Kernel Fusion papers, 2023–2026

Key findings

• Kernel Fusion fell from 51 papers in 2023 to 48 in 2026, so interest is cooling.
• NeurIPS publishes the most Kernel Fusion work: 73 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Sensor Fusion: papers tagged with both rose from 2 in 2023 to 12 in 2026.
• Among the 5 topics under Hardware and Compilers, it ranks #3 by 2026 paper count; the fastest grower in the group, Edge Inference, is up 4.0x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Kernel Fusion papers

221 papers, page 2 of 5

51. CVPR 2025Parameterized Blur Kernel Prior Learning for Local Motion Deblurring
52. CVPR 2025RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion
53. CVPR 2025SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion
54. CVPR 2025ShiftwiseConv: Small Convolutional Kernel with Large Kernel Effect
55. CVPR 2025SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
56. CVPR 2025TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
57. CVPR 2025UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion
58. ICLR 2025Coreset Spectral Clustering
59. ICLR 2025Deep Kernel Posterior Learning under Infinite Variance Prior Weights
60. ICLR 2025Divergence of Neural Tangent Kernel in Classification Problems
61. ICLR 2025DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization
62. ICLR 2025Fast Summation of Radial Kernels via QMC Slicing
63. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
64. ICLR 2025Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions
65. ICLR 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
66. ICML 2025Adaptive kernel predictors from feature-learning infinite limits of neural networks
67. ICML 2025Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion
68. ICML 2025COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel Clustering
69. ICML 2025Equivariant Neural Tangent Kernels
70. ICML 2025K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes
71. ICML 2025Learning Curves of Stochastic Gradient Descent in Kernel Regression
72. ICML 2025Learning Input Encodings for Kernel-Optimal Implicit Neural Representations
73. ICML 2025Nested Expectations with Kernel Quadrature
74. ICML 2025NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
75. ICML 2025PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity
76. ICML 2025Permutation-Free High-Order Interaction Tests
77. ICML 2025RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer
78. ICML 2025Scalable Gaussian Processes with Latent Kronecker Structure
79. ICML 2025The Price of Linear Time: Error Analysis of Structured Kernel Interpolation
80. NeurIPS 2025Anchor-based Maximum Discrepancy for Relative Similarity Testing
81. NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
82. NeurIPS 2025ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
83. NeurIPS 2025Computational Efficiency under Covariate Shift in Kernel Ridge Regression
84. NeurIPS 2025Conditional Distribution Compression via the Kernel Conditional Mean Embedding
85. NeurIPS 2025Diversifying Parallel Ergodic Search: A Signature Kernel Evolution Strategy
86. NeurIPS 2025Fast Training of Large Kernel Models with Delayed Projections
87. NeurIPS 2025FFN Fusion: Rethinking Sequential Computation in Large Language Models
88. NeurIPS 2025FlashMoE: Fast Distributed MoE in a Single Kernel
89. NeurIPS 2025Hierarchical Shortest-Path Graph Kernel Network
90. NeurIPS 2025Just One Layer Norm Guarantees Stable Extrapolation
91. NeurIPS 2025Kernel conditional tests from learning-theoretic bounds
92. NeurIPS 2025Kernel von Mises Formula of the Influence Function
93. NeurIPS 2025Learning Provably Improves the Convergence of Gradient Descent
94. NeurIPS 2025Linearization Explains Fine-Tuning in Large Language Models
95. NeurIPS 2025MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
96. NeurIPS 2025Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration
97. NeurIPS 2025On the Hardness of Conditional Independence Testing In Practice
98. NeurIPS 2025Optimal kernel regression bounds under energy-bounded noise
99. NeurIPS 2025Regularized least squares learning with heavy-tailed noise is minimax optimal
100. NeurIPS 2025Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis

FAQ

How many Kernel Fusion papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

221 in total: 51 in 2023, 66 in 2024, 56 in 2025, 48 in 2026.

How many Kernel Fusion papers are at NeurIPS 2026?

NeurIPS 2026 has 14 Kernel Fusion papers, versus 25 the year before.

How many Kernel Fusion papers are at ICLR 2026?

ICLR 2026 has 9 Kernel Fusion papers, versus 8 the year before.

How many Kernel Fusion papers are at ICML 2026?

ICML 2026 has 13 Kernel Fusion papers, versus 14 the year before.

How many Kernel Fusion papers are at CVPR 2026?

CVPR 2026 has 12 Kernel Fusion papers, versus 9 the year before.

Which conference publishes the most Kernel Fusion papers?

NeurIPS, with 73 papers from 2023 to 2026.