小样本学习论文趋势 2023–2026

主要结论

• 小样本学习论文从 2023 年的 251 篇降到 2026 年的 224 篇，热度在回落。
• CVPR 是发小样本学习论文最多的会议，2023–2026 年共 303 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 24 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的基础模型适配是 3.8 倍，小样本学习是 0.9 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 2026BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
• ICML 2026Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
• ICLR 2026Adaptive Concept Discovery for Interpretable Few-Shot Text Classification
• CVPR 2026A Closer Look at Cross-Domain Few-Shot Object Detection Fine-Tuning Matters
• NeurIPS 2025A Few Moments Please: Scalable Graphon Learning via Moment Matching
• ICML 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
• ICLR 2025Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint
• CVPR 20253D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation
• NeurIPS 2024Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
• ICML 2024Accelerating Convergence in Bayesian Few-Shot Classification
• ICLR 2024Few-shot Hybrid Domain Adaptation of Image Generator
• CVPR 2024Deformable One-shot Face Stylization via DINO Semantic Guidance
• NeurIPS 2023Alignment with human representations supports robust few-shot learning
• ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
• ICLR 2023Bidirectional Language Models Are Also Few-shot Learners
• CVPR 2023A Meta-Learning Approach to Predicting Performance and Data Requirements
• NeurIPS 2026Beyond Normal References: Discriminative Few-Shot Anomaly Detection
• ICML 2026BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework
• ICLR 2026Dual Distillation for Few-Shot Anomaly Detection
• CVPR 2026Beyond Patches Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation

全部小样本学习论文

共 251 篇，第 3 / 6 页

101. ICLR 2023Large Language Models are Human-Level Prompt Engineers
102. ICLR 2023Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
103. ICLR 2023MARS: Meta-learning as Score Matching in the Function Space
104. ICLR 2023MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
105. ICLR 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
106. ICLR 2023Meta Temporal Point Processes
107. ICLR 2023Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
108. ICLR 2023Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
109. ICLR 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
110. ICLR 2023Neural DAG Scheduling via One-Shot Priority Sampling
111. ICLR 2023On the Soft-Subnetwork for Few-Shot Class Incremental Learning
112. ICLR 2023OTOv2: Automatic, Generic, User-Friendly
113. ICLR 2023PEER: A Collaborative Language Model
114. ICLR 2023Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer
115. ICLR 2023Promptagator: Few-shot Dense Retrieval From 8 Examples
116. ICLR 2023Prototypical Calibration for Few-shot Learning of Language Models
117. ICLR 2023QAID: Question Answering Inspired Few-shot Intent Detection
118. ICLR 2023Relative representations enable zero-shot latent space communication
119. ICLR 2023Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings
120. ICLR 2023Selective Annotation Makes Language Models Better Few-Shot Learners
121. ICLR 2023Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
122. ICLR 2023Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus
123. ICLR 2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
124. ICLR 2023Suppressing the Heterogeneity: A Strong Feature Extractor for Few-shot Segmentation
125. ICLR 2023Task Ambiguity in Humans and Language Models
126. ICLR 2023TempCLR: Temporal Alignment Representation with Contrastive Learning
127. ICLR 2023Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
128. ICLR 2023Towards Addressing Label Skews in One-Shot Federated Learning
129. ICLR 2023Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case
130. ICLR 2023Transfer NAS with Meta-learned Bayesian Surrogates
131. ICLR 2023Understanding Train-Validation Split in Meta-Learning with Neural Networks
132. ICLR 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
133. ICLR 2023Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
134. ICLR 2023Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning
135. ICLR 2023ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients
136. ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
137. ICML 2023A Closer Look at Few-shot Classification Again
138. ICML 2023Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
139. ICML 2023Adaptive Compositional Continual Meta-Learning
140. ICML 2023Adaptive IMLE for Few-shot Pretraining-free Generative Modelling
141. ICML 2023Benign Overfitting in Two-layer ReLU Convolutional Neural Networks
142. ICML 2023CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
143. ICML 2023Cooperative Open-ended Learning Framework for Zero-Shot Coordination
144. ICML 2023Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
145. ICML 2023Does Continual Learning Equally Forget All Parameters?
146. ICML 2023Effective Structured Prompting by Meta-Learning and Representative Verbalizer
147. ICML 2023Efficient Training of Language Models using Few-Shot Learning
148. ICML 2023Evolving Semantic Prototype Improves Generative Zero-Shot Learning
149. ICML 2023Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
150. ICML 2023Few-Sample Feature Selection via Feature Manifold Learning

常见问题

2023–2026 年四大会议一共有多少篇小样本学习论文？

共 898 篇，按年份分别是 2023 年 251 篇、2024 年 220 篇、2025 年 203 篇、2026 年 224 篇。

NeurIPS 2026 有多少篇小样本学习论文？

NeurIPS 2026 有 51 篇小样本学习论文，上一届是 68 篇。

ICLR 2026 有多少篇小样本学习论文？

ICLR 2026 有 38 篇小样本学习论文，上一届是 36 篇。

ICML 2026 有多少篇小样本学习论文？

ICML 2026 有 56 篇小样本学习论文，上一届是 35 篇。

CVPR 2026 有多少篇小样本学习论文？

CVPR 2026 有 79 篇小样本学习论文，上一届是 64 篇。

哪个会议的小样本学习论文最多？

CVPR，2023–2026 年共 303 篇。