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 223 篇，第 3 / 5 页

101. ICLR 2026Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
102. ICLR 2026OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
103. ICLR 2026One-Shot Exemplars for Class Grounding in Self-Supervised Learning
104. ICLR 2026pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
105. ICLR 2026Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning
106. ICLR 2026Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
107. ICLR 2026REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
108. ICLR 2026Retain and Adapt: Auto-Balanced Model Editing for Open-Vocabulary Object Detection under Domain Shifts
109. ICLR 2026SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
110. ICLR 2026Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
111. ICLR 2026Structure-Aware Graph Hypernetworks for Neural Program Synthesis
112. ICLR 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
113. ICLR 2026The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
114. ICLR 2026The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics
115. ICLR 2026Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting Without Disclosure
116. ICLR 2026Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification
117. ICML 2026Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
118. ICML 2026Benchmarking Dense and Indiscernible Object Counting with Blueberries
119. ICML 2026Beyond Description: Federated Adaptation via Semantic-Visual Prototype Alignment
120. ICML 2026BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework
121. ICML 2026Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform
122. ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
123. ICML 2026CAOS: Conformal Aggregation of One-Shot Predictors
124. ICML 2026Consistent Zero-Shot Imitation with Contrastive Goal Inference
125. ICML 2026Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment
126. ICML 2026DiP-G: Discrete Prompting for Graph Neural Networks
127. ICML 2026Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
128. ICML 2026Distribution Alignment for One-Shot Federated Learning via Optimal Transport
129. ICML 2026DNA: Uncovering Universal Latent Forgery Knowledge
130. ICML 2026Few-Shot Design Optimization by Exploiting Auxiliary Information
131. ICML 2026Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
132. ICML 2026Fleet: Few Shots Lead Effective AI-generated Image Detection
133. ICML 2026From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic Segmentation
134. ICML 2026Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
135. ICML 2026Harnessing Spectrum Video for Subject-Level Few-Shot and Cross-Montage EEG Generalization
136. ICML 2026Hedging on the Frontier: Learning New Tasks with Few Samples
137. ICML 2026How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
138. ICML 2026Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
139. ICML 2026Infinite Mask Diffusion for Few-Step Distillation
140. ICML 2026InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
141. ICML 2026Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies
142. ICML 2026Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems
143. ICML 2026Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible?
144. ICML 2026Meta-learning Structure-Preserving Dynamics
145. ICML 2026Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization
146. ICML 2026Motion Dynamics Learning for Few-Shot Embodied Adaptation
147. ICML 2026On the Expressive Power of Permutation-Equivariant Weight-Space Networks
148. ICML 2026One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
149. ICML 2026One-shot Conditional Sampling: MMD meets Nearest Neighbors
150. ICML 2026One-Shot Weighted Ensemble Estimation for Federated Quantile Regression: Optimal Statistical Guarantees under Heterogeneous Structured Data

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。