mlsanityData to 7 Oct 2026

Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism

arXiv 2503.23767 ↗First posted 31 Mar 2025cs.NEcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Lateral connection is a fundamental feature of biological neural circuits, facilitating local information processing and adaptive learning. In this work, we integrate lateral connections with a substructure selection network to develop a novel diffusion model based on spiking neural networks (SNNs). Unlike conventional artificial neural networks, SNNs employ an intrinsic spiking inner loop to process sequential binary spikes. We leverage this spiking inner loop alongside a lateral connection mechanism to iteratively refine the substructure selection network, enhancing model adaptability and expressivity. Specifically, we design a lateral connection framework comprising a learnable lateral matrix and a lateral mapping function, both implemented using spiking neurons, to dynamically update lateral connections. Through mathematical modeling, we establish that the proposed lateral update mechanism, under a well-defined local objective, aligns with biologically plausible synaptic plasticity principles. Extensive experiments validate the effectiveness of our approach, analyzing the role of substructure selection and lateral connection during training. Furthermore, quantitative comparisons demonstrate that our model consistently surpasses state-of-the-art SNN-based generative models across multiple benchmark datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 33 of its 47 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

33 of 47 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts14 Mar
  2. 2024SDiT: Spiking Diffusion Model with Transformer18 Feb
  3. 2023Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks20 Aug
  4. 2023Spiking Denoising Diffusion Probabilistic Models29 Jun
  5. 2022Scalable Diffusion Models with Transformers19 Dec
  6. 2022Classifier-Free Diffusion Guidance26 Jul
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  11. 2020Denoising Diffusion Implicit Models6 Oct
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 21

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  10. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  11. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  12. 2021Taming Sparsely Activated Transformer with Stochastic Expertscited by 112
9 more
  1. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 82
  2. 2021Fully Spiking Variational Autoencodercited by 22
  3. 2022An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connectionscited by 13
  4. 2019Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detectioncited by 9
  5. 2015STDP as presynaptic activity times rate of change of postsynaptic activitycited by 8
  6. 2021Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Codingcited by 8
  7. 2023Spiking Generative Adversarial Network with Attention Scoring Decodingcited by 7
  8. 2023Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modelingcited by 5
  9. 2024Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Spiking Diffusion Models
  2. 2025Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning
  3. 2023Fully Spiking Denoising Diffusion Implicit Models
  4. 2026Dendritic In-Context Learning in a Single-Layer Spiking Neural Network
  5. 2024P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
  6. 2025Spiking Neural Models for Decision-Making Tasks with Learning
  7. 2024SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds
  8. 2026SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts