模拟计算论文趋势 2023–2026
模拟 ML
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 16 篇被归入该主题的论文。
主要结论
- 模拟计算论文从 2023 年的 5 篇降到 2026 年的 4 篇，热度在回落。
- NeurIPS 是发模拟计算论文最多的会议，2023–2026 年共 10 篇，占四个会议总量的 63%。
- 在「量子与其他」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的神经形态计算是 1.9 倍，模拟计算是 0.8 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 2 | 2 | 1 | 0 | 5 |
| 2024 | 2 | 0 | 1 | 0 | 3 |
| 2025 | 4 | 0 | 0 | 0 | 4 |
| 2026 | 2 | 0 | 2 | 0 | 4 |
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 2026Event2Vec: Processing neuromorphic events directly by representations in vector space
- NeurIPS 2025Learning long range dependencies through time reversal symmetry breaking
- NeurIPS 2024Towards training digitally-tied analog blocks via hybrid gradient computation
- ICML 2024Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems
- NeurIPS 2023Computing Approximate $\ell_p$ Sensitivities
- ICML 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
- ICLR 2023Computing all Optimal Partial Transports
- NeurIPS 2026Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
- ICML 2026Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
- NeurIPS 2025Position: Require Frontier AI Labs To Release Small "Analog" Models
- NeurIPS 2024Towards Exact Gradient-based Training on Analog In-memory Computing
- NeurIPS 2023Energy-based learning algorithms for analog computing: a comparative study
- ICLR 2023Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
- NeurIPS 2025Analog Foundation Models
- NeurIPS 2025Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
全部模拟计算论文
共 16 篇，第 1 / 1 页
- ICML 2026Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
- ICML 2026Event2Vec: Processing neuromorphic events directly by representations in vector space
- NeurIPS 2026Algebraic Machine Learning: learning as computing subsets of the subdirect decomposition from Abstract Algebra
- NeurIPS 2026Computing All Optimal Partial $p$-Wasserstein Matchings on the Line
- NeurIPS 2025Analog Foundation Models
- NeurIPS 2025Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
- NeurIPS 2025Learning long range dependencies through time reversal symmetry breaking
- NeurIPS 2025Position: Require Frontier AI Labs To Release Small "Analog" Models
- ICML 2024Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems
- NeurIPS 2024Towards Exact Gradient-based Training on Analog In-memory Computing
- NeurIPS 2024Towards training digitally-tied analog blocks via hybrid gradient computation
- ICLR 2023Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
- ICLR 2023Computing all Optimal Partial Transports
- ICML 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
- NeurIPS 2023Computing Approximate $\ell_p$ Sensitivities
- NeurIPS 2023Energy-based learning algorithms for analog computing: a comparative study
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 查模拟计算在 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": "analog-computing"}
常见问题
- 2023–2026 年四大会议一共有多少篇模拟计算论文？
- 共 16 篇，按年份分别是 2023 年 5 篇、2024 年 3 篇、2025 年 4 篇、2026 年 4 篇。
- NeurIPS 2026 有多少篇模拟计算论文？
- NeurIPS 2026 有 2 篇模拟计算论文，上一届是 4 篇。
- ICLR 2023 有多少篇模拟计算论文？
- ICLR 2023 有 2 篇模拟计算论文。
- ICML 2026 有多少篇模拟计算论文？
- ICML 2026 有 2 篇模拟计算论文。
- 哪个会议的模拟计算论文最多？
- NeurIPS，2023–2026 年共 10 篇。