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 55 篇，第 1 / 2 页

1. ICLR 2023Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
2. ICLR 2023Bidirectional Language Models Are Also Few-shot Learners
3. ICLR 2023Composing Ensembles of Pre-trained Models via Iterative Consensus
4. ICLR 2023Constraining Representations Yields Models That Know What They Don't Know
5. ICLR 2023Contrastive Meta-Learning for Partially Observable Few-Shot Learning
6. ICLR 2023CrAM: A Compression-Aware Minimizer
7. ICLR 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
8. ICLR 2023Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity
9. ICLR 2023DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training
10. ICLR 2023Decoupled Training for Long-Tailed Classification With Stochastic Representations
11. ICLR 2023Denoising Masked Autoencoders Help Robust Classification
12. ICLR 2023Dilated convolution with learnable spacings
13. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
14. ICLR 2023FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
15. ICLR 2023Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
16. ICLR 2023Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks
17. ICLR 2023Human-Guided Fair Classification for Natural Language Processing
18. ICLR 2023Improving Deep Regression with Ordinal Entropy
19. ICLR 2023Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
20. ICLR 2023Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
21. ICLR 2023Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
22. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
23. ICLR 2023Masked Unsupervised Self-training for Label-free Image Classification
24. ICLR 2023MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
25. ICLR 2023Multi-lingual Evaluation of Code Generation Models
26. ICLR 2023Mutual Partial Label Learning with Competitive Label Noise
27. ICLR 2023NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
28. ICLR 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
29. ICLR 2023Neural-based classification rule learning for sequential data
30. ICLR 2023Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization
31. ICLR 2023On the Soft-Subnetwork for Few-Shot Class Incremental Learning
32. ICLR 2023OTOv2: Automatic, Generic, User-Friendly
33. ICLR 2023Out-of-distribution Representation Learning for Time Series Classification
34. ICLR 2023Parallel Deep Neural Networks Have Zero Duality Gap
35. ICLR 2023PEER: A Collaborative Language Model
36. ICLR 2023Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
37. ICLR 2023Prototypical Calibration for Few-shot Learning of Language Models
38. ICLR 2023Relative representations enable zero-shot latent space communication
39. ICLR 2023Selective Annotation Makes Language Models Better Few-Shot Learners
40. ICLR 2023Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
41. ICLR 2023Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
42. ICLR 2023Strategic Classification with Graph Neural Networks
43. ICLR 2023TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing
44. ICLR 2023TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
45. ICLR 2023TempCLR: Temporal Alignment Representation with Contrastive Learning
46. ICLR 2023Towards Addressing Label Skews in One-Shot Federated Learning
47. ICLR 2023Towards Better Selective Classification
48. ICLR 2023UL2: Unifying Language Learning Paradigms
49. ICLR 2023Understanding Zero-shot Adversarial Robustness for Large-Scale Models
50. ICLR 2023Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?

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。