神经形态计算论文趋势 2023–2026
脉冲网络
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 92 篇被归入该主题的论文。
主要结论
- 神经形态计算论文从 2023 年的 18 篇增长到 2026 年的 35 篇，三年间扩大到约 1.9 倍。
- NeurIPS 是发神经形态计算论文最多的会议，2023–2026 年共 34 篇，占四个会议总量的 37%。
- 交叉方向里涨得最快的是应用 · neuroscience and cognitive science：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 12 篇。
- 在「量子与其他」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的光学计算是 1.2 倍，神经形态计算是 1.9 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 8 | 4 | 5 | 1 | 18 |
| 2024 | 9 | 6 | 3 | 1 | 19 |
| 2025 | 7 | 4 | 6 | 3 | 20 |
| 2026 | 10 | 15 | 8 | 2 | 35 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026Algebraic Machine Learning: learning as computing subsets of the subdirect decomposition from Abstract Algebra
- ICML 2026Equilibrium Propagation for Non-Conservative Systems
- ICLR 2026Beyond Linear Processing: Dendritic Bilinear Integration in Spiking Neural Networks
- CVPR 2026Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses
- NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
- ICML 2025Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model
- ICLR 2025Quantized Spike-driven Transformer
- CVPR 2025Spiking Transformer with Spatial-Temporal Attention
- NeurIPS 2024LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
- ICML 2024Robust Stable Spiking Neural Networks
- ICLR 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
- CVPR 2024DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses
- NeurIPS 2023Computing Approximate $\ell_p$ Sensitivities
- ICML 2023Dynamics-inspired Neuromorphic Visual Representation Learning
- ICLR 2023A Higher Precision Algorithm for Computing the $1$-Wasserstein Distance
- CVPR 2023Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks
- NeurIPS 2026Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
- ICML 2026Event2Vec: Processing neuromorphic events directly by representations in vector space
- ICLR 2026Breaking Gradient Temporal Collinearity for Robust Spiking Neural Networks
- CVPR 2026SDTrack A Baseline for Event-based Tracking via Spiking Neural Networks
全部神经形态计算论文
共 20 篇，第 1 / 1 页
- CVPR 2025Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers
- CVPR 2025Spiking Transformer with Spatial-Temporal Attention
- CVPR 2025STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks
- ICLR 2025QP-SNN: Quantized and Pruned Spiking Neural Networks
- ICLR 2025Quantized Spike-driven Transformer
- ICLR 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspective
- ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
- ICML 2025Computing Voting Rules with Improvement Feedback
- ICML 2025Efficient ANN-SNN Conversion with Error Compensation Learning
- ICML 2025Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
- ICML 2025Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model
- ICML 2025Training High Performance Spiking Neural Network by Temporal Model Calibration
- ICML 2025TS-SNN: Temporal Shift Module for Spiking Neural Networks
- NeurIPS 2025Bounds on the computational complexity of neurons due to dendritic morphology
- NeurIPS 2025FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
- NeurIPS 2025G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks
- NeurIPS 2025Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics
- NeurIPS 2025S$^2$NN: Sub-bit Spiking Neural Networks
- NeurIPS 2025Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
- NeurIPS 2025The Parameterized Complexity of Computing the VC-Dimension
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查神经形态计算在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "neuromorphic-computing"}
常见问题
- 2023–2026 年四大会议一共有多少篇神经形态计算论文？
- 共 92 篇，按年份分别是 2023 年 18 篇、2024 年 19 篇、2025 年 20 篇、2026 年 35 篇。
- NeurIPS 2026 有多少篇神经形态计算论文？
- NeurIPS 2026 有 10 篇神经形态计算论文，上一届是 7 篇。
- ICLR 2026 有多少篇神经形态计算论文？
- ICLR 2026 有 15 篇神经形态计算论文，上一届是 4 篇。
- ICML 2026 有多少篇神经形态计算论文？
- ICML 2026 有 8 篇神经形态计算论文，上一届是 6 篇。
- CVPR 2026 有多少篇神经形态计算论文？
- CVPR 2026 有 2 篇神经形态计算论文，上一届是 3 篇。
- 哪个会议的神经形态计算论文最多？
- NeurIPS，2023–2026 年共 34 篇。