AI Paper Atlas

Research map / Benchmarks / SHD

SHD leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SHD. Best accuracy: 96.41 (SpikCommander (1L-8-128), AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

SHD · accuracy

13 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
196.41SpikCommander (1L-8-128)SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition
AAAI 2026 · Table 1
Spiking networks
296.2D-RFDendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling
NeurIPS 2025 · Table 1
Spiking networks
396.1TIDESTIDES: Implicit Time-Awareness in Selective State Space Models
NeurIPS 2026 · Table 3
Causal and generative time series
495.5Mul-free channel-wise PSN
SNN-delay
Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics
NeurIPS 2025 · SHD comparison table
Spiking networks
595.07DCLS-Delays (2L-1KC)Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
ICLR 2024 · Table: Classification accuracy
Spiking networks
694.96Ours
2F512HD
Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks
ICML 2026 · Table 1
Spiking networks
792.7BHRFBalanced Resonate-and-Fire Neurons
ICML 2024 · Table 1
Spiking networks
892.36HetSynLIFHetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
NeurIPS 2025 · Table 1
Spiking networks
991.39S2-NetFrom Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination
NeurIPS 2026 · Table 2
Spiking networks
1091.19Ours
Recurrent
Rethinking Spiking Neural Networks from an Ensemble Learning Perspective
ICLR 2025 · Comparative results on the 1D
Spiking networks
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.