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 192 篇，第 3 / 4 页

101. ICML 2025Runtime Analysis of Evolutionary NAS for Multiclass Classification
102. ICML 2025SAND: One-Shot Feature Selection with Additive Noise Distortion
103. ICML 2025Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
104. ICML 2025Towards Learning to Complete Anything in Lidar
105. ICML 2025VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
106. ICML 2025When Do LLMs Help With Node Classification? A Comprehensive Analysis
107. ICML 2025Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices
108. ICML 2025Zero Shot Generalization of Vision-Based RL Without Data Augmentation
109. ICML 2025Zero-Inflated Bandits
110. ICML 2025Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
111. ICML 2025Zero-Shot Generalization of GNNs over Distinct Attribute Domains
112. ICML 2025Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer
113. ICML 2025Zero-Shot Offline Imitation Learning via Optimal Transport
114. ICML 2024$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy
115. ICML 2024Accelerating Convergence in Bayesian Few-Shot Classification
116. ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
117. ICML 2024Automated Loss function Search for Class-imbalanced Node Classification
118. ICML 2024Benign Overfitting in Adversarial Training of Neural Networks
119. ICML 2024Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
120. ICML 2024Classification Under Strategic Self-Selection
121. ICML 2024Compositional Few-Shot Class-Incremental Learning
122. ICML 2024Confidence-aware Contrastive Learning for Selective Classification
123. ICML 2024Consistent Adversarially Robust Linear Classification: Non-Parametric Setting
124. ICML 2024Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods
125. ICML 2024DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
126. ICML 2024Early Time Classification with Accumulated Accuracy Gap Control
127. ICML 2024Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer
128. ICML 2024Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
129. ICML 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
130. ICML 2024How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
131. ICML 2024HyperFields: Towards Zero-Shot Generation of NeRFs from Text
132. ICML 2024Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition
133. ICML 2024Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
134. ICML 2024Learning to Route Among Specialized Experts for Zero-Shot Generalization
135. ICML 2024Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
136. ICML 2024MD tree: a model-diagnostic tree grown on loss landscape
137. ICML 2024Meta Evidential Transformer for Few-Shot Open-Set Recognition
138. ICML 2024MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
139. ICML 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
140. ICML 2024Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization
141. ICML 2024No Dimensional Sampling Coresets for Classification
142. ICML 2024One Meta-tuned Transformer is What You Need for Few-shot Learning
143. ICML 2024One-Shot Strategic Classification Under Unknown Costs
144. ICML 2024PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
145. ICML 2024Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
146. ICML 2024Prompt-based Visual Alignment for Zero-shot Policy Transfer
147. ICML 2024Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models
148. ICML 2024QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning
149. ICML 2024Restoring balance: principled under/oversampling of data for optimal classification
150. ICML 2024Robust Classification via a Single Diffusion Model

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。