Winner-take-all spiking self-attention replaces softmax in spiking transformers to support language modeling on 16 datasets with spike-driven, energy-efficient architectures.
Spike-driven transformer v2: Meta spiking neural network architecture inspiring the design of next-generation neuro- morphic chips
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
PAS-Net is a fully multiplier-free spiking neural network that enforces human joint constraints spatially and uses causal neuromodulation temporally to achieve state-of-the-art accuracy on IMU HAR with up to 98% lower dynamic energy via early-exit.
Spikinghash combines 3D-DWT Spiking WaveMixer, Spiking Self-Attention, and a dynamic soft similarity loss to produce energy-efficient hash codes for DVS data retrieval.
SAFformer uses brain-inspired active predictive filtering in a spiking transformer to reach new state-of-the-art accuracy on CIFAR-10/100 and CIFAR10-DVS plus 80.5% top-1 on ImageNet-1K at 26.58M parameters and 5.88 mJ energy.
SDLLM is a spike-driven LLM that uses gamma-SQP two-step encoding, bidirectional symmetric quantization, and membrane potential clipping to achieve 7x lower energy consumption and 4.2% higher accuracy than prior spike-based language models.
ASN uses trainable parameters for adaptive membrane dynamics and firing in SNNs, with NASN adding normalization, and reports effectiveness across 19 vision and language datasets.
citing papers explorer
-
Winner-Take-All Spiking Transformer for Language Modeling
Winner-take-all spiking self-attention replaces softmax in spiking transformers to support language modeling on 16 datasets with spike-driven, energy-efficient architectures.
-
Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition
PAS-Net is a fully multiplier-free spiking neural network that enforces human joint constraints spatially and uses causal neuromodulation temporally to achieve state-of-the-art accuracy on IMU HAR with up to 98% lower dynamic energy via early-exit.
-
Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT
Spikinghash combines 3D-DWT Spiking WaveMixer, Spiking Self-Attention, and a dynamic soft similarity loss to produce energy-efficient hash codes for DVS data retrieval.
-
SAFformer:Improving Spiking Transformer via Active Predictive Filtering
SAFformer uses brain-inspired active predictive filtering in a spiking transformer to reach new state-of-the-art accuracy on CIFAR-10/100 and CIFAR10-DVS plus 80.5% top-1 on ImageNet-1K at 26.58M parameters and 5.88 mJ energy.
-
Spike-driven Large Language Model
SDLLM is a spike-driven LLM that uses gamma-SQP two-step encoding, bidirectional symmetric quantization, and membrane potential clipping to achieve 7x lower energy consumption and 4.2% higher accuracy than prior spike-based language models.
-
Adaptive Spiking Neurons for Vision and Language Modeling
ASN uses trainable parameters for adaptive membrane dynamics and firing in SNNs, with NASN adding normalization, and reports effectiveness across 19 vision and language datasets.