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

57 papers, page 1 of 2

1. NeurIPS 2025A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
2. NeurIPS 2025Accelerating Feature Conformal Prediction via Taylor Approximation
3. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
4. NeurIPS 2025Approximating Shapley Explanations in Reinforcement Learning
5. NeurIPS 2025Attribution-Driven Adaptive Token Pruning for Transformers
6. NeurIPS 2025Better Training Data Attribution via Better Inverse Hessian-Vector Products
7. NeurIPS 2025BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization
8. NeurIPS 2025Beyond Last-Click: An Optimal Mechanism for Ad Attribution
9. NeurIPS 2025Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
10. NeurIPS 2025Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models
11. NeurIPS 2025Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees
12. NeurIPS 2025DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
13. NeurIPS 2025Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
14. NeurIPS 2025Demystifying Spectral Feature Learning for Instrumental Variable Regression
15. NeurIPS 2025DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
16. NeurIPS 2025Distributional Training Data Attribution: What do Influence Functions Sample?
17. NeurIPS 2025Distributionally Robust Feature Selection
18. NeurIPS 2025Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
19. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution
20. NeurIPS 2025Enhancing Training Data Attribution with Representational Optimization
21. NeurIPS 2025Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
22. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
23. NeurIPS 2025Fast Data Attribution for Text-to-Image Models
24. NeurIPS 2025Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning
25. NeurIPS 2025Feature-aware Modulation for Learning from Temporal Tabular Data
26. NeurIPS 2025Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
27. NeurIPS 2025From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
28. NeurIPS 2025GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
29. NeurIPS 2025H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
30. NeurIPS 2025Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
31. NeurIPS 2025How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model
32. NeurIPS 2025ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
33. NeurIPS 2025Inverse Methods for Missing Data Imputation
34. NeurIPS 2025JAFAR: Jack up Any Feature at Any Resolution
35. NeurIPS 2025Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
36. NeurIPS 2025On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
37. NeurIPS 2025On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
38. NeurIPS 2025OrdShap: Feature Position Importance for Sequential Black-Box Models
39. NeurIPS 2025Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning
40. NeurIPS 2025Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
41. NeurIPS 2025Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
42. NeurIPS 2025Regional Explanations: Bridging Local and Global Variable Importance
43. NeurIPS 2025Rescaled Influence Functions: Accurate Data Attribution in High Dimension
44. NeurIPS 2025Revising and Falsifying Sparse Autoencoder Feature Explanations
45. NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
46. NeurIPS 2025Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
47. NeurIPS 2025Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
48. NeurIPS 2025SHAP values via sparse Fourier representation
49. NeurIPS 2025Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
50. NeurIPS 2025Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

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.