特征归因论文趋势 2023–2026

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。

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 168 篇，第 4 / 4 页

151. NeurIPS 2024Parallel Backpropagation for Shared-Feature Visualization
152. NeurIPS 2024Personalized Federated Learning via Feature Distribution Adaptation
153. NeurIPS 2024Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
154. NeurIPS 2024Provable Benefit of Cutout and CutMix for Feature Learning
155. NeurIPS 2024ProxyFusion: Face Feature Aggregation Through Sparse Experts
156. NeurIPS 2024shapiq: Shapley Interactions for Machine Learning
157. NeurIPS 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
158. NeurIPS 2024SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis
159. NeurIPS 2024Symmetries in Overparametrized Neural Networks: A Mean Field View
160. NeurIPS 2024The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
161. NeurIPS 2024The Prevalence of Neural Collapse in Neural Multivariate Regression
162. NeurIPS 2024To Learn or Not to Learn, That is the Question — A Feature-Task Dual Learning Model of Perceptual Learning
163. NeurIPS 2024Training Data Attribution via Approximate Unrolling
164. NeurIPS 2024Understanding Visual Feature Reliance through the Lens of Complexity
165. NeurIPS 2024Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
166. NeurIPS 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
167. NeurIPS 2024Where Do Large Learning Rates Lead Us?
168. NeurIPS 2024You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection

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。