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 146 篇，第 1 / 3 页

1. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
2. ICML 2023$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates
3. ICML 2023A Closer Look at Self-Supervised Lightweight Vision Transformers
4. ICML 2023A Watermark for Large Language Models
5. ICML 2023Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems
6. ICML 2023Approximate Stein Classes for Truncated Density Estimation
7. ICML 2023Approximately Optimal Core Shapes for Tensor Decompositions
8. ICML 2023Approximation Algorithms for Fair Range Clustering
9. ICML 2023Are Large Kernels Better Teachers than Transformers for ConvNets?
10. ICML 2023Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
11. ICML 2023Bag of Tricks for Training Data Extraction from Language Models
12. ICML 2023BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
13. ICML 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
14. ICML 2023BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models
15. ICML 2023Calibrating Multimodal Learning
16. ICML 2023Can Forward Gradient Match Backpropagation?
17. ICML 2023ClimaX: A foundation model for weather and climate
18. ICML 2023CLUSTSEG: Clustering for Universal Segmentation
19. ICML 2023CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
20. ICML 2023COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects
21. ICML 2023Concept-based Explanations for Out-of-Distribution Detectors
22. ICML 2023Cones: Concept Neurons in Diffusion Models for Customized Generation
23. ICML 2023Continual Vision-Language Representation Learning with Off-Diagonal Information
24. ICML 2023Continuous Spatiotemporal Transformer
25. ICML 2023Coordinate Descent Methods for Fractional Minimization
26. ICML 2023Data Poisoning Attacks Against Multimodal Encoders
27. ICML 2023Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
28. ICML 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
29. ICML 2023Demystifying Disagreement-on-the-Line in High Dimensions
30. ICML 2023Distilling Internet-Scale Vision-Language Models into Embodied Agents
31. ICML 2023Dual Focal Loss for Calibration
32. ICML 2023dugMatting: Decomposed-Uncertainty-Guided Matting
33. ICML 2023Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
34. ICML 2023Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
35. ICML 2023Equivariant Architectures for Learning in Deep Weight Spaces
36. ICML 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
37. ICML 2023Fast Combinatorial Algorithms for Min Max Correlation Clustering
38. ICML 2023Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron
39. ICML 2023Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
40. ICML 2023Generalized Teacher Forcing for Learning Chaotic Dynamics
41. ICML 2023GFlowNet-EM for Learning Compositional Latent Variable Models
42. ICML 2023Global optimality for Euclidean CCCP under Riemannian convexity
43. ICML 2023Global optimality of Elman-type RNNs in the mean-field regime
44. ICML 2023Gradient-based Wang--Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space
45. ICML 2023Grounding Language Models to Images for Multimodal Inputs and Outputs
46. ICML 2023H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features
47. ICML 2023Hiding Data Helps: On the Benefits of Masking for Sparse Coding
48. ICML 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
49. ICML 2023High Fidelity Image Counterfactuals with Probabilistic Causal Models
50. ICML 2023High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors

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。