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 695 篇，第 1 / 14 页

1. CVPR 2026A Training-Free Style-Personalization via SVD-Based Feature Decomposition
2. CVPR 2026Align Once to Explain Feature Alignment for Scalable B-cosification of
3. CVPR 2026AlignPose Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
4. CVPR 2026Attribution as Retrieval Model-Agnostic AI-Generated Image Attribution
5. CVPR 2026Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
6. CVPR 2026Back to the Feature Explaining Video Classifiers with Video Counterfactual
7. CVPR 2026CRFT Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
8. CVPR 2026Cross-domain Dual-stream Feature Disentanglement for Brain Disorder Prediction with Sparsely
9. CVPR 2026D2FANet Enhancing Video Object Detection with Dual-Domain Feature Aggregation Network
10. CVPR 2026Deep Feature Deformation Weights
11. CVPR 2026DisCa Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
12. CVPR 2026Disentangle-then-Align Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
13. CVPR 2026Domain-Skewed Federated Learning with Feature Decoupling and Calibration
14. CVPR 2026ELiC Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and
15. CVPR 2026FBTA Enabling Single-GPU End-to-End Gigapixel WSI Classification with Feature Bridging
16. CVPR 2026FeatureFool Zero-Query Fooling of Video Models via Feature Map
17. CVPR 2026Forecast the Principal Stabilize the Residual Subspace-Aware Feature Caching for
18. CVPR 2026From Feature Learning to Spectral Basis Learning A Unifying and
19. CVPR 2026FUSAR-GPT A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model
20. CVPR 2026GazeOnce360 Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusion
21. CVPR 2026H-Sets Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
22. CVPR 2026H2A2 Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D
23. CVPR 2026Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation
24. CVPR 2026Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian
25. CVPR 2026IncreFA Breaking the Static Wall of Generative Model Attribution
26. CVPR 2026Is the Modality Gap a Bug or a Feature A
27. CVPR 2026Learning Convex Decomposition via Feature Fields
28. CVPR 2026Locate-then-Sparsify Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
29. CVPR 2026MambaLiteUNet Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
30. CVPR 2026Measure The Feature Universe Topology-based Pseudo Labeling and Gravity Consistency
31. CVPR 2026Meta-FC Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
32. CVPR 2026Mistake Attribution Fine-Grained Mistake Understanding in Egocentric Videos
33. CVPR 2026Multi-Modal Image Fusion via Intervention-Stable Feature Learning
34. CVPR 2026NAF Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
35. CVPR 2026Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification
36. CVPR 2026Post-training Feature Pruning for Fundus Images Classification
37. CVPR 2026SAGA Source Attribution of Generative AI Videos
38. CVPR 2026Selfi Self-improving Reconstruction Engine via 3D Geometric Feature Alignment
39. CVPR 2026Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream
40. CVPR 2026Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
41. CVPR 2026TextFM Robust Semi-dense Feature Matching with Language Guidance
42. CVPR 2026The Geometry of Robustness Optimizing Loss Landscape Curvature and Feature
43. CVPR 2026TIACam Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
44. CVPR 2026TokenTrace Multi-Concept Attribution through Watermarked Token Recovery
45. CVPR 2026ULF-Loc Unbiased Landmark Feature for Robust Visual Localization with 3D
46. CVPR 2026Unlocking Token Rewards via Training-Free Reward Attribution
47. CVPR 2026UPLiFT Efficient Pixel-Dense Feature Upsampling with Local Attenders
48. CVPR 2026Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidance
49. CVPR 2026What Your Features Reveal Data-Efficient Black-Box Feature Inversion Attack for
50. ICLR 2026$\boldsymbol{\partial^\infty}$-Grid: A Neural Differential Equation Solver with Differentiable Feature Grids

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。