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

695 papers, page 4 of 14

151. ICML 2026Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
152. ICML 2026SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
153. ICML 2026Step-Resolved Data Attribution for Looped Transformers
154. ICML 2026Streaming Covariate Balancing via Discrepancy-Based Feature Coresets
155. ICML 2026Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning
156. ICML 2026The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
157. ICML 2026Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
158. ICML 2026Unifying Low Dimensional Spectra in Deep Learning
159. NeurIPS 2026ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
160. NeurIPS 2026ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
161. NeurIPS 2026Adaptive Feature Propagation for Attribute-Missing Graph Clustering
162. NeurIPS 2026Attribution-Guided Exit Policy for Reliable Early-Exit Inference
163. NeurIPS 2026Avoiding Feature Collapse in Graph ODEs via Hysteretic Topology Evolution
164. NeurIPS 2026Boundary Mass in Feature Space as a Label-Budget Diagnostic for Representations
165. NeurIPS 2026Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes
166. NeurIPS 2026Calibrating Generative Models to Feature Distributions with MMD Finetuning
167. NeurIPS 2026Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
168. NeurIPS 2026Decomposing Conformal Uncertainty: Calibration- and Instance-Driven Feature Attribution
169. NeurIPS 2026Designing Kernel Surrogate Models for Multimodal Attribution
170. NeurIPS 2026DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
171. NeurIPS 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
172. NeurIPS 2026EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation
173. NeurIPS 2026Efficient Benchmarking Is Just Feature Selection and Multiple Regression
174. NeurIPS 2026ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP
175. NeurIPS 2026Feature Information Dynamics in Diffusion
176. NeurIPS 2026Federated Logic Gate Networks via Boolean Feature Selection
177. NeurIPS 2026FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
178. NeurIPS 2026FM-ChangeNet: Learning Change through Pathwise Feature Transport
179. NeurIPS 2026Forward Shapley Scoring for Non-Myopic Active Feature Acquisition
180. NeurIPS 2026FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry
181. NeurIPS 2026From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
182. NeurIPS 2026From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment
183. NeurIPS 2026GraphUAT: Uncertainty Attribution in Graph Neural Networks
184. NeurIPS 2026haphazard: A unified library and benchmark for online learning under varying feature availability
185. NeurIPS 2026How does feature learning change the function space evolution?
186. NeurIPS 2026Hypernetworks for Dynamic Feature Selection
187. NeurIPS 2026Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
188. NeurIPS 2026In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL
189. NeurIPS 2026Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
190. NeurIPS 2026Intrinsically Interpretable Attention via Sparse Post-Training
191. NeurIPS 2026Invariant Features in Language Models: Geometric Characterization and Model Attribution
192. NeurIPS 2026Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
193. NeurIPS 2026LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection
194. NeurIPS 2026Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
195. NeurIPS 2026Panoptic Saliency Ranking
196. NeurIPS 2026PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations
197. NeurIPS 2026quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
198. NeurIPS 2026Reading Attribution from Attention: Evidence Heads as Latent Attribution Mechanisms in LLMs
199. NeurIPS 2026Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation
200. NeurIPS 2026Residual Calibration via Local Feature-Space Refinement

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.