- 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
- 2020Controlling generative models with continuous factors of variationscited by 93
- 2020Model-Predictive Control via Cross-Entropy and Gradient-Based Optimizationcited by 32
- 2022On Conditioning the Input Noise for Controlled Image Generation with Diffusion Modelscited by 14
Built on by
Citing papers per year: 2023: 1.
1 paper.
- 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
- 2023On the Design Fundamentals of Diffusion Models: A Survey7 Jun 2023
Similar, not cited
Close in wording, no citation either way
- 2025Feedback Guidance of Diffusion Models
- 2023Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance
- 2026Spectral Guidance for Flexible and Efficient Control of Diffusion Models
- 2025Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model
- 2026C2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
- 2026On the Robustness of Distribution Support under Diffusion Guidance
- 2025REG: Rectified Gradient Guidance for Conditional Diffusion Models
- 2024Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory