多模态大模型论文趋势 2023–2026

主要结论

• 多模态大模型论文从 2023 年的 1,226 篇增长到 2026 年的 5,192 篇，三年间扩大到约 4.2 倍。
• NeurIPS 是发多模态大模型论文最多的会议，2023–2026 年共 3,319 篇，占四个会议总量的 30%。
• 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 35 篇增至 2026 年的 596 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 1；同组增长最快的AI 智能体是 12 倍，多模态大模型是 4.2 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 2026$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
• ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
• ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
• CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
• NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
• ICLR 2025$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
• CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
• NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
• ICML 2024A Multimodal Automated Interpretability Agent
• ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
• CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
• NeurIPS 20234M: Massively Multimodal Masked Modeling
• ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
• ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
• CVPR 20233D Concept Learning and Reasoning From Multi-View Images
• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
• ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
• CVPR 20263D-IDE 3D Implicit Depth Emergent

全部多模态大模型论文

共 3,075 篇，第 1 / 62 页

1. CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
2. CVPR 20253D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
3. CVPR 20253D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
4. CVPR 20253D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
5. CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
6. CVPR 20254Deform: Neural Surface Deformation for Robust Shape Interpolation
7. CVPR 2025A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
8. CVPR 2025A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
9. CVPR 2025A Flag Decomposition for Hierarchical Datasets
10. CVPR 2025A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations
11. CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
12. CVPR 2025A Regularization-Guided Equivariant Approach for Image Restoration
13. CVPR 2025A Semantic Knowledge Complementarity based Decoupling Framework for Semi-supervised Class-imbalanced Medical Image Segmentation
14. CVPR 2025A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
15. CVPR 2025A Unified Image-Dense Annotation Generation Model for Underwater Scenes
16. CVPR 2025A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
17. CVPR 2025A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
18. CVPR 2025A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment
19. CVPR 2025ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects
20. CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
21. CVPR 2025ACL: Activating Capability of Linear Attention for Image Restoration
22. CVPR 2025Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration
23. CVPR 2025Activating Sparse Part Concepts for 3D Class Incremental Learning
24. CVPR 2025Active Data Curation Effectively Distills Large-Scale Multimodal Models
25. CVPR 2025Active Event-based Stereo Vision
26. CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
27. CVPR 2025AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
28. CVPR 2025Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
29. CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
30. CVPR 2025Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration
31. CVPR 2025Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution
32. CVPR 2025Adaptive Keyframe Sampling for Long Video Understanding
33. CVPR 2025Adaptive Parameter Selection for Tuning Vision-Language Models
34. CVPR 2025Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition
35. CVPR 2025ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Resolution
36. CVPR 2025Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training
37. CVPR 2025Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
38. CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
39. CVPR 2025Adversarial Diffusion Compression for Real-World Image Super-Resolution
40. CVPR 2025AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
41. CVPR 2025AIpparel: A Multimodal Foundation Model for Digital Garments
42. CVPR 2025Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement
43. CVPR 2025AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
44. CVPR 2025Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
45. CVPR 2025All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
46. CVPR 2025AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation Nowcasting
47. CVPR 2025Anchor-Aware Similarity Cohesion in Target Frames Enables Predicting Temporal Moment Boundaries in 2D
48. CVPR 2025AnimateAnything: Consistent and Controllable Animation for Video Generation
49. CVPR 2025ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction
50. CVPR 2025Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception

常见问题

2023–2026 年四大会议一共有多少篇多模态大模型论文？

共 11,209 篇，按年份分别是 2023 年 1,226 篇、2024 年 1,716 篇、2025 年 3,075 篇、2026 年 5,192 篇。

NeurIPS 2026 有多少篇多模态大模型论文？

NeurIPS 2026 有 1,366 篇多模态大模型论文，上一届是 1,074 篇。

ICLR 2026 有多少篇多模态大模型论文？

ICLR 2026 有 1,401 篇多模态大模型论文，上一届是 816 篇。

ICML 2026 有多少篇多模态大模型论文？

ICML 2026 有 1,051 篇多模态大模型论文，上一届是 390 篇。

CVPR 2026 有多少篇多模态大模型论文？

CVPR 2026 有 1,374 篇多模态大模型论文，上一届是 795 篇。

哪个会议的多模态大模型论文最多？

NeurIPS，2023–2026 年共 3,319 篇。