Contrastive Attention Mitigates Spectral Bias in Spiking Transformers

arXiv:2610.01403 · cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: Spiking Neural Networks

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks
• Spiking Neural Networks Need High Frequency Information
• How Do Vision Transformers Work?
• Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
• cosFormer: Rethinking Softmax in Attention
• SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks
• Long-Term Visual Object Tracking with Event Cameras: An Associative Memory Augmented Tracker and A Benchmark Dataset
• Event-Driven Learning for Spiking Neural Networks
• Differential Transformer
• SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
• Spikingformer: A Key Foundation Model for Spiking Neural Networks

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems