零样本分类论文趋势 2023–2026

主要结论

• 零样本分类论文从 2023 年的 203 篇增长到 2026 年的 257 篇，三年间扩大到约 1.3 倍。
• CVPR 是发零样本分类论文最多的会议，2023–2026 年共 318 篇，占四个会议总量的 32%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 22 篇。
• 在「开放词汇视觉」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的视觉定位是 4.3 倍，零样本分类是 1.3 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 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
• ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
• ICLR 2026Boomerang Distillation Enables Zero-Shot Model Size Interpolation
• CVPR 2026AG-VAS Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
• NeurIPS 2025\(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
• CVPR 2025AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP
• NeurIPS 2024BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
• ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
• ICLR 2024AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
• CVPR 2024Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
• NeurIPS 2023Black-box Backdoor Defense via Zero-shot Image Purification
• ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
• ICLR 2023Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
• CVPR 2023(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning
• NeurIPS 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
• ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• ICLR 2026Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot Learning
• CVPR 2026DLVP-CLIP Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual

全部零样本分类论文

共 49 篇，第 1 / 1 页

1. ICML 2025A Classification View on Meta Learning Bandits
2. ICML 2025A Generalization Theory for Zero-Shot Prediction
3. ICML 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
4. ICML 2025Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
5. ICML 2025CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
6. ICML 2025Conformity Score Averaging for Classification
7. ICML 2025DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
8. ICML 2025Discovering a Zero (Zero-Vector Class of Machine Learning)
9. ICML 2025DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
10. ICML 2025Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech
11. ICML 2025EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
12. ICML 2025ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
13. ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
14. ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
15. ICML 2025Fine-Grained Captioning of Long Videos through Scene Graph Consolidation
16. ICML 2025Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models
17. ICML 2025GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
18. ICML 2025Implicit Subgraph Neural Network
19. ICML 2025Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
20. ICML 2025Learning from True-False Labels via Multi-modal Prompt Retrieving
21. ICML 2025Learning Imbalanced Data with Beneficial Label Noise
22. ICML 2025Maximum Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators
23. ICML 2025Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
24. ICML 2025NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
25. ICML 2025Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment
26. ICML 2025On the Provable Separation of Scales in Maximal Update Parameterization
27. ICML 2025One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
28. ICML 2025Online Linear Classification with Massart Noise
29. ICML 2025PAC-Bayes Analysis for Recalibration in Classification
30. ICML 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
31. ICML 2025Proto Successor Measure: Representing the Behavior Space of an RL Agent
32. ICML 2025Provable Zero-Shot Generalization in Offline Reinforcement Learning
33. ICML 2025Provably Improving Generalization of Few-shot models with Synthetic Data
34. ICML 2025Random Registers for Cross-Domain Few-Shot Learning
35. ICML 2025Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective
36. ICML 2025Robust Automatic Modulation Classification with Fuzzy Regularization
37. ICML 2025Runtime Analysis of Evolutionary NAS for Multiclass Classification
38. ICML 2025SAND: One-Shot Feature Selection with Additive Noise Distortion
39. ICML 2025Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
40. ICML 2025Towards Learning to Complete Anything in Lidar
41. ICML 2025VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
42. ICML 2025When Do LLMs Help With Node Classification? A Comprehensive Analysis
43. ICML 2025Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices
44. ICML 2025Zero Shot Generalization of Vision-Based RL Without Data Augmentation
45. ICML 2025Zero-Inflated Bandits
46. ICML 2025Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
47. ICML 2025Zero-Shot Generalization of GNNs over Distinct Attribute Domains
48. ICML 2025Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer
49. ICML 2025Zero-Shot Offline Imitation Learning via Optimal Transport

常见问题

2023–2026 年四大会议一共有多少篇零样本分类论文？

共 992 篇，按年份分别是 2023 年 203 篇、2024 年 262 篇、2025 年 270 篇、2026 年 257 篇。

NeurIPS 2026 有多少篇零样本分类论文？

NeurIPS 2026 有 68 篇零样本分类论文，上一届是 86 篇。

ICLR 2026 有多少篇零样本分类论文？

ICLR 2026 有 44 篇零样本分类论文，上一届是 56 篇。

ICML 2026 有多少篇零样本分类论文？

ICML 2026 有 64 篇零样本分类论文，上一届是 49 篇。

CVPR 2026 有多少篇零样本分类论文？

CVPR 2026 有 81 篇零样本分类论文，上一届是 79 篇。

哪个会议的零样本分类论文最多？

CVPR，2023–2026 年共 318 篇。