小样本学习论文趋势 2023–2026

元学习与小样本

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 898 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

小样本学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202376564079251
202464383781220
202568363564203
202651385679224

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

全部小样本学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 897 篇，第 7 / 18 页

  1. ICLR 2025Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
  2. ICLR 2025LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently
  3. ICLR 2025Making Text Embedders Few-Shot Learners
  4. ICLR 2025Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
  5. ICLR 2025Meta-Dynamical State Space Models for Integrative Neural Data Analysis
  6. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
  7. ICLR 2025Multi-Perspective Data Augmentation for Few-shot Object Detection
  8. ICLR 2025Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
  9. ICLR 2025One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning
  10. ICLR 2025PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning
  11. ICLR 2025Predicate Hierarchies Improve Few-Shot State Classification
  12. ICLR 2025Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework
  13. ICLR 2025Protein Language Model Fitness is a Matter of Preference
  14. ICLR 2025Prototype antithesis for biological few-shot class-incremental learning
  15. ICLR 2025Safety Alignment Should be Made More Than Just a Few Tokens Deep
  16. ICLR 2025STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
  17. ICLR 2025SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
  18. ICLR 2025UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery
  19. ICLR 2025Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation
  20. ICLR 2025Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation
  21. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?
  22. ICLR 2025Zero-Shot Natural Language Explanations
  23. ICLR 2025ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning
  24. ICML 2025Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
  25. ICML 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
  26. ICML 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
  27. ICML 2025Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
  28. ICML 2025CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
  29. ICML 2025Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning
  30. ICML 2025DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
  31. ICML 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
  32. ICML 2025Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework
  33. ICML 2025Feedforward Few-shot Species Range Estimation
  34. ICML 2025Few-Shot Learner Generalizes Across AI-Generated Image Detection
  35. ICML 2025FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
  36. ICML 2025Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
  37. ICML 2025GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
  38. ICML 2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
  39. ICML 2025On the Provable Separation of Scales in Maximal Update Parameterization
  40. ICML 2025One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
  41. ICML 2025PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
  42. ICML 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
  43. ICML 2025Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
  44. ICML 2025Provable Zero-Shot Generalization in Offline Reinforcement Learning
  45. ICML 2025Provably Improving Generalization of Few-shot models with Synthetic Data
  46. ICML 2025Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
  47. ICML 2025Random Registers for Cross-Domain Few-Shot Learning
  48. ICML 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
  49. ICML 2025Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective
  50. ICML 2025SAND: One-Shot Feature Selection with Additive Noise Distortion

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查小样本学习在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "few-shot-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「元学习与迁移」下的其他主题