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 86 篇，第 2 / 2 页

51. NeurIPS 2025Robust Minimax Boosting with Performance Guarantees
52. NeurIPS 2025Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
53. NeurIPS 2025SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification
54. NeurIPS 2025ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
55. NeurIPS 2025SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
56. NeurIPS 2025SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
57. NeurIPS 2025Split conformal classification with unsupervised calibration
58. NeurIPS 2025SuperCLIP: CLIP with Simple Classification Supervision
59. NeurIPS 2025Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
60. NeurIPS 2025Taming generative video models for zero-shot optical flow extraction
61. NeurIPS 2025Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
62. NeurIPS 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
63. NeurIPS 2025TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
64. NeurIPS 2025Towards Robust Zero-Shot Reinforcement Learning
65. NeurIPS 2025Transformers are almost optimal metalearners for linear classification
66. NeurIPS 2025Tree-Guided Diffusion Planner
67. NeurIPS 2025True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
68. NeurIPS 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster
69. NeurIPS 2025UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
70. NeurIPS 2025Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
71. NeurIPS 2025Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
72. NeurIPS 2025Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
73. NeurIPS 2025Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
74. NeurIPS 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
75. NeurIPS 2025ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
76. NeurIPS 2025Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling
77. NeurIPS 2025Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts
78. NeurIPS 2025Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework
79. NeurIPS 2025Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
80. NeurIPS 2025Zero-Shot Performance Prediction for Probabilistic Scaling Laws
81. NeurIPS 2025Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
82. NeurIPS 2025Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks
83. NeurIPS 2025Zero-shot World Models via Search in Memory
84. NeurIPS 2025ZeroS: Zero‑Sum Linear Attention for Efficient Transformers
85. NeurIPS 2025ZeroSep: Separate Anything in Audio with Zero Training
86. NeurIPS 2025ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

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。