mlsanityData to 7 Oct 2026

DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures

arXiv 2310.04750 ↗First posted 7 Oct 2023cs.AI cs.CV cs.LGcited by 6

On the map: Diffusion models → Diffusion foundations and sampling

also in 1 more
Abstract (arXiv)

Diffusion models have recently exhibited remarkable performance on synthetic data. After a diffusion path is selected, a base model, such as UNet, operates as a denoising autoencoder, primarily predicting noises that need to be eliminated step by step. Consequently, it is crucial to employ a model that aligns with the expected budgets to facilitate superior synthetic performance. In this paper, we meticulously analyze the diffusion model and engineer a base model search approach, denoted "DiffNAS". Specifically, we leverage GPT-4 as a supernet to expedite the search, supplemented with a search memory to enhance the results. Moreover, we employ RFID as a proxy to promptly rank the experimental outcomes produced by GPT-4. We also adopt a rapid-convergence training strategy to boost search efficiency. Rigorous experimentation corroborates that our algorithm can augment the search efficiency by 2 times under GPT-based scenarios, while also attaining a performance of 2.82 with 0.37 improvement in FID on CIFAR10 relative to the benchmark IDDPM algorithm.

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 25 of its 30 references that are in the map. First posted on arXiv 7 Oct 2023.

Builds on

25 of 30 references.

Closest ancestors · 11

Same direction, newest first

  1. 2022Wavelet Diffusion Models are fast and scalable Image Generators29 Nov
  2. 2022Classifier-Free Diffusion Guidance26 Jul
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  5. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents2 Jan
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  8. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  9. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  10. 2020Denoising Diffusion Probabilistic Models19 Jun
  11. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 14

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  5. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  6. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  7. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  8. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 216
  9. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
  10. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 111
  11. 2021Prioritized Architecture Sampling with Monto-Carlo Tree Searchcited by 32
  12. 2021ViTAS: Vision Transformer Architecture Searchcited by 31
2 more
  1. 2021BCNet: Searching for Network Width with Bilaterally Coupled Networkcited by 23
  2. 2023Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detectioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
  2. 2025Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Modelscited by 14
  3. 2024FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Modelscited by 9
  4. 2024TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Modelscited by 9
  5. 2026Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentationcited by 2
  6. 2025Intelligent Mobile AI-Generated Content Services via Interactive Prompt Engineering and Dynamic Service Provisioningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
  2. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
  3. 2025Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
  4. 2023Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search
  5. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
  6. 2026From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
  7. 2025Diffusion Models: A Mathematical Introduction
  8. 2023DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning