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 992 篇，第 3 / 20 页

101. ICLR 2026KernelFusion: Zero-Shot Blind Super-Resolution via Patch Diffusion
102. ICLR 2026Learning From Dictionary: Enhancing Robustness of Machine-Generated Text Detection in Zero-Shot Language via Adversarial Training
103. ICLR 2026Learning from Label Proportions via Proportional Value Classification
104. ICLR 2026Learning to Grasp Anything By Playing with Random Toys
105. ICLR 2026Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding
106. ICLR 2026Measuring Uncertainty Calibration
107. ICLR 2026Monotone Near-Zero-Sum Games: A Generalization of Convex-Concave Minimax
108. ICLR 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval
109. ICLR 2026Object-Centric Refinement for Enhanced Zero-Shot Segmentation
110. ICLR 2026On the $O(1/T)$ Convergence of Alternating Gradient Descent–Ascent in Bilinear Games
111. ICLR 2026OWLEYE: ZERO-SHOT LEARNER FOR CROSSDOMAIN GRAPH DATA ANOMALY DETECTION
112. ICLR 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
113. ICLR 2026Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
114. ICLR 2026Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
115. ICLR 2026Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation
116. ICLR 2026Structure-Aware Graph Hypernetworks for Neural Program Synthesis
117. ICLR 2026The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
118. ICLR 2026TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
119. ICLR 2026Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
120. ICLR 2026Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification
121. ICLR 2026VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision–Language Models
122. ICLR 2026Zero-shot Forecasting by Simulation Alone
123. ICLR 2026Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition
124. ICLR 2026Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
125. ICLR 2026ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
126. ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
127. ICML 2026Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games
128. ICML 2026Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
129. ICML 2026Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation
130. ICML 2026Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
131. ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
132. ICML 2026BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
133. ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
134. ICML 2026CAOS: Conformal Aggregation of One-Shot Predictors
135. ICML 2026Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting
136. ICML 2026Class-Conditional Distribution Balancing for Group Robust Classification
137. ICML 2026CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detection
138. ICML 2026Consistent Zero-Shot Imitation with Contrastive Goal Inference
139. ICML 2026Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
140. ICML 2026Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
141. ICML 2026Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment
142. ICML 2026Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
143. ICML 2026EquiCAD: A Geometric Equivariant Neural Network for 3D Shape Classification
144. ICML 2026Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
145. ICML 2026Foundation Inference Models for Ordinary Differential Equations
146. ICML 2026From Individual Calibration to Reliable Classifiers: ALD Parameterization with mPAIC Guarantees
147. ICML 2026From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
148. ICML 2026From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
149. ICML 2026Fully Zero-Shot Image Dehazing
150. ICML 2026Granularity-Aware Adaptive Classifier Expansion via Zero-Shot 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。