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 3 / 6 页

101. ICLR 2024From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
102. ICLR 2024GAIA: Zero-shot Talking Avatar Generation
103. ICLR 2024Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
104. ICLR 2024GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
105. ICLR 2024Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
106. ICLR 2024Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
107. ICLR 2024Intriguing Properties of Generative Classifiers
108. ICLR 2024Label-free Node Classification on Graphs with Large Language Models (LLMs)
109. ICLR 2024Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
110. ICLR 2024Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
111. ICLR 2024Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
112. ICLR 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
113. ICLR 2024One For All: Towards Training One Graph Model For All Classification Tasks
114. ICLR 2024PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
115. ICLR 2024PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
116. ICLR 2024Prompt Learning with Quaternion Networks
117. ICLR 2024R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
118. ICLR 2024Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
119. ICLR 2024ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
120. ICLR 2024SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
121. ICLR 2024Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
122. ICLR 2024Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
123. ICLR 2024The optimality of kernel classifiers in Sobolev space
124. ICLR 2024Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
125. ICLR 2024ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
126. ICLR 2024Zero Bubble (Almost) Pipeline Parallelism
127. ICLR 2024Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
128. ICLR 2024Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models
129. ICLR 2024Zero-Shot Robustification of Zero-Shot Models
130. ICML 2024$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy
131. ICML 2024Accelerating Convergence in Bayesian Few-Shot Classification
132. ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
133. ICML 2024Automated Loss function Search for Class-imbalanced Node Classification
134. ICML 2024Benign Overfitting in Adversarial Training of Neural Networks
135. ICML 2024Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
136. ICML 2024Classification Under Strategic Self-Selection
137. ICML 2024Compositional Few-Shot Class-Incremental Learning
138. ICML 2024Confidence-aware Contrastive Learning for Selective Classification
139. ICML 2024Consistent Adversarially Robust Linear Classification: Non-Parametric Setting
140. ICML 2024Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods
141. ICML 2024DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
142. ICML 2024Early Time Classification with Accumulated Accuracy Gap Control
143. ICML 2024Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer
144. ICML 2024Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
145. ICML 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
146. ICML 2024How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
147. ICML 2024HyperFields: Towards Zero-Shot Generation of NeRFs from Text
148. ICML 2024Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition
149. ICML 2024Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
150. ICML 2024Learning to Route Among Specialized Experts for Zero-Shot Generalization

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。