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 8 / 20 页

  1. ICLR 2025Glauber Generative Model: Discrete Diffusion Models via Binary Classification
  2. ICLR 2025Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
  3. ICLR 2025HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
  4. ICLR 2025Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
  5. ICLR 2025Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
  6. ICLR 2025Learning Clustering-based Prototypes for Compositional Zero-Shot Learning
  7. ICLR 2025LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models
  8. ICLR 2025Making Text Embedders Few-Shot Learners
  9. ICLR 2025Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
  10. ICLR 2025MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
  11. ICLR 2025Mitigating Spurious Correlations in Zero-Shot Multimodal Models
  12. ICLR 2025MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
  13. ICLR 2025MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
  14. ICLR 2025Multi-Label Test-Time Adaptation with Bound Entropy Minimization
  15. ICLR 2025NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics
  16. ICLR 2025NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
  17. ICLR 2025On the Transfer of Object-Centric Representation Learning
  18. ICLR 2025OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination
  19. ICLR 2025Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost
  20. ICLR 2025Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming
  21. ICLR 2025PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
  22. ICLR 2025Predicate Hierarchies Improve Few-Shot State Classification
  23. ICLR 2025Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection
  24. ICLR 2025Protein Language Model Fitness is a Matter of Preference
  25. ICLR 2025Prototype antithesis for biological few-shot class-incremental learning
  26. ICLR 2025Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer
  27. ICLR 2025Random-Set Neural Networks
  28. ICLR 2025REMEDY: Recipe Merging Dynamics in Large Vision-Language Models
  29. ICLR 2025Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
  30. ICLR 2025SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
  31. ICLR 2025Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
  32. ICLR 2025Transformer Learns Optimal Variable Selection in Group-Sparse Classification
  33. ICLR 2025Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
  34. ICLR 2025Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
  35. ICLR 2025Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
  36. ICLR 2025Visually Consistent Hierarchical Image Classification
  37. ICLR 2025W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
  38. ICLR 2025Zero-shot forecasting of chaotic systems
  39. ICLR 2025Zero-shot Imputation with Foundation Inference Models for Dynamical Systems
  40. ICLR 2025Zero-shot Model-based Reinforcement Learning using Large Language Models
  41. ICLR 2025Zero-Shot Natural Language Explanations
  42. ICLR 2025ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning
  43. ICML 2025A Classification View on Meta Learning Bandits
  44. ICML 2025A Generalization Theory for Zero-Shot Prediction
  45. ICML 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
  46. ICML 2025Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
  47. ICML 2025CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
  48. ICML 2025Conformity Score Averaging for Classification
  49. ICML 2025DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
  50. ICML 2025Discovering a Zero (Zero-Vector Class of Machine Learning)

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