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

193 papers, page 2 of 4

51. NeurIPS 2026TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
52. NeurIPS 2026Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
53. NeurIPS 2026The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature Learning
54. NeurIPS 2026The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
55. NeurIPS 2026Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
56. NeurIPS 2026Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs
57. NeurIPS 2026Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction
58. NeurIPS 2026Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution
59. NeurIPS 2026What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
60. NeurIPS 2026When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
61. NeurIPS 2026Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
62. NeurIPS 2025A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
63. NeurIPS 2025Accelerating Feature Conformal Prediction via Taylor Approximation
64. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
65. NeurIPS 2025Approximating Shapley Explanations in Reinforcement Learning
66. NeurIPS 2025Attribution-Driven Adaptive Token Pruning for Transformers
67. NeurIPS 2025Better Training Data Attribution via Better Inverse Hessian-Vector Products
68. NeurIPS 2025BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
69. NeurIPS 2025Beyond Last-Click: An Optimal Mechanism for Ad Attribution
70. NeurIPS 2025Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
71. NeurIPS 2025Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
72. NeurIPS 2025Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees
73. NeurIPS 2025DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
74. NeurIPS 2025Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
75. NeurIPS 2025Demystifying Spectral Feature Learning for Instrumental Variable Regression
76. NeurIPS 2025DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
77. NeurIPS 2025Distributional Training Data Attribution: What do Influence Functions Sample?
78. NeurIPS 2025Distributionally Robust Feature Selection
79. NeurIPS 2025Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
80. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution
81. NeurIPS 2025Enhancing Training Data Attribution with Representational Optimization
82. NeurIPS 2025Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
83. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
84. NeurIPS 2025Fast Data Attribution for Text-to-Image Models
85. NeurIPS 2025Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning
86. NeurIPS 2025Feature-aware Modulation for Learning from Temporal Tabular Data
87. NeurIPS 2025Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
88. NeurIPS 2025From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
89. NeurIPS 2025GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
90. NeurIPS 2025H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
91. NeurIPS 2025Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
92. NeurIPS 2025How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
93. NeurIPS 2025ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
94. NeurIPS 2025Inverse Methods for Missing Data Imputation
95. NeurIPS 2025JAFAR: Jack up Any Feature at Any Resolution
96. NeurIPS 2025Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
97. NeurIPS 2025On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
98. NeurIPS 2025On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
99. NeurIPS 2025OrdShap: Feature Position Importance for Sequential Black-Box Models
100. NeurIPS 2025Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning

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.