Feature Attribution papers, 2023–2026

Key findings

• Feature Attribution went from 118 papers in 2023 to 219 in 2026, roughly 1.9x in three years.
• NeurIPS publishes the most Feature Attribution work: 193 papers from 2023 to 2026, 28% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 1 in 2023 to 14 in 2026.
• Among the 5 topics under Interpretability, it ranks #1 by 2026 paper count; the fastest grower in the group, Mechanistic Interpretability, is up 8.1x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
• ICML 2026Activation with Intrinsic-Extrinsic Consensus
• ICLR 2026AnyUp: Universal Feature Upsampling
• CVPR 2026A Training-Free Style-Personalization via SVD-Based Feature Decomposition
• NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
• ICML 2025BCE vs. CE in Deep Feature Learning
• ICLR 2025A Differentiable Rank-Based Objective for Better Feature Learning
• CVPR 2025A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
• ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
• CVPR 2024DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
• NeurIPS 2023$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models
• ICML 2023Decoding Layer Saliency in Language Transformers
• ICLR 2023Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
• CVPR 2023A Practical Upper Bound for the Worst-Case Attribution Deviations
• NeurIPS 2026Adaptive Feature Propagation for Attribute-Missing Graph Clustering
• ICML 2026Aggregate Models, Not Explanations: Improving Feature Importance Estimation
• ICLR 2026Attribution-Guided Decoding
• CVPR 2026FBTA Enabling Single-GPU End-to-End Gigapixel WSI Classification with Feature Bridging

All Feature Attribution papers

175 papers, page 2 of 4

51. ICML 2026Step-Resolved Data Attribution for Looped Transformers
52. ICML 2026Streaming Covariate Balancing via Discrepancy-Based Feature Coresets
53. ICML 2026Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning
54. ICML 2026The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
55. ICML 2026Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
56. ICML 2026Unifying Low Dimensional Spectra in Deep Learning
57. ICML 2025A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
58. ICML 2025Active feature acquisition via explainability-driven ranking
59. ICML 2025Adaptive kernel predictors from feature-learning infinite limits of neural networks
60. ICML 2025BCE vs. CE in Deep Feature Learning
61. ICML 2025Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination
62. ICML 2025Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
63. ICML 2025Causal Attribution Analysis for Continuous Outcomes
64. ICML 2025Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
65. ICML 2025Confounder-Free Continual Learning via Recursive Feature Normalization
66. ICML 2025Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant
67. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
68. ICML 2025Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models
69. ICML 2025Feature Importance Metrics in the Presence of Missing Data
70. ICML 2025Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
71. ICML 2025Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
72. ICML 2025Feature Shift Localization Network
73. ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
74. ICML 2025Federated Learning for Feature Generalization with Convex Constraints
75. ICML 2025From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
76. ICML 2025From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
77. ICML 2025Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition
78. ICML 2025GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation
79. ICML 2025Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization
80. ICML 2025Gradient-based Explanations for Deep Learning Survival Models
81. ICML 2025Identifying and Understanding Cross-Class Features in Adversarial Training
82. ICML 2025Mahalanobis++: Improving OOD Detection via Feature Normalization
83. ICML 2025Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
84. ICML 2025No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
85. ICML 2025Nonlinear transformers can perform inference-time feature learning
86. ICML 2025On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
87. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
88. ICML 2025On the Role of Label Noise in the Feature Learning Process
89. ICML 2025One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
90. ICML 2025One-Pass Feature Evolvable Learning with Theoretical Guarantees
91. ICML 2025Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data
92. ICML 2025Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
93. ICML 2025Random Feature Representation Boosting
94. ICML 2025SAND: One-Shot Feature Selection with Additive Noise Distortion
95. ICML 2025SPEX: Scaling Feature Interaction Explanations for LLMs
96. ICML 2025Statistical Test for Feature Selection Pipelines by Selective Inference
97. ICML 2025Stochastic Encodings for Active Feature Acquisition
98. ICML 2025Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters
99. ICML 2025Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
100. ICML 2025TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments

FAQ

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

695 in total: 118 in 2023, 168 in 2024, 190 in 2025, 219 in 2026.

How many Feature Attribution papers are at NeurIPS 2026?

NeurIPS 2026 has 61 Feature Attribution papers, versus 57 the year before.

How many Feature Attribution papers are at ICLR 2026?

ICLR 2026 has 53 Feature Attribution papers, versus 42 the year before.

How many Feature Attribution papers are at ICML 2026?

ICML 2026 has 56 Feature Attribution papers, versus 51 the year before.

How many Feature Attribution papers are at CVPR 2026?

CVPR 2026 has 49 Feature Attribution papers, versus 40 the year before.

Which conference publishes the most Feature Attribution papers?

NeurIPS, with 193 papers from 2023 to 2026.