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 44 篇，第 1 / 1 页

1. ICLR 2026DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
2. ICLR 2026LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
3. ICLR 2026Log-Linear Attention
4. ICLR 2026PETRI: Learning Unified Cell Embeddings from Unpaired Modalities via Early-Fusion Joint Reconstruction
5. ICLR 2026Probabilistic Kernel Function for Fast Angle Testing
6. ICLR 2026Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees
7. ICLR 2026SNaX: sparse narrow accelerated mixture of experts
8. ICLR 2026Subspace Kernel Learning on Tensor Sequences
9. ICLR 2026Training-Free Determination of Network Width via Neural Tangent Kernel
10. ICLR 2025Coreset Spectral Clustering
11. ICLR 2025Deep Kernel Posterior Learning under Infinite Variance Prior Weights
12. ICLR 2025Divergence of Neural Tangent Kernel in Classification Problems
13. ICLR 2025DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization
14. ICLR 2025Fast Summation of Radial Kernels via QMC Slicing
15. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
16. ICLR 2025Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions
17. ICLR 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
18. ICLR 2024An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
19. ICLR 2024Convolutional Deep Kernel Machines
20. ICLR 2024Counterfactual Density Estimation using Kernel Stein Discrepancies
21. ICLR 2024Explaining Kernel Clustering via Decision Trees
22. ICLR 2024Fusing Models with Complementary Expertise
23. ICLR 2024lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
24. ICLR 2024Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
25. ICLR 2024Scalable Neural Network Kernels
26. ICLR 2024Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
27. ICLR 2024The optimality of kernel classifiers in Sobolev space
28. ICLR 2024Towards Meta-Pruning via Optimal Transport
29. ICLR 2024Transformer Fusion with Optimal Transport
30. ICLR 2023A Kernel Perspective of Skip Connections in Convolutional Networks
31. ICLR 2023Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel
32. ICLR 2023Characterizing the spectrum of the NTK via a power series expansion
33. ICLR 2023Classically Approximating Variational Quantum Machine Learning with Random Fourier Features
34. ICLR 2023Kernel Neural Optimal Transport
35. ICLR 2023On The Relative Error of Random Fourier Features for Preserving Kernel Distance
36. ICLR 2023On the Saturation Effect of Kernel Ridge Regression
37. ICLR 2023Random Laplacian Features for Learning with Hyperbolic Space
38. ICLR 2023Reliability of CKA as a Similarity Measure in Deep Learning
39. ICLR 2023Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
40. ICLR 2023Self-supervised learning with rotation-invariant kernels
41. ICLR 2023Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation
42. ICLR 2023Symmetric Pruning in Quantum Neural Networks
43. ICLR 2023Trainability Preserving Neural Pruning
44. ICLR 2023Tuning Frequency Bias in Neural Network Training with Nonuniform Data

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。