arXiv AI August 17, 2026 By Kiran Nair, Rodrigue Rizk, KC Santosh

SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformers

arXiv:2608. 13702v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains challenging because the non-differentiable spike function requires surrogate gradients whose fixed shape may be suboptimal across layers and training stages.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv Machine Learning

Jun 11

A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks

arXiv:2606. 11236v1 Announce Type: cross Abstract: Training deep spiking neural networks (SNNs) remains challenging due to sharp loss landscapes and temporal inconsistency caused by surrogate gradients.

By Yechan Kang, Yongjin Kweon, Mingyeong Seo, Sohee Park, Yeonguk Jeon, Jongkil Park, Hyun Jae Jang, Jaewook Kim, YeonJoo Jeong, Suyoun Lee, Seongsik Park

llms computer-vision

arXiv AI

2d ago

Contrastive Attention Mitigates Spectral Bias in Spiking Transformers

The paper introduces Spiking Contrastive Attention (SCA), a module designed to reduce spectral bias in Spiking Transformers by enhancing high‑frequency information. It demonstrates that spiking neurons and spiking self‑attention act as low‑pass filters, leading to loss of high‑frequency components. Experiments show that SCA improves performance across image classification, semantic segmentation, and event‑based tracking while maintaining lower complexity than the original spiking self‑attention.

By Xiaoli Liu, Malu Zhang, Yang Yang

llms computer-vision safety

arXiv AI

Sep 10

Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies

arXiv:2605.30361v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) offer compelling energy efficiency on neuromorphic hardware, yet their training remains challenging because th...

By Dhruv Patankar, Sachit Ramesha Gowda

arXiv AI

Jun 30

Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction

arXiv:2605. 08022v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networks (ANNs).

By Himanshu Udupi, Xiaocong Yang, ChengXiang Zhai

arXiv AI

Jun 11

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

arXiv:2606. 12287v1 Announce Type: cross Abstract: The Transformer architecture is widely regarded as the most powerful tool for natural language processing, but due to a high number of complex operations, it inherently faces the issue of high energy consumption.

By Claas Beger, Florian Walter, Alois Knoll

llms rag computer-vision nlp

arXiv AI

Aug 7

Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

arXiv:2604. 08894v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs).

By Zecheng Hao, Shenghao Xie, Kang Chen, Wenxuan Liu, Zhaofei Yu, Tiejun Huang

llms benchmarks

One email a morning, machine-written

Related stories

A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks

Contrastive Attention Mitigates Spectral Bias in Spiking Transformers

Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies

Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer