Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism

Summary:

This work brings diffusion modeling into the spiking neural network setting through a biologically inspired lateral-connection design. By combining adaptive lateral selection with the intrinsic temporal dynamics of SNNs, the model improves generative quality and parameter efficiency while keeping the design grounded in plausible neural computation.

Bibtex:

@misc{feng2025spikingdiffusion,
  title={Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism},
  author={Linghao Feng and Dongcheng Zhao and Sicheng Shen and Yi Zeng},
  year={2025},
  eprint={2503.23767},
  archivePrefix={arXiv},
  primaryClass={cs.NE},
  url={https://arxiv.org/abs/2503.23767}
}

Recommended citation: Feng, L., Zhao, D., Shen, S., & Zeng, Y. (2025). Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism.
Download Paper