零样本分类论文趋势 2023–2026

零样本识别

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 992 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

零样本分类论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202346552874203
202482455184262
202586564979270
202668446481257

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

全部零样本分类论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 992 篇，第 4 / 20 页

  1. ICML 2026HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
  2. ICML 2026Improving Zero-Shot Offline RL via Behavioral Task Sampling
  3. ICML 2026InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
  4. ICML 2026Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision–Language Models
  5. ICML 2026Klein Hyperbolic Metric Learning
  6. ICML 2026Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization’s Impact on VLMs Beyond Accuracy
  7. ICML 2026Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems
  8. ICML 2026Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
  9. ICML 2026MusicDET: Zero-Shot AI-Generated Music Detection
  10. ICML 2026Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
  11. ICML 2026Offline Two-Player Zero-Sum Markov Games with KL Regularization
  12. ICML 2026On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
  13. ICML 2026OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection
  14. ICML 2026Prompt Tuning for CLIP on the Pretrained Manifold
  15. ICML 2026Protein Autoregressive Modeling via Multiscale Structure Generation
  16. ICML 2026PSMix: Robust Point Cloud Recognition through Spectral Domain Mixing
  17. ICML 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
  18. ICML 2026Scaling depth capacity via zero/one-layer model expansion
  19. ICML 2026scCBGM: Single-Cell Editing via Concept Bottlenecks
  20. ICML 2026Segment Anything with Robust Uncertainty-Accuracy Correlation
  21. ICML 2026SGERA: Stein-Guided ECG-Report Alignment for ECG Representation Learning
  22. ICML 2026Stabilizing Equation Learning via Zero-Point Constraints
  23. ICML 2026Stage-wise Distortion–Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
  24. ICML 2026Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability
  25. ICML 2026Test-time Generalization for Physics through Neural Operator Splitting
  26. ICML 2026TextMesh4D: Zero-shot Text-to-4D Mesh Generation
  27. ICML 2026Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
  28. ICML 2026Treatment Responder Classification with Abstention
  29. ICML 2026Universal Algorithm-Implicit Learning
  30. ICML 2026URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
  31. ICML 2026VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
  32. ICML 2026Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction
  33. ICML 2026Welfare-Optimal Classification with Accuracy Auctions
  34. ICML 2026When Generalized Zero-Shot Learning Meets PU Learning: A Plug-and-Play Framework for Seen-Class Bias Mitigation
  35. ICML 2026Zero-Flow Encoders
  36. ICML 2026Zero-shot Active Mapping via Fused 360-BEV Representations and Vision–Language Models
  37. ICML 2026Zero-Shot Off-Policy Learning
  38. ICML 2026Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
  39. ICML 2026ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion
  40. NeurIPS 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
  41. NeurIPS 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
  42. NeurIPS 2026Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
  43. NeurIPS 2026Beyond MNIST: Limitations of Amplitude Encoding on Quantum Classification
  44. NeurIPS 2026Black-box model classification under the discriminative factorization
  45. NeurIPS 2026BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
  46. NeurIPS 2026Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
  47. NeurIPS 2026Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution
  48. NeurIPS 2026Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
  49. NeurIPS 2026DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
  50. NeurIPS 2026DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule

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 查零样本分类在 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": "zero-shot-classification"}

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零样本分类论文？
共 992 篇，按年份分别是 2023 年 203 篇、2024 年 262 篇、2025 年 270 篇、2026 年 257 篇。
NeurIPS 2026 有多少篇零样本分类论文？
NeurIPS 2026 有 68 篇零样本分类论文，上一届是 86 篇。
ICLR 2026 有多少篇零样本分类论文？
ICLR 2026 有 44 篇零样本分类论文，上一届是 56 篇。
ICML 2026 有多少篇零样本分类论文？
ICML 2026 有 64 篇零样本分类论文，上一届是 49 篇。
CVPR 2026 有多少篇零样本分类论文？
CVPR 2026 有 81 篇零样本分类论文，上一届是 79 篇。
哪个会议的零样本分类论文最多？
CVPR，2023–2026 年共 318 篇。

「开放词汇视觉」下的其他主题