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 262 篇，第 2 / 6 页

51. CVPR 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation
52. CVPR 2024Multiplane Prior Guided Few-Shot Aerial Scene Rendering
53. CVPR 2024Named Entity Driven Zero-Shot Image Manipulation
54. CVPR 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priors
55. CVPR 2024On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?
56. CVPR 2024Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
57. CVPR 2024Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
58. CVPR 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
59. CVPR 2024ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
60. CVPR 2024Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning
61. CVPR 2024SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
62. CVPR 2024Simple Semantic-Aided Few-Shot Learning
63. CVPR 2024Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer
64. CVPR 2024Test-Time Zero-Shot Temporal Action Localization
65. CVPR 2024TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
66. CVPR 2024Transductive Zero-Shot and Few-Shot CLIP
67. CVPR 2024Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
68. CVPR 2024UniDepth: Universal Monocular Metric Depth Estimation
69. CVPR 2024Unified Language-driven Zero-shot Domain Adaptation
70. CVPR 2024VidToMe: Video Token Merging for Zero-Shot Video Editing
71. CVPR 2024Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding
72. CVPR 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning
73. CVPR 2024VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment
74. CVPR 2024Z*: Zero-shot Style Transfer via Attention Reweighting
75. CVPR 2024ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting
76. CVPR 2024ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images
77. CVPR 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
78. CVPR 2024Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions
79. CVPR 2024Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping
80. CVPR 2024Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
81. CVPR 2024ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
82. CVPR 2024ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining
83. CVPR 2024ZeroShape: Regression-based Zero-shot Shape Reconstruction
84. CVPR 2024ZONE: Zero-Shot Instruction-Guided Local Editing
85. ICLR 2024AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
86. ICLR 2024ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
87. ICLR 2024AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
88. ICLR 2024BECLR: Batch Enhanced Contrastive Few-Shot Learning
89. ICLR 2024CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
90. ICLR 2024Classification with Conceptual Safeguards
91. ICLR 2024Consistency-guided Prompt Learning for Vision-Language Models
92. ICLR 2024DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
93. ICLR 2024Empirical Likelihood for Fair Classification
94. ICLR 2024Enhancing Instance-Level Image Classification with Set-Level Labels
95. ICLR 2024Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
96. ICLR 2024FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
97. ICLR 2024Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
98. ICLR 2024Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
99. ICLR 2024Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
100. ICLR 2024Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

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。