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 2 / 4 页

51. ICML 2026Universal Algorithm-Implicit Learning
52. ICML 2026Unsupervised Process-Aware Coreset Selection for In-Context Learning
53. ICML 2026URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
54. ICML 2026Weight-Space Learning for Certifiable Few-shot Transfer Learning
55. ICML 2026XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge
56. ICML 2026ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
57. ICML 2025Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
58. ICML 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
59. ICML 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
60. ICML 2025Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
61. ICML 2025CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
62. ICML 2025Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning
63. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
64. ICML 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
65. ICML 2025Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework
66. ICML 2025Feedforward Few-shot Species Range Estimation
67. ICML 2025Few-Shot Learner Generalizes Across AI-Generated Image Detection
68. ICML 2025FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
69. ICML 2025Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
70. ICML 2025GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
71. ICML 2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
72. ICML 2025On the Provable Separation of Scales in Maximal Update Parameterization
73. ICML 2025One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
74. ICML 2025PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
75. ICML 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
76. ICML 2025Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
77. ICML 2025Provable Zero-Shot Generalization in Offline Reinforcement Learning
78. ICML 2025Provably Improving Generalization of Few-shot models with Synthetic Data
79. ICML 2025Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
80. ICML 2025Random Registers for Cross-Domain Few-Shot Learning
81. ICML 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
82. ICML 2025Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective
83. ICML 2025SAND: One-Shot Feature Selection with Additive Noise Distortion
84. ICML 2025Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
85. ICML 2025Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
86. ICML 2025SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
87. ICML 2025The Missing Alignment Link of In-context Learning on Sequences
88. ICML 2025The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
89. ICML 2025Unlocking the Power of SAM 2 for Few-Shot Segmentation
90. ICML 2025Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer
91. ICML 2025Zero-Shot Offline Imitation Learning via Optimal Transport
92. ICML 2024Accelerating Convergence in Bayesian Few-Shot Classification
93. ICML 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
94. ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
95. ICML 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
96. ICML 2024Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection
97. ICML 2024Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation
98. ICML 2024Byzantine Resilient and Fast Federated Few-Shot Learning
99. ICML 2024Can a Few Decide for Many? The Metric Distortion of Sortition
100. ICML 2024Compositional Few-Shot Class-Incremental 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。