Few-Shot Learning papers, 2023–2026

Key findings

• Few-Shot Learning fell from 251 papers in 2023 to 224 in 2026, so interest is cooling.
• CVPR publishes the most Few-Shot Learning work: 303 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 4 in 2023 to 24 in 2026.
• Among the 5 topics under Meta-Learning and Transfer, it ranks #4 by 2026 paper count; the fastest grower in the group, Foundation Model Adaptation, is up 3.8x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Few-Shot Learning papers

203 papers, page 4 of 5

151. NeurIPS 2025FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization
152. NeurIPS 2025Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
153. NeurIPS 2025GLVD: Guided Learned Vertex Descent
154. NeurIPS 2025Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
155. NeurIPS 2025Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
156. NeurIPS 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
157. NeurIPS 2025InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
158. NeurIPS 2025L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias
159. NeurIPS 2025Learning to Learn with Contrastive Meta-Objective
160. NeurIPS 2025Learning to Rank for In-Context Example Retrieval
161. NeurIPS 2025MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification
162. NeurIPS 2025Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
163. NeurIPS 2025MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
164. NeurIPS 2025MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention
165. NeurIPS 2025Multi-Modal Interactive Agent Layer for Few-Shot Universal Cross-Domain Retrieval and Beyond
166. NeurIPS 2025Multi-Objective One-Shot Pruning for Large Language Models
167. NeurIPS 2025Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
168. NeurIPS 2025NormFit: A Lightweight Solution for Few-Shot Federated Learning with Non-IID Data
169. NeurIPS 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
170. NeurIPS 2025One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
171. NeurIPS 2025Optimization Inspired Few-Shot Adaptation for Large Language Models
172. NeurIPS 2025Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
173. NeurIPS 2025PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting
174. NeurIPS 2025Precise Diffusion Inversion: Towards Novel Samples and Few-Step Models
175. NeurIPS 2025Preference-driven Knowledge Distillation for Few-shot Node Classification
176. NeurIPS 2025Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation
177. NeurIPS 2025ReDi: Rectified Discrete Flow
178. NeurIPS 2025ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive Dataset
179. NeurIPS 2025Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
180. NeurIPS 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
181. NeurIPS 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
182. NeurIPS 2025SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation
183. NeurIPS 2025Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
184. NeurIPS 2025Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
185. NeurIPS 2025Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
186. NeurIPS 2025Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
187. NeurIPS 2025Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
188. NeurIPS 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
189. NeurIPS 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
190. NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
191. NeurIPS 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
192. NeurIPS 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
193. NeurIPS 2025Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
194. NeurIPS 2025UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
195. NeurIPS 2025Universal Few-shot Spatial Control for Diffusion Models
196. NeurIPS 2025UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
197. NeurIPS 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
198. NeurIPS 2025Weak-shot Keypoint Estimation via Keyness and Correspondence Transfer
199. NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models
200. NeurIPS 2025Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts

FAQ

How many Few-Shot Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

898 in total: 251 in 2023, 220 in 2024, 203 in 2025, 224 in 2026.

How many Few-Shot Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 51 Few-Shot Learning papers, versus 68 the year before.

How many Few-Shot Learning papers are at ICLR 2026?

ICLR 2026 has 38 Few-Shot Learning papers, versus 36 the year before.

How many Few-Shot Learning papers are at ICML 2026?

ICML 2026 has 56 Few-Shot Learning papers, versus 35 the year before.

How many Few-Shot Learning papers are at CVPR 2026?

CVPR 2026 has 79 Few-Shot Learning papers, versus 64 the year before.

Which conference publishes the most Few-Shot Learning papers?

CVPR, with 303 papers from 2023 to 2026.