Adaptive Spiking Neurons for Vision and Language Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913029579341824 |
|---|---|
| author | Zhou, Chenlin Guo, Sihang Wang, Jiaqi Ma, Dongyang Cheng, Jin Meng, Qingyan Ma, Zhengyu Tian, Yonghong |
| author_facet | Zhou, Chenlin Guo, Sihang Wang, Jiaqi Ma, Dongyang Cheng, Jin Meng, Qingyan Ma, Zhengyu Tian, Yonghong |
| contents | Regarded as the third generation of neural networks, Spiking Neural Networks (SNNs) have garnered significant traction due to their biological plausibility and energy efficiency. Recent advancements in large models necessitate spiking neurons capable of high performance, adaptability, and training efficiency. In this work, we first propose a novel functional perspective that provides general guidance for designing the new generation of spiking neurons. Following the insightful guidelines, we propose the Adaptive Spiking Neuron (ASN), which incorporates trainable parameters to learn membrane potential dynamics and enable adaptive firing. ASN adopts an integer training and spike inference paradigm, facilitating efficient SNN training. To further enhance robustness, we propose a specialized variant of ASN, the Normalized Adaptive Spiking Neuron (NASN), which integrates normalization to stabilize training. We evaluate our neuron model on 19 datasets spanning five distinct tasks in both vision and language modalities, demonstrating the effectiveness and versatility of the ASN family. Our ASN family is expected to become the new generation of general-purpose spiking neurons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12365 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Spiking Neurons for Vision and Language Modeling Zhou, Chenlin Guo, Sihang Wang, Jiaqi Ma, Dongyang Cheng, Jin Meng, Qingyan Ma, Zhengyu Tian, Yonghong Neural and Evolutionary Computing Regarded as the third generation of neural networks, Spiking Neural Networks (SNNs) have garnered significant traction due to their biological plausibility and energy efficiency. Recent advancements in large models necessitate spiking neurons capable of high performance, adaptability, and training efficiency. In this work, we first propose a novel functional perspective that provides general guidance for designing the new generation of spiking neurons. Following the insightful guidelines, we propose the Adaptive Spiking Neuron (ASN), which incorporates trainable parameters to learn membrane potential dynamics and enable adaptive firing. ASN adopts an integer training and spike inference paradigm, facilitating efficient SNN training. To further enhance robustness, we propose a specialized variant of ASN, the Normalized Adaptive Spiking Neuron (NASN), which integrates normalization to stabilize training. We evaluate our neuron model on 19 datasets spanning five distinct tasks in both vision and language modalities, demonstrating the effectiveness and versatility of the ASN family. Our ASN family is expected to become the new generation of general-purpose spiking neurons. |
| title | Adaptive Spiking Neurons for Vision and Language Modeling |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2604.12365 |