mlsanityData to 7 Oct 2026

An efficient probabilistic hardware architecture for diffusion-like models

arXiv 2510.23972 ↗First posted 28 Oct 2025cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

The proliferation of probabilistic AI has prompted proposals for specialized stochastic computers. Despite promising efficiency gains, these proposals have failed to gain traction because they rely on fundamentally limited modeling techniques and exotic, unscalable hardware. In this work, we address these shortcomings by proposing an all-transistor probabilistic computer that implements powerful denoising models at the hardware level. A system-level analysis indicates that devices based on our architecture could achieve performance parity with GPUs on a simple image benchmark using approximately 10,000 times less energy.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 40 of its 94 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

40 of 94 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
28 more
  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  4. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  5. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  6. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 630
  7. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  8. 2021How to Train Your Energy-Based Modelscited by 271
  9. 2023The Impact of AI on Developer Productivity: Evidence from GitHub Copilotcited by 264
  10. 2019Diagnosing and Enhancing VAE Modelscited by 192
  11. 2020The Hardware Lotterycited by 160
  12. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  13. 2024Energy-Based Diffusion Language Models for Text Generationcited by 86
  14. 2022Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Trainingcited by 78
  15. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  16. 2015Application of Quantum Annealing to Training of Deep Neural Networkscited by 37
  17. 2023Efficient Video and Audio processing with Loihi 2cited by 28
  18. 2021Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machinescited by 27
  19. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  20. 2024SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learningcited by 24
  21. 2023Training Deep Boltzmann Networks with Sparse Ising Machinescited by 23
  22. 2023Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihoodcited by 19
  23. 2023Efficient Training of Energy-Based Models Using Jarzynski Equalitycited by 15
  24. 2025VCT: Training Consistency Models with Variational Noise Couplingcited by 15
  25. 2019Thermodynamic Computingcited by 12
  26. 2023CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learningcited by 10
  27. 2025Scalable Connectivity for Ising Machines: Dense to Sparsecited by 3
  28. 2019Low Barrier Nanomagnet Design for Binary Stochastic Neurons: Design Challenges for Real Nanomagnets with Fabrication Defectscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Generative Models on Analog Hardware with Dynamicscited by 2
  2. 2025Correspondence Between Ising Machines and Neural Networkscited by 1
  3. 2026Thermodynamic Diffusion Inference with Minimal Digital Conditioningcited by 1
  4. 2026A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computingcited by 1
  5. 2026Symmetric Equilibrium Propagation for Thermodynamic Diffusion Trainingcited by 0
  6. 2026Scaling Up Thermodynamic AI Modelscited by 0
  7. 2026CN101 - A Digital Thermodynamic Computer for Generative AIcited by 0
  8. 2026Diversity of EML-type operatorscited by 0