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 2 of 14

51. ICLR 2026$\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed Generalization
52. ICLR 2026ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
53. ICLR 2026Adaptive Regularization for Large-Scale Sparse Feature Embedding Models
54. ICLR 2026AnyUp: Universal Feature Upsampling
55. ICLR 2026Attribution-Guided Decoding
56. ICLR 2026Bayesian Influence Functions for Hessian-Free Data Attribution
57. ICLR 2026Bridging Input Feature Spaces Towards Graph Foundation Models
58. ICLR 2026COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics
59. ICLR 2026Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution
60. ICLR 2026Correlations in the Data Lead to Semantically Rich Feature Geometry Under Superposition
61. ICLR 2026Dissecting Representation Misalignment in Contrastive Learning via Influence Function
62. ICLR 2026DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration
63. ICLR 2026Evaluating Data Influence in Meta Learning
64. ICLR 2026Evolution of Concepts in Language Model Pre-Training
65. ICLR 2026Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products
66. ICLR 2026f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
67. ICLR 2026FACT: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
68. ICLR 2026Faithfulness Under the Distribution: A New Look at Attribution Evaluation
69. ICLR 2026Feature compression is the root cause of adversarial fragility in neural networks
70. ICLR 2026FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
71. ICLR 2026Flow-Disentangled Feature Importance
72. ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
73. ICLR 2026Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs
74. ICLR 2026Influence Dynamics and Stagewise Data Attribution
75. ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
76. ICLR 2026Learning to Weight Parameters for Training Data Attribution
77. ICLR 2026Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
78. ICLR 2026Let OOD Feature Exploring Vast Predefined Classifiers
79. ICLR 2026Missingness Bias Calibration in Feature Attribution Explanations
80. ICLR 2026Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity
81. ICLR 2026Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
82. ICLR 2026NIMO: a Nonlinear Interpretable MOdel
83. ICLR 2026Online time series prediction using feature adjustment
84. ICLR 2026Relational Feature Caching for Accelerating Diffusion Transformers
85. ICLR 2026Residual Feature Integration is Sufficient to Prevent Negative Transfer
86. ICLR 2026Scaling Attention via Feature Sparsity
87. ICLR 2026Segment-Level Attribution for Selective Learning of Long Reasoning Traces
88. ICLR 2026Splat Feature Solver
89. ICLR 2026Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaption
90. ICLR 2026Tackling the XAI Disagreement Problem with Adaptive Feature Grouping
91. ICLR 2026Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse Autoencoders
92. ICLR 2026Temporal superposition and feature geometry of RNNs under memory demands
93. ICLR 2026Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution
94. ICLR 2026TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATION
95. ICLR 2026Transfer Learning in Infinite Width Feature Learning Networks
96. ICLR 2026Trapped by simplicity: When Transformers fail to learn from noisy features
97. ICLR 2026TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees
98. ICLR 2026ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional Views
99. ICLR 2026Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
100. ICLR 2026Untraceable DeepFakes via Traceable Fingerprint Elimination

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.