Research map / Architectures and efficiency / Spiking networks
Bio-inspired spiking neuron models
Designs neuron models with compartments, resonance, and plasticity for long-term temporal modeling.
22 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Spiking networks, keyword cluster “neurons · biological · neuronal”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
8 papers in 2023–24 and 7 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 11.0% to 4.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Efficient and Robust Spiking Neural Circuit for Navigation Inspired by Echolocating Bats (NeurIPS 2016 · 5 citations)
- 2017 · Sparse convolutional coding for neuronal assembly detection (NeurIPS 2017 · 12 citations)
- 2020 · Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons (NeurIPS 2020 · 4 citations)
- 2021 · Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity (NeurIPS 2021 · 23 citations)
- 2022 · GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks (NeurIPS 2022 · 45 citations)
- 2023 · Astromorphic Self-Repair of Neuromorphic Hardware Systems (AAAI 2023 · 13 citations)
- 2024 · SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation (AAAI 2024 · 46 citations)
- 2025 · P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · 5 citations)
- 2026 · From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination (NeurIPS 2026 · 0 citations)
Earliest papers here
- Efficient and Robust Spiking Neural Circuit for Navigation Inspired by Echolocating Bats (NeurIPS 2016 · 5 citations)
- Sparse convolutional coding for neuronal assembly detection (NeurIPS 2017 · 12 citations)
- Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons (NeurIPS 2020 · 4 citations)
What has been tried
19 papers here report 196 measured changes (a component added, removed or swapped, compared with a baseline): helped 65%, no clear effect 9%, hurt 22%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add the proposed knowledge distillation (KD) training | GLUE datasets · accuracy | 4% to 5% | Helped | SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation (AAAI 2024 · 46 citations) |
| initialize beta1, beta2 to (-0.2, 0.8) | S-MNIST · test accuracy (%) | 99.20 -> 89.36 | Hurt | TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling (AAAI 2024 · 26 citations) |
| Add the spiking-threshold regularization L_v | surface reconstruction · Chamfer distance | Helped | Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation (AAAI 2024 · 10 citations) | |
| Add the surrogate gradient | LRA Text test · accuracy | 70.90 -> 81.20 | Helped | P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · 5 citations) |
| Add a refractory period and smooth reset | RF neuron simulation · SOPs | Helped | Balanced Resonate-and-Fire Neurons (ICML 2024 · 3 citations) | |
| add RF-PLC instead of FT-based ITD extraction | SLoClas · accuracy | No clear effect | Spike-based Neuromorphic Model for Sound Source Localization (NeurIPS 2024 · 2 citations) | |
| Add SCP to PDP | ant_dir · reward | 3284 ± 570 -> 6904 ± 801 | Helped | Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · 0 citations) |
| add adaptive threshold | S-CIFAR10 · accuracy | 83.9 -> 84.3 | Helped | Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling (NeurIPS 2025) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Long Range Arena (ListOps, Text, Retrieval, Image, Pathfinder) · 2 of 5 papers
- psMNIST · 2 of 5 papers
Baselines
- S4 · 2 of 5 papers
- Binary S4D · 2 of 5 papers
- Transformer · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 15 papers; from OpenAlex and the papers' affiliations).
- The Chinese University of Hong Kong · 2 papers
- University of Electronic Science and Technology of China · 2 papers
Use it
Download BibTeX of 21 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Sparse efficient spiking sequence models (26 papers)
Elsewhere in the topic
- Training deep spiking networks (141 papers)
- Spiking transformers (87 papers)
- Event-camera spiking networks (13 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).