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 93 篇，第 1 / 2 页

1. NeurIPS 2026Benchmarking Optimizers for Large Language Model Pretraining
2. NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
3. NeurIPS 2026Contrastive Pretraining Scales Agentic Exploration
4. NeurIPS 2026CytoWave: Perturbation-Centric Pretraining for Single-Cell Response Prediction
5. NeurIPS 2026Does Cross-Panel Pretraining Transfer Under Marker Heterogeneity? A Large-Scale Empirical Study in Clinical Flow Cytometry
6. NeurIPS 2026Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
7. NeurIPS 2026EMO: Pretraining Mixture of Experts for Emergent Modularity
8. NeurIPS 2026Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
9. NeurIPS 2026FinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining
10. NeurIPS 2026Improving Self-Supervised Vision Transformers with Cross Distillation
11. NeurIPS 2026Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
12. NeurIPS 2026Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
13. NeurIPS 2026mmLIP: mmWave Radar-Language Interactive Pretraining via Point Confidence
14. NeurIPS 2026Neuron Populations Exhibit Divergent Selectivity with Scale
15. NeurIPS 2026Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
16. NeurIPS 2026Pretraining Curricula Enable Selective Fine-tuning
17. NeurIPS 2026Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models
18. NeurIPS 2026ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
19. NeurIPS 2026Progressive Residual Warmup for Language Model Pretraining
20. NeurIPS 2026Rethinking Contrastive Targets in Radiology Language-Image Pretraining
21. NeurIPS 2026Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining
22. NeurIPS 2026Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
23. NeurIPS 2026SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization
24. NeurIPS 2026Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation
25. NeurIPS 2026Strong Teacher Not Needed? On Distillation in LLM Pretraining
26. NeurIPS 2026Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling
27. NeurIPS 2026TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
28. NeurIPS 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
29. NeurIPS 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
30. NeurIPS 2025AmorLIP: Efficient Language-Image Pretraining via Amortization
31. NeurIPS 2025Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
32. NeurIPS 2025Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
33. NeurIPS 2025CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation
34. NeurIPS 2025Contrastive Self-Supervised Learning As Neural Manifold Packing
35. NeurIPS 2025Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
36. NeurIPS 2025EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
37. NeurIPS 2025Enhancing Contrastive Learning with Variable Similarity
38. NeurIPS 2025Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining
39. NeurIPS 2025Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining
40. NeurIPS 2025From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures
41. NeurIPS 2025From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
42. NeurIPS 2025Group-Level Data Selection for Efficient Pretraining
43. NeurIPS 2025Meta CLIP 2: A Worldwide Scaling Recipe
44. NeurIPS 2025MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
45. NeurIPS 2025Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
46. NeurIPS 2025Object Concepts Emerge from Motion
47. NeurIPS 2025Object-centric binding in Contrastive Language-Image Pretraining
48. NeurIPS 2025Perception Encoder: The best visual embeddings are not at the output of the network
49. NeurIPS 2025REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
50. NeurIPS 2025The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

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。