算子融合论文趋势 2023–2026

主要结论

• 算子融合论文从 2023 年的 51 篇降到 2026 年的 48 篇，热度在回落。
• NeurIPS 是发算子融合论文最多的会议，2023–2026 年共 73 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是传感融合：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 12 篇。
• 在「硬件与编译」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的端侧推理是 4.0 倍，算子融合是 0.9 倍。

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 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
• ICML 2026Asymmetric conformal prediction with penalized kernel sum-of-squares
• ICLR 2026Probabilistic Kernel Function for Fast Angle Testing
• CVPR 2026Bridging RGB and Hematoxylin Components An Interleaved Guidance and Fusion
• NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
• ICML 2025Equivariant Neural Tangent Kernels
• ICLR 2025DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization
• CVPR 2025Parameterized Blur Kernel Prior Learning for Local Motion Deblurring
• NeurIPS 2024Efficient Convex Algorithms for Universal Kernel Learning
• ICML 2024Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
• ICLR 2024Convolutional Deep Kernel Machines
• CVPR 2024Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion
• NeurIPS 2023CosNet: A Generalized Spectral Kernel Network
• ICML 2023A Kernel Stein Test of Goodness of Fit for Sequential Models
• ICLR 2023A Kernel Perspective of Skip Connections in Convolutional Networks
• CVPR 2023Compacting Binary Neural Networks by Sparse Kernel Selection
• NeurIPS 2026Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
• ICML 2026Even Faster Kernel Matrix Linear Algebra via Density Estimation
• ICLR 2026LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
• CVPR 2026CryoKRAQEN Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous

全部算子融合论文

共 51 篇，第 1 / 2 页

1. CVPR 2023Compacting Binary Neural Networks by Sparse Kernel Selection
2. CVPR 2023Efficient Multimodal Fusion via Interactive Prompting
3. CVPR 2023Federated Learning With Data-Agnostic Distribution Fusion
4. CVPR 2023K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring
5. CVPR 2023Kernel Aware Resampler
6. CVPR 2023LinK: Linear Kernel for LiDAR-Based 3D Perception
7. CVPR 2023Neural Kernel Surface Reconstruction
8. CVPR 2023Structured Kernel Estimation for Photon-Limited Deconvolution
9. ICLR 2023A Kernel Perspective of Skip Connections in Convolutional Networks
10. ICLR 2023Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel
11. ICLR 2023Characterizing the spectrum of the NTK via a power series expansion
12. ICLR 2023Classically Approximating Variational Quantum Machine Learning with Random Fourier Features
13. ICLR 2023Kernel Neural Optimal Transport
14. ICLR 2023On The Relative Error of Random Fourier Features for Preserving Kernel Distance
15. ICLR 2023On the Saturation Effect of Kernel Ridge Regression
16. ICLR 2023Random Laplacian Features for Learning with Hyperbolic Space
17. ICLR 2023Reliability of CKA as a Similarity Measure in Deep Learning
18. ICLR 2023Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
19. ICLR 2023Self-supervised learning with rotation-invariant kernels
20. ICLR 2023Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation
21. ICLR 2023Symmetric Pruning in Quantum Neural Networks
22. ICLR 2023Trainability Preserving Neural Pruning
23. ICLR 2023Tuning Frequency Bias in Neural Network Training with Nonuniform Data
24. ICML 2023A Kernel Stein Test of Goodness of Fit for Sequential Models
25. ICML 2023Consistency of Multiple Kernel Clustering
26. ICML 2023Delayed Feedback in Kernel Bandits
27. ICML 2023Estimation Beyond Data Reweighting: Kernel Method of Moments
28. ICML 2023Fast Private Kernel Density Estimation via Locality Sensitive Quantization
29. ICML 2023Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space
30. ICML 2023Integrating Prior Knowledge in Contrastive Learning with Kernel
31. ICML 2023KDEformer: Accelerating Transformers via Kernel Density Estimation
32. ICML 2023Kernel Logistic Regression Approximation of an Understandable ReLU Neural Network
33. ICML 2023Kernel QuantTree
34. ICML 2023NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning
35. ICML 2023On the Optimality of Misspecified Kernel Ridge Regression
36. ICML 2023Optimal Convergence Rates for Agnostic Nyström Kernel Learning
37. ICML 2023Toward Large Kernel Models
38. NeurIPS 2023Calibration by Distribution Matching: Trainable Kernel Calibration Metrics
39. NeurIPS 2023ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion
40. NeurIPS 2023CosNet: A Generalized Spectral Kernel Network
41. NeurIPS 2023Designing Robust Transformers using Robust Kernel Density Estimation
42. NeurIPS 2023Gradient-Free Kernel Stein Discrepancy
43. NeurIPS 2023Kernel Quadrature with Randomly Pivoted Cholesky
44. NeurIPS 2023Kernel-Based Tests for Likelihood-Free Hypothesis Testing
45. NeurIPS 2023Kernelized Cumulants: Beyond Kernel Mean Embeddings
46. NeurIPS 2023RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy
47. NeurIPS 2023Statistical Insights into HSIC in High Dimensions
48. NeurIPS 2023Stein $\Pi$-Importance Sampling
49. NeurIPS 2023The Exact Sample Complexity Gain from Invariances for Kernel Regression
50. NeurIPS 2023Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

常见问题

2023–2026 年四大会议一共有多少篇算子融合论文？

共 221 篇，按年份分别是 2023 年 51 篇、2024 年 66 篇、2025 年 56 篇、2026 年 48 篇。

NeurIPS 2026 有多少篇算子融合论文？

NeurIPS 2026 有 14 篇算子融合论文，上一届是 25 篇。

ICLR 2026 有多少篇算子融合论文？

ICLR 2026 有 9 篇算子融合论文，上一届是 8 篇。

ICML 2026 有多少篇算子融合论文？

ICML 2026 有 13 篇算子融合论文，上一届是 14 篇。

CVPR 2026 有多少篇算子融合论文？

CVPR 2026 有 12 篇算子融合论文，上一届是 9 篇。

哪个会议的算子融合论文最多？

NeurIPS，2023–2026 年共 73 篇。