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 64 篇，第 1 / 2 页

1. ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
2. ICML 2026Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
3. ICML 2026Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
4. ICML 2026Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation
5. ICML 2026Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
6. ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
7. ICML 2026BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
8. ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
9. ICML 2026CAOS: Conformal Aggregation of One-Shot Predictors
10. ICML 2026Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting
11. ICML 2026Class-Conditional Distribution Balancing for Group Robust Classification
12. ICML 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detection
13. ICML 2026Consistent Zero-Shot Imitation with Contrastive Goal Inference
14. ICML 2026Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
15. ICML 2026Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
16. ICML 2026Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment
17. ICML 2026Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
18. ICML 2026EquiCAD: A Geometric Equivariant Neural Network for 3D Shape Classification
19. ICML 2026Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
20. ICML 2026Foundation Inference Models for Ordinary Differential Equations
21. ICML 2026From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC Guarantees
22. ICML 2026From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
23. ICML 2026From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
24. ICML 2026Fully Zero-Shot Image Dehazing
25. ICML 2026Granularity-Aware Adaptive Classifier Expansion via Zero-Shot Learning
26. ICML 2026HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
27. ICML 2026Improving Zero-Shot Offline RL via Behavioral Task Sampling
28. ICML 2026InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
29. ICML 2026Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision–Language Models
30. ICML 2026Klein Hyperbolic Metric Learning
31. ICML 2026Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization’s Impact on VLMs Beyond Accuracy
32. ICML 2026Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems
33. ICML 2026Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
34. ICML 2026MusicDET: Zero-Shot AI-Generated Music Detection
35. ICML 2026Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
36. ICML 2026Offline Two-Player Zero-Sum Markov Games with KL Regularization
37. ICML 2026On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
38. ICML 2026OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection
39. ICML 2026Prompt Tuning for CLIP on the Pretrained Manifold
40. ICML 2026Protein Autoregressive Modeling via Multiscale Structure Generation
41. ICML 2026PSMix: Robust Point Cloud Recognition through Spectral Domain Mixing
42. ICML 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
43. ICML 2026Scaling depth capacity via zero/one-layer model expansion
44. ICML 2026scCBGM: Single-Cell Editing via Concept Bottlenecks
45. ICML 2026Segment Anything with Robust Uncertainty-Accuracy Correlation
46. ICML 2026SGERA: Stein-Guided ECG-Report Alignment for ECG Representation Learning
47. ICML 2026Stabilizing Equation Learning via Zero-Point Constraints
48. ICML 2026Stage-wise Distortion–Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
49. ICML 2026Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability
50. ICML 2026Test-time Generalization for Physics through Neural Operator Splitting

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。