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

160 papers, page 3 of 4

101. ICLR 2024Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
102. ICLR 2024Estimating Conditional Mutual Information for Dynamic Feature Selection
103. ICLR 2024Exploring the cloud of feature interaction scores in a Rashomon set
104. ICLR 2024Feature Collapse
105. ICLR 2024Feature emergence via margin maximization: case studies in algebraic tasks
106. ICLR 2024Feature-aligned N-BEATS with Sinkhorn divergence
107. ICLR 2024Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
108. ICLR 2024GOAt: Explaining Graph Neural Networks via Graph Output Attribution
109. ICLR 2024Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
110. ICLR 2024Grokking as the transition from lazy to rich training dynamics
111. ICLR 2024Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
112. ICLR 2024Intriguing Properties of Data Attribution on Diffusion Models
113. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
114. ICLR 2024Less is More: Fewer Interpretable Region via Submodular Subset Selection
115. ICLR 2024Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
116. ICLR 2024More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
117. ICLR 2024On the Joint Interaction of Models, Data, and Features
118. ICLR 2024Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
119. ICLR 2024Path Choice Matters for Clear Attributions in Path Methods
120. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
121. ICLR 2024SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
122. ICLR 2024Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
123. ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
124. ICLR 2024Spurious Feature Diversification Improves Out-of-distribution Generalization
125. ICLR 2024Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
126. ICLR 2024Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
127. ICLR 2024Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
128. ICLR 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
129. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
130. ICLR 2024VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
131. ICLR 2024Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
132. ICLR 2023Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
133. ICLR 2023Composing Task Knowledge With Modular Successor Feature Approximators
134. ICLR 2023Confidence-Based Feature Imputation for Graphs with Partially Known Features
135. ICLR 2023Contrastive Corpus Attribution for Explaining Representations
136. ICLR 2023CoRTX: Contrastive Framework for Real-time Explanation
137. ICLR 2023Explaining RL Decisions with Trajectories
138. ICLR 2023Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks
139. ICLR 2023Feature selection and low test error in shallow low-rotation ReLU networks
140. ICLR 2023FedFA: Federated Feature Augmentation
141. ICLR 2023Fooling SHAP with Stealthily Biased Sampling
142. ICLR 2023Function-Consistent Feature Distillation
143. ICLR 2023GEASS: Neural causal feature selection for high-dimensional biological data
144. ICLR 2023Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
145. ICLR 2023Interpretability with full complexity by constraining feature information
146. ICLR 2023Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
147. ICLR 2023Learning Multimodal Data Augmentation in Feature Space
148. ICLR 2023Long-Tailed Learning Requires Feature Learning
149. ICLR 2023MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion
150. ICLR 2023Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

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.