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 82 篇，第 1 / 2 页

1. NeurIPS 2024$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
2. NeurIPS 2024A Foundation Model for Zero-shot Logical Query Reasoning
3. NeurIPS 2024ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
4. NeurIPS 2024An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
5. NeurIPS 2024AutoMix: Automatically Mixing Language Models
6. NeurIPS 2024AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
7. NeurIPS 2024BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
8. NeurIPS 2024BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
9. NeurIPS 2024Bridge the Modality and Capability Gaps in Vision-Language Model Selection
10. NeurIPS 2024Building a stable classifier with the inflated argmax
11. NeurIPS 2024Building Timeseries Dataset: Empowering Large-Scale Building Analytics
12. NeurIPS 2024Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
13. NeurIPS 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
14. NeurIPS 2024Classification Diffusion Models: Revitalizing Density Ratio Estimation
15. NeurIPS 2024Combining Observational Data and Language for Species Range Estimation
16. NeurIPS 2024Confidence Calibration of Classifiers with Many Classes
17. NeurIPS 2024Conformal Classification with Equalized Coverage for Adaptively Selected Groups
18. NeurIPS 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
19. NeurIPS 2024CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
20. NeurIPS 2024DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
21. NeurIPS 2024Distributional Successor Features Enable Zero-Shot Policy Optimization
22. NeurIPS 2024Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
23. NeurIPS 2024EEVR: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation Learning
24. NeurIPS 2024Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
25. NeurIPS 2024EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
26. NeurIPS 2024EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
27. NeurIPS 2024Facilitating Multimodal Classification via Dynamically Learning Modality Gap
28. NeurIPS 2024Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
29. NeurIPS 2024Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
30. NeurIPS 2024Fast Rates for Bandit PAC Multiclass Classification
31. NeurIPS 2024Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
32. NeurIPS 2024Foundation Inference Models for Markov Jump Processes
33. NeurIPS 2024GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
34. NeurIPS 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Models
35. NeurIPS 2024Hierarchical Selective Classification
36. NeurIPS 2024How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
37. NeurIPS 2024Implicit Bias of Mirror Flow on Separable Data
38. NeurIPS 2024Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
39. NeurIPS 2024Instance-adaptive Zero-shot Chain-of-Thought Prompting
40. NeurIPS 2024InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
41. NeurIPS 2024Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
42. NeurIPS 2024Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
43. NeurIPS 2024Listenable Maps for Zero-Shot Audio Classifiers
44. NeurIPS 2024LLM-based Skill Diffusion for Zero-shot Policy Adaptation
45. NeurIPS 2024LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
46. NeurIPS 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Data
47. NeurIPS 2024Masked Pre-training Enables Universal Zero-shot Denoiser
48. NeurIPS 2024Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
49. NeurIPS 2024Model-Based Transfer Learning for Contextual Reinforcement Learning
50. NeurIPS 2024Multiclass Transductive Online Learning

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。