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 9 / 18 页

  1. NeurIPS 2025ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive Dataset
  2. NeurIPS 2025Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
  3. NeurIPS 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
  4. NeurIPS 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
  5. NeurIPS 2025SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation
  6. NeurIPS 2025Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
  7. NeurIPS 2025Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
  8. NeurIPS 2025Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
  9. NeurIPS 2025Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
  10. NeurIPS 2025Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
  11. NeurIPS 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
  12. NeurIPS 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
  13. NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
  14. NeurIPS 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
  15. NeurIPS 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
  16. NeurIPS 2025Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
  17. NeurIPS 2025UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
  18. NeurIPS 2025Universal Few-shot Spatial Control for Diffusion Models
  19. NeurIPS 2025UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
  20. NeurIPS 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
  21. NeurIPS 2025Weak-shot Keypoint Estimation via Keyness and Correspondence Transfer
  22. NeurIPS 2025Zebra-Llama: Towards Extremely Efficient Hybrid Models
  23. NeurIPS 2025Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts
  24. NeurIPS 2025Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework
  25. NeurIPS 2025Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
  26. NeurIPS 2025ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
  27. CVPR 20243DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces
  28. CVPR 2024A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models
  29. CVPR 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
  30. CVPR 2024Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation
  31. CVPR 2024Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
  32. CVPR 2024AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
  33. CVPR 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
  34. CVPR 2024Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features
  35. CVPR 2024CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification
  36. CVPR 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning
  37. CVPR 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining
  38. CVPR 2024DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting
  39. CVPR 2024Deformable One-shot Face Stylization via DINO Semantic Guidance
  40. CVPR 2024DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning
  41. CVPR 2024Dense Vision Transformer Compression with Few Samples
  42. CVPR 2024Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning
  43. CVPR 2024DiaLoc: An Iterative Approach to Embodied Dialog Localization
  44. CVPR 2024DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
  45. CVPR 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning
  46. CVPR 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
  47. CVPR 2024Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
  48. CVPR 2024EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars
  49. CVPR 2024Exact Fusion via Feature Distribution Matching for Few-shot Image Generation
  50. CVPR 2024Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation

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