视觉语言预训练论文趋势 2023–2026

主要结论

• 视觉语言预训练论文从 2023 年的 65 篇增长到 2026 年的 87 篇，三年间扩大到约 1.3 倍。
• NeurIPS 是发视觉语言预训练论文最多的会议，2023–2026 年共 93 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 9 篇。
• 在「开放词汇视觉」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的视觉定位是 4.3 倍，视觉语言预训练是 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 2026Benchmarking Optimizers for Large Language Model Pretraining
• ICML 2026How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off
• ICLR 2026PonderLM: Pretraining Language Models to Ponder in Continuous Space
• CVPR 2026Large-scale Codec Avatars The Unreasonable Effectiveness of Large-scale Avatar Pretraining
• NeurIPS 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
• ICML 2025Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
• ICLR 2025Attributing Culture-Conditioned Generations to Pretraining Corpora
• CVPR 2025MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
• NeurIPS 2024Data curation via joint example selection further accelerates multimodal learning
• ICML 2024Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
• ICLR 2024Demystifying CLIP Data
• CVPR 2024ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks
• NeurIPS 2023Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
• ICML 2023Contrastive Learning Meets Homophily: Two Birds with One Stone
• ICLR 2023Energy-Inspired Self-Supervised Pretraining for Vision Models
• CVPR 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
• NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
• ICML 2026Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
• ICLR 2026MICLIP: Learning to Interpret Representation in Vision Models
• CVPR 2026The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations

全部视觉语言预训练论文

共 27 篇，第 1 / 1 页

1. CVPR 2026b-CLIP Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
2. CVPR 2026BabyVLM-V2 Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation
3. CVPR 2026Beyond 3D VQAs Injecting 3D Spatial Priors into Vision-Language Models
4. CVPR 2026CLEP Contrastive Language-Pose Pretraining
5. CVPR 2026Concept-Aware Batch Sampling Improves Language-Image Pretraining
6. CVPR 2026EthoCLIP Ontology-Enhanced Video-Language Pretraining for Animal Behavior Understanding
7. CVPR 2026Evo-1 Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
8. CVPR 2026FALCON False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment
9. CVPR 2026From Panel to Pixel Zoom-In Vision-Language Pretraining from Biomedical Scientific
10. CVPR 2026Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via
11. CVPR 2026Joint-Aligned Latent Action Towards Scalable VLA Pretraining in the Wild
12. CVPR 2026LA-Pose Latent Action Pretraining Meets Pose Estimation
13. CVPR 2026Large-scale Codec Avatars The Unreasonable Effectiveness of Large-scale Avatar Pretraining
14. CVPR 2026Learning from Itself Mining Internal Knowledge from Vision Language Models
15. CVPR 2026MedKCO Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration
16. CVPR 2026Modeling Cross-vision Synergy for Unified Large Vision Model
17. CVPR 2026MuViT Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy
18. CVPR 2026PowerCLIP Powerset Alignment for Contrastive Pre-Training
19. CVPR 2026Scaling Parallel Sequence Models to Vision Foundation Models
20. CVPR 2026Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning
21. CVPR 2026Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
22. CVPR 2026The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations
23. CVPR 2026TIPSv2 Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
24. CVPR 2026Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
25. CVPR 2026Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language
26. CVPR 2026UniRefiner Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
27. CVPR 2026Unlearning without Forgetting Securely Removing Targeted Concepts from Large-Scale Vision-Language

常见问题

2023–2026 年四大会议一共有多少篇视觉语言预训练论文？

共 263 篇，按年份分别是 2023 年 65 篇、2024 年 55 篇、2025 年 56 篇、2026 年 87 篇。

NeurIPS 2026 有多少篇视觉语言预训练论文？

NeurIPS 2026 有 27 篇视觉语言预训练论文，上一届是 26 篇。

ICLR 2026 有多少篇视觉语言预训练论文？

ICLR 2026 有 14 篇视觉语言预训练论文，上一届是 17 篇。

ICML 2026 有多少篇视觉语言预训练论文？

ICML 2026 有 19 篇视觉语言预训练论文，上一届是 3 篇。

CVPR 2026 有多少篇视觉语言预训练论文？

CVPR 2026 有 27 篇视觉语言预训练论文，上一届是 10 篇。

哪个会议的视觉语言预训练论文最多？

NeurIPS，2023–2026 年共 93 篇。