视觉语言预训练论文趋势 2023–2026

对比预训练

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 263 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

视觉语言预训练论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023241382065
2024161291855
2025261731056
20262714192787

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

全部视觉语言预训练论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 55 篇，第 1 / 2 页

  1. CVPR 2024Anchor-based Robust Finetuning of Vision-Language Models
  2. CVPR 2024BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
  3. CVPR 2024Building Vision-Language Models on Solid Foundations with Masked Distillation
  4. CVPR 2024Efficient Vision-Language Pre-training by Cluster Masking
  5. CVPR 2024EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
  6. CVPR 2024FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models
  7. CVPR 2024Iterated Learning Improves Compositionality in Large Vision-Language Models
  8. CVPR 2024MAFA: Managing False Negatives for Vision-Language Pre-training
  9. CVPR 2024Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
  10. CVPR 2024MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
  11. CVPR 2024OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
  12. CVPR 2024ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks
  13. CVPR 2024PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
  14. CVPR 2024S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data
  15. CVPR 2024SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training
  16. CVPR 2024SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
  17. CVPR 2024ViTamin: Designing Scalable Vision Models in the Vision-Language Era
  18. CVPR 2024ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining
  19. ICLR 20243D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
  20. ICLR 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
  21. ICLR 2024COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
  22. ICLR 2024Demystifying CLIP Data
  23. ICLR 2024Detecting Pretraining Data from Large Language Models
  24. ICLR 2024Headless Language Models: Learning without Predicting with Contrastive Weight Tying
  25. ICLR 2024In-Context Pretraining: Language Modeling Beyond Document Boundaries
  26. ICLR 2024LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
  27. ICLR 2024On the Provable Advantage of Unsupervised Pretraining
  28. ICLR 2024Tag2Text: Guiding Vision-Language Model via Image Tagging
  29. ICLR 2024Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
  30. ICLR 2024Unsupervised Pretraining for Fact Verification by Language Model Distillation
  31. ICML 2024Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
  32. ICML 2024Modeling Caption Diversity in Contrastive Vision-Language Pretraining
  33. ICML 2024OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
  34. ICML 2024Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
  35. ICML 2024Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
  36. ICML 2024Provable Contrastive Continual Learning
  37. ICML 2024Revealing Vision-Language Integration in the Brain with Multimodal Networks
  38. ICML 2024SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment
  39. ICML 2024Two Tales of Single-Phase Contrastive Hebbian Learning
  40. NeurIPS 2024A Practitioner's Guide to Real-World Continual Multimodal Pretraining
  41. NeurIPS 2024Accelerating Augmentation Invariance Pretraining
  42. NeurIPS 2024BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
  43. NeurIPS 2024Boundary Matters: A Bi-Level Active Finetuning Method
  44. NeurIPS 2024Classification Done Right for Vision-Language Pre-Training
  45. NeurIPS 2024Data curation via joint example selection further accelerates multimodal learning
  46. NeurIPS 2024Easy Regional Contrastive Learning of Expressive Fashion Representations
  47. NeurIPS 2024Exploring Molecular Pretraining Model at Scale
  48. NeurIPS 2024Harnessing small projectors and multiple views for efficient vision pretraining
  49. NeurIPS 2024LocCa: Visual Pretraining with Location-aware Captioners
  50. NeurIPS 2024Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction

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 查视觉语言预训练在 NeurIPS 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": "vision-language-pretraining"}

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。

「开放词汇视觉」下的其他主题