特征归因论文趋势 2023–2026
Saliency 与 SHAP
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 695 篇被归入该主题的论文。
主要结论
- 特征归因论文从 2023 年的 118 篇增长到 2026 年的 219 篇，三年间扩大到约 1.9 倍。
- NeurIPS 是发特征归因论文最多的会议，2023–2026 年共 193 篇，占四个会议总量的 28%。
- 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 14 篇。
- 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的机制解释是 8.1 倍，特征归因是 1.9 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 25 | 29 | 21 | 43 | 118 |
| 2024 | 50 | 36 | 47 | 35 | 168 |
| 2025 | 57 | 42 | 51 | 40 | 190 |
| 2026 | 61 | 53 | 56 | 49 | 219 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- 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
全部特征归因论文
共 219 篇，第 5 / 5 页
- NeurIPS 2026Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection
- NeurIPS 2026Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
- NeurIPS 2026ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
- NeurIPS 2026Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
- NeurIPS 2026SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
- NeurIPS 2026Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
- NeurIPS 2026Spectral Insights from the Unconstrained Feature Model for Neural Multi-Output Regression
- NeurIPS 2026Strategic Feature Selection and Regularization
- NeurIPS 2026TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
- NeurIPS 2026Temporal Prototype Alignment for Frozen-Feature Dataset Distillation
- NeurIPS 2026The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature Learning
- NeurIPS 2026The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
- NeurIPS 2026Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
- NeurIPS 2026Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs
- NeurIPS 2026Training-Free 3D Editing via Feature-Divergence Localization and Trajectory Correction
- NeurIPS 2026Utility-Driven Clustered Federated Learning via Class-wise Interaction Attribution
- NeurIPS 2026What Does a Sparse Autoencoder Feature Do? A Weight-Based Account
- NeurIPS 2026When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
- NeurIPS 2026Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查特征归因在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "feature-attribution"}
常见问题
- 2023–2026 年四大会议一共有多少篇特征归因论文？
- 共 695 篇，按年份分别是 2023 年 118 篇、2024 年 168 篇、2025 年 190 篇、2026 年 219 篇。
- NeurIPS 2026 有多少篇特征归因论文？
- NeurIPS 2026 有 61 篇特征归因论文，上一届是 57 篇。
- ICLR 2026 有多少篇特征归因论文？
- ICLR 2026 有 53 篇特征归因论文，上一届是 42 篇。
- ICML 2026 有多少篇特征归因论文？
- ICML 2026 有 56 篇特征归因论文，上一届是 51 篇。
- CVPR 2026 有多少篇特征归因论文？
- CVPR 2026 有 49 篇特征归因论文，上一届是 40 篇。
- 哪个会议的特征归因论文最多？
- NeurIPS，2023–2026 年共 193 篇。