多模态大模型论文趋势 2023–2026
视觉语言模型、图像/视频理解与生成式多模态基础模型
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 11,209 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 433 | 138 | 146 | 509 | 1,226 |
| 2024 | 446 | 321 | 323 | 626 | 1,716 |
| 2025 | 1,074 | 816 | 390 | 795 | 3,075 |
| 2026 | 1,366 | 1,401 | 1,051 | 1,374 | 5,192 |
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 1,226 篇，第 14 / 25 页
- ICML 2023A Watermark for Large Language Models
- ICML 2023Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems
- ICML 2023Approximate Stein Classes for Truncated Density Estimation
- ICML 2023Approximately Optimal Core Shapes for Tensor Decompositions
- ICML 2023Approximation Algorithms for Fair Range Clustering
- ICML 2023Are Large Kernels Better Teachers than Transformers for ConvNets?
- ICML 2023Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
- ICML 2023Bag of Tricks for Training Data Extraction from Language Models
- ICML 2023BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
- ICML 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- ICML 2023BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models
- ICML 2023Calibrating Multimodal Learning
- ICML 2023Can Forward Gradient Match Backpropagation?
- ICML 2023ClimaX: A foundation model for weather and climate
- ICML 2023CLUSTSEG: Clustering for Universal Segmentation
- ICML 2023CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
- ICML 2023COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects
- ICML 2023Concept-based Explanations for Out-of-Distribution Detectors
- ICML 2023Cones: Concept Neurons in Diffusion Models for Customized Generation
- ICML 2023Continual Vision-Language Representation Learning with Off-Diagonal Information
- ICML 2023Continuous Spatiotemporal Transformer
- ICML 2023Coordinate Descent Methods for Fractional Minimization
- ICML 2023Data Poisoning Attacks Against Multimodal Encoders
- ICML 2023Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
- ICML 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
- ICML 2023Demystifying Disagreement-on-the-Line in High Dimensions
- ICML 2023Distilling Internet-Scale Vision-Language Models into Embodied Agents
- ICML 2023Dual Focal Loss for Calibration
- ICML 2023dugMatting: Decomposed-Uncertainty-Guided Matting
- ICML 2023Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
- ICML 2023Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
- ICML 2023Equivariant Architectures for Learning in Deep Weight Spaces
- ICML 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
- ICML 2023Fast Combinatorial Algorithms for Min Max Correlation Clustering
- ICML 2023Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron
- ICML 2023Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
- ICML 2023Generalized Teacher Forcing for Learning Chaotic Dynamics
- ICML 2023GFlowNet-EM for Learning Compositional Latent Variable Models
- ICML 2023Global optimality for Euclidean CCCP under Riemannian convexity
- ICML 2023Global optimality of Elman-type RNNs in the mean-field regime
- ICML 2023Gradient-based Wang--Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space
- ICML 2023Grounding Language Models to Images for Multimodal Inputs and Outputs
- ICML 2023H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features
- ICML 2023Hiding Data Helps: On the Benefits of Masking for Sparse Coding
- ICML 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
- ICML 2023High Fidelity Image Counterfactuals with Probabilistic Causal Models
- ICML 2023High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors
- ICML 2023Hyena Hierarchy: Towards Larger Convolutional Language Models
- ICML 2023Identifying Interpretable Subspaces in Image Representations
- ICML 2023Identifying Useful Learnwares for Heterogeneous Label Spaces
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 查多模态大模型在 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": "multimodal-llms"}
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。