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 138 篇，第 2 / 3 页

51. ICLR 2023Identifiability Results for Multimodal Contrastive Learning
52. ICLR 2023Image as Set of Points
53. ICLR 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
54. ICLR 2023Interactive Portrait Harmonization
55. ICLR 2023ISAAC Newton: Input-based Approximate Curvature for Newton's Method
56. ICLR 2023Iterative Patch Selection for High-Resolution Image Recognition
57. ICLR 2023Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
58. ICLR 2023Large Language Models are Human-Level Prompt Engineers
59. ICLR 2023Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
60. ICLR 2023Learning Iterative Neural Optimizers for Image Steganography
61. ICLR 2023Learning Multimodal Data Augmentation in Feature Space
62. ICLR 2023Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
63. ICLR 2023Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
64. ICLR 2023Learning to Decompose Visual Features with Latent Textual Prompts
65. ICLR 2023Learning to Grow Pretrained Models for Efficient Transformer Training
66. ICLR 2023Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models
67. ICLR 2023Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
68. ICLR 2023Leveraging Large Language Models for Multiple Choice Question Answering
69. ICLR 2023Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
70. ICLR 2023LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
71. ICLR 2023LMSeg: Language-guided Multi-dataset Segmentation
72. ICLR 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
73. ICLR 2023LPT: Long-tailed Prompt Tuning for Image Classification
74. ICLR 2023Masked Unsupervised Self-training for Label-free Image Classification
75. ICLR 2023Masked Vision and Language Modeling for Multi-modal Representation Learning
76. ICLR 2023MaskViT: Masked Visual Pre-Training for Video Prediction
77. ICLR 2023MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
78. ICLR 2023Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
79. ICLR 2023Measuring axiomatic soundness of counterfactual image models
80. ICLR 2023MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
81. ICLR 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
82. ICLR 2023MIMT: Masked Image Modeling Transformer for Video Compression
83. ICLR 2023Mini-batch $k$-means terminates within $O(d/\epsilon)$ iterations
84. ICLR 2023MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
85. ICLR 2023MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without Compromises
86. ICLR 2023MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
87. ICLR 2023Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
88. ICLR 2023Mosaic Representation Learning for Self-supervised Visual Pre-training
89. ICLR 2023Multimodal Analogical Reasoning over Knowledge Graphs
90. ICLR 2023Multimodal Federated Learning via Contrastive Representation Ensemble
91. ICLR 2023MultiViz: Towards Visualizing and Understanding Multimodal Models
92. ICLR 2023NeRN: Learning Neural Representations for Neural Networks
93. ICLR 2023Neural Bregman Divergences for Distance Learning
94. ICLR 2023Neural Compositional Rule Learning for Knowledge Graph Reasoning
95. ICLR 2023Neural Optimal Transport
96. ICLR 2023Open-Vocabulary Object Detection upon Frozen Vision and Language Models
97. ICLR 2023PaLI: A Jointly-Scaled Multilingual Language-Image Model
98. ICLR 2023Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
99. ICLR 2023PatchDCT: Patch Refinement for High Quality Instance Segmentation
100. ICLR 2023PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

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。