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 302 篇，第 3 / 7 页

  1. CVPR 2025FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
  2. CVPR 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
  3. CVPR 2025GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis
  4. CVPR 2025HumanMM: Global Human Motion Recovery from Multi-shot Videos
  5. CVPR 2025Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
  6. CVPR 2025Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance
  7. CVPR 2025ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning
  8. CVPR 2025InsTaG: Learning Personalized 3D Talking Head from Few-Second Video
  9. CVPR 2025Logits DeConfusion with CLIP for Few-Shot Learning
  10. CVPR 2025LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
  11. CVPR 2025MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices
  12. CVPR 2025MVSAnywhere: Zero-Shot Multi-View Stereo
  13. CVPR 2025One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency
  14. CVPR 2025OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging
  15. CVPR 2025ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models
  16. CVPR 2025Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
  17. CVPR 2025Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
  18. CVPR 2025Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
  19. CVPR 2025SAM2Object: Consolidating View Consistency via SAM2 for Zero-Shot 3D Instance Segmentation
  20. CVPR 2025SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning
  21. CVPR 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matching
  22. CVPR 2025Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail
  23. CVPR 2025Synthetic Prior for Few-Shot Drivable Head Avatar Inversion
  24. CVPR 2025TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
  25. CVPR 2025TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
  26. CVPR 2025Task-Specific Gradient Adaptation for Few-Shot One-Class Classification
  27. CVPR 2025Temporal Alignment-Free Video Matching for Few-shot Action Recognition
  28. CVPR 2025Text Augmented Correlation Transformer For Few-shot Classification & Segmentation
  29. CVPR 2025The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
  30. CVPR 2025Token Cropr: Faster ViTs for Quite a Few Tasks
  31. CVPR 2025Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning
  32. CVPR 2025Twinner: Shining Light on Digital Twins in a Few Snaps
  33. CVPR 2025UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning
  34. CVPR 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
  35. CVPR 2025UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
  36. CVPR 2025Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation
  37. CVPR 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning
  38. CVPR 2025Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
  39. CVPR 2025Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression
  40. CVPR 2025Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)
  41. CVPR 2025Zero-Shot Monocular Scene Flow Estimation in the Wild
  42. CVPR 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping
  43. CVPR 20243DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces
  44. CVPR 2024A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models
  45. CVPR 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
  46. CVPR 2024Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation
  47. CVPR 2024Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
  48. CVPR 2024AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
  49. CVPR 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
  50. CVPR 2024Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

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