零样本分类论文趋势 2023–2026

主要结论

• 零样本分类论文从 2023 年的 203 篇增长到 2026 年的 257 篇，三年间扩大到约 1.3 倍。
• CVPR 是发零样本分类论文最多的会议，2023–2026 年共 318 篇，占四个会议总量的 32%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 22 篇。
• 在「开放词汇视觉」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的视觉定位是 4.3 倍，零样本分类是 1.3 倍。

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

• NeurIPS 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
• ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
• ICLR 2026Boomerang Distillation Enables Zero-Shot Model Size Interpolation
• CVPR 2026AG-VAS Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
• NeurIPS 2025\(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
• CVPR 2025AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP
• NeurIPS 2024BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
• ICML 2024Agent Instructs Large Language Models to be General Zero-Shot Reasoners
• ICLR 2024AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
• CVPR 2024Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
• NeurIPS 2023Black-box Backdoor Defense via Zero-shot Image Purification
• ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
• ICLR 2023Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
• CVPR 2023(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning
• NeurIPS 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
• ICML 2026Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• ICLR 2026Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot Learning
• CVPR 2026DLVP-CLIP Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual

全部零样本分类论文

共 270 篇，第 2 / 6 页

51. CVPR 2025Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition
52. CVPR 2025Seurat: From Moving Points to Depth
53. CVPR 2025SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
54. CVPR 2025Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail
55. CVPR 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
56. CVPR 2025TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
57. CVPR 2025Task-Specific Gradient Adaptation for Few-Shot One-Class Classification
58. CVPR 2025Temporal Alignment-Free Video Matching for Few-shot Action Recognition
59. CVPR 2025Text Augmented Correlation Transformer For Few-shot Classification & Segmentation
60. CVPR 2025Towards Efficient Foundation Model for Zero-shot Amodal Segmentation
61. CVPR 2025Towards Source-Free Machine Unlearning
62. CVPR 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
63. CVPR 2025Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning
64. CVPR 2025UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning
65. CVPR 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
66. CVPR 2025VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
67. CVPR 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning
68. CVPR 2025Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
69. CVPR 2025Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion
70. CVPR 2025Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression
71. CVPR 2025Zero-Shot 4D Lidar Panoptic Segmentation
72. CVPR 2025Zero-Shot Blind-spot Image Denoising via Implicit Neural Sampling
73. CVPR 2025Zero-Shot Head Swapping in Real-World Scenarios
74. CVPR 2025Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)
75. CVPR 2025Zero-Shot Monocular Scene Flow Estimation in the Wild
76. CVPR 2025Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
77. CVPR 2025Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model
78. CVPR 2025Zero-Shot Styled Text Image Generation, but Make It Autoregressive
79. CVPR 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping
80. ICLR 2025A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
81. ICLR 2025Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
82. ICLR 2025AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation
83. ICLR 2025CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
84. ICLR 2025Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning
85. ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
86. ICLR 2025Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification
87. ICLR 2025Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
88. ICLR 2025Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint
89. ICLR 2025Distribution-Specific Agnostic Conditional Classification With Halfspaces
90. ICLR 2025Divergence of Neural Tangent Kernel in Classification Problems
91. ICLR 2025Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning
92. ICLR 2025Federated Few-Shot Class-Incremental Learning
93. ICLR 2025Fully-inductive Node Classification on Arbitrary Graphs
94. ICLR 2025Glauber Generative Model: Discrete Diffusion Models via Binary Classification
95. ICLR 2025Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
96. ICLR 2025HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
97. ICLR 2025Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
98. ICLR 2025Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
99. ICLR 2025Learning Clustering-based Prototypes for Compositional Zero-Shot Learning
100. ICLR 2025LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models

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。