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 168 篇，第 3 / 4 页

101. ICLR 2024One-shot Empirical Privacy Estimation for Federated Learning
102. ICLR 2024Overthinking the Truth: Understanding how Language Models Process False Demonstrations
103. ICLR 2024Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
104. ICLR 2024Personalize Segment Anything Model with One Shot
105. ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
106. ICLR 2024Scalable Language Model with Generalized Continual Learning
107. ICLR 2024Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
108. ICLR 2024TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
109. ICLR 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
110. ICLR 2024Zero and Few-shot Semantic Parsing with Ambiguous Inputs
111. ICLR 2024Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
112. ICLR 2024Zero-Shot Robustification of Zero-Shot Models
113. ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
114. ICLR 2023AANG : Automating Auxiliary Learning
115. ICLR 2023Analogy-Forming Transformers for Few-Shot 3D Parsing
116. ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
117. ICLR 2023Bidirectional Language Models Are Also Few-shot Learners
118. ICLR 2023Composing Ensembles of Pre-trained Models via Iterative Consensus
119. ICLR 2023Context-enriched molecule representations improve few-shot drug discovery
120. ICLR 2023Contrastive Meta-Learning for Partially Observable Few-Shot Learning
121. ICLR 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
122. ICLR 2023Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity
123. ICLR 2023Decomposed Prompting: A Modular Approach for Solving Complex Tasks
124. ICLR 2023Distributional Meta-Gradient Reinforcement Learning
125. ICLR 2023Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
126. ICLR 2023Few-shot Backdoor Attacks via Neural Tangent Kernels
127. ICLR 2023Few-Shot Domain Adaptation For End-to-End Communication
128. ICLR 2023FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
129. ICLR 2023Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
130. ICLR 2023Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks
131. ICLR 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs
132. ICLR 2023Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion
133. ICLR 2023Improving Out-of-distribution Generalization with Indirection Representations
134. ICLR 2023Large Language Models are Human-Level Prompt Engineers
135. ICLR 2023Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
136. ICLR 2023MARS: Meta-learning as Score Matching in the Function Space
137. ICLR 2023MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
138. ICLR 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
139. ICLR 2023Meta Temporal Point Processes
140. ICLR 2023Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
141. ICLR 2023Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
142. ICLR 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
143. ICLR 2023Neural DAG Scheduling via One-Shot Priority Sampling
144. ICLR 2023On the Soft-Subnetwork for Few-Shot Class Incremental Learning
145. ICLR 2023OTOv2: Automatic, Generic, User-Friendly
146. ICLR 2023PEER: A Collaborative Language Model
147. ICLR 2023Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer
148. ICLR 2023Promptagator: Few-shot Dense Retrieval From 8 Examples
149. ICLR 2023Prototypical Calibration for Few-shot Learning of Language Models
150. ICLR 2023QAID: Question Answering Inspired Few-shot Intent Detection

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。