Feature Attribution papers, 2023–2026
Saliency and SHAP
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 695 papers are tagged with this topic.
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.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 25 | 29 | 21 | 43 | 118 |
| 2024 | 50 | 36 | 47 | 35 | 168 |
| 2025 | 57 | 42 | 51 | 40 | 190 |
| 2026 | 61 | 53 | 56 | 49 | 219 |
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
49 papers, page 1 of 1
- CVPR 2026A Training-Free Style-Personalization via SVD-Based Feature Decomposition
- CVPR 2026Align Once to Explain Feature Alignment for Scalable B-cosification of
- CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
- CVPR 2026Attribution as Retrieval Model-Agnostic AI-Generated Image Attribution
- CVPR 2026Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
- CVPR 2026Back to the Feature Explaining Video Classifiers with Video Counterfactual
- CVPR 2026CRFT Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
- CVPR 2026Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely
- CVPR 2026D2FANet Enhancing Video Object Detection with Dual-Domain Feature Aggregation Network
- CVPR 2026Deep Feature Deformation Weights
- CVPR 2026DisCa Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
- CVPR 2026Disentangle-then-Align Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
- CVPR 2026Domain-Skewed Federated Learning with Feature Decoupling and Calibration
- CVPR 2026ELiC Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and
- CVPR 2026FBTA Enabling Single-GPU End-to-End Gigapixel WSI Classification with Feature Bridging
- CVPR 2026FeatureFool Zero-Query Fooling of Video Models via Feature Map
- CVPR 2026Forecast the Principal Stabilize the Residual Subspace-Aware Feature Caching for
- CVPR 2026From Feature Learning to Spectral Basis Learning A Unifying and
- CVPR 2026FUSAR-GPT A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model
- CVPR 2026GazeOnce360 Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusion
- CVPR 2026H-Sets Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
- CVPR 2026H2A2 Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D
- CVPR 2026Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation
- CVPR 2026Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian
- CVPR 2026IncreFA Breaking the Static Wall of Generative Model Attribution
- CVPR 2026Is the Modality Gap a Bug or a Feature A
- CVPR 2026Learning Convex Decomposition via Feature Fields
- CVPR 2026Locate-then-Sparsify Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
- CVPR 2026MambaLiteUNet Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
- CVPR 2026Measure The Feature Universe Topology-based Pseudo Labeling and Gravity Consistency
- CVPR 2026Meta-FC Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
- CVPR 2026Mistake Attribution Fine-Grained Mistake Understanding in Egocentric Videos
- CVPR 2026Multi-Modal Image Fusion via Intervention-Stable Feature Learning
- CVPR 2026NAF Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
- CVPR 2026Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification
- CVPR 2026Post-training Feature Pruning for Fundus Images Classification
- CVPR 2026SAGA Source Attribution of Generative AI Videos
- CVPR 2026Selfi Self-improving Reconstruction Engine via 3D Geometric Feature Alignment
- CVPR 2026Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream
- CVPR 2026Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
- CVPR 2026TextFM Robust Semi-dense Feature Matching with Language Guidance
- CVPR 2026The Geometry of Robustness Optimizing Loss Landscape Curvature and Feature
- CVPR 2026TIACam Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
- CVPR 2026TokenTrace Multi-Concept Attribution through Watermarked Token Recovery
- CVPR 2026ULF-Loc Unbiased Landmark Feature for Robust Visual Localization with 3D
- CVPR 2026Unlocking Token Rewards via Training-Free Reward Attribution
- CVPR 2026UPLiFT Efficient Pixel-Dense Feature Upsampling with Local Attenders
- CVPR 2026Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidance
- CVPR 2026What Your Features Reveal Data-Efficient Black-Box Feature Inversion Attack for
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Feature Attribution papers grew at NeurIPS from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "feature-attribution"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
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.