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 221 篇，第 1 / 5 页

1. CVPR 2026Bridging RGB and Hematoxylin Components An Interleaved Guidance and Fusion
2. CVPR 2026CryoKRAQEN Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous
3. CVPR 2026Decoding 3D Perception via BrainSSD Synergistic Fusion of EEG Representations
4. CVPR 2026DPGF-Net Dual-Prior Guided Fusion Network for Joint Assessment of Perceptual
5. CVPR 2026Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning
6. CVPR 2026Exposing Functional Fusion A New Class of Strategic Backdoor in
7. CVPR 2026GeoSURGE Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
8. CVPR 2026Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape
9. CVPR 2026Hybrid Robust Collaborative Perception with LiDAR-4D Radar Fusion under Adverse
10. CVPR 2026More Than Meets the Eye A Unified Image Fusion Framework
11. CVPR 2026The Drift Kernel Why Diffusion Models Change Even When Told
12. CVPR 2026TTAPFormer Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of
13. ICLR 2026DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
14. ICLR 2026LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
15. ICLR 2026Log-Linear Attention
16. ICLR 2026PETRI: Learning Unified Cell Embeddings from Unpaired Modalities via Early-Fusion Joint Reconstruction
17. ICLR 2026Probabilistic Kernel Function for Fast Angle Testing
18. ICLR 2026Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees
19. ICLR 2026SNaX: sparse narrow accelerated mixture of experts
20. ICLR 2026Subspace Kernel Learning on Tensor Sequences
21. ICLR 2026Training-Free Determination of Network Width via Neural Tangent Kernel
22. ICML 2026Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach
23. ICML 2026Asymmetric conformal prediction with penalized kernel sum-of-squares
24. ICML 2026Dimensionality Reduction with Point-distributions Similarity Invariant
25. ICML 2026Diversity-Aware Recursive Feature Multiple Kernel Learning
26. ICML 2026Even Faster Kernel Matrix Linear Algebra via Density Estimation
27. ICML 2026Feasible Fusion: Constrained Joint Estimation under Structural Non-Overlap
28. ICML 2026Finite-Width Neural Tangent Kernels from Feynman Diagrams
29. ICML 2026Kernel-based Maximum-of-difference Test for Two-sample Comparison
30. ICML 2026Model Fusion via Retrofitting
31. ICML 2026New Bounds for Kernel Sums via Fast Spherical Embeddings
32. ICML 2026Preserving Plasticity in Continual Learning via Dynamical Isometry
33. ICML 2026Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
34. ICML 2026UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations
35. NeurIPS 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
36. NeurIPS 2026Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
37. NeurIPS 2026Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
38. NeurIPS 2026Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
39. NeurIPS 2026Flow-based Spectral Kernel Learning for Nonstationary Attention
40. NeurIPS 2026Fusion or Confusion? Multimodal Complexity Is Not All You Need
41. NeurIPS 2026Kernel Selection is Model Selection: A Unified Complexity-Penalised Approach for MMD Two-Sample Tests
42. NeurIPS 2026Kernel-Gradient Drifting Models
43. NeurIPS 2026Mini-batch kernel $k$-means
44. NeurIPS 2026Near-Optimal Regret in Adversarial Kernel Bandits
45. NeurIPS 2026Optimal algorithmic complexity of inference in quantum kernel methods
46. NeurIPS 2026ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion
47. NeurIPS 2026Sparse Attention as Compact Kernel Regression
48. NeurIPS 2026Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall
49. CVPR 2025Deformable Radial Kernel Splatting
50. CVPR 2025Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

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。