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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 24 | 13 | 8 | 20 | 65 |
| 2024 | 16 | 12 | 9 | 18 | 55 |
| 2025 | 26 | 17 | 3 | 10 | 56 |
| 2026 | 27 | 14 | 19 | 27 | 87 |
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 263 篇，第 6 / 6 页
- NeurIPS 2023Implicit variance regularization in non-contrastive SSL
- NeurIPS 2023Improving CLIP Training with Language Rewrites
- NeurIPS 2023Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation
- NeurIPS 2023LOVM: Language-Only Vision Model Selection
- NeurIPS 2023Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
- NeurIPS 2023MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
- NeurIPS 2023MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
- NeurIPS 2023Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
- NeurIPS 2023Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks
- NeurIPS 2023SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
- NeurIPS 2023Towards In-context Scene Understanding
- NeurIPS 2023Type-to-Track: Retrieve Any Object via Prompt-based Tracking
- NeurIPS 2023Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
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"}
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。