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 15 / 25 页
- ICML 2023ILLUME: Rationalizing Vision-Language Models through Human Interactions
- ICML 2023Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
- ICML 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
- ICML 2023Improving Visual Prompt Tuning for Self-supervised Vision Transformers
- ICML 2023Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning
- ICML 2023Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
- ICML 2023Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics
- ICML 2023IRNeXt: Rethinking Convolutional Network Design for Image Restoration
- ICML 2023Is Overfitting Necessary for Implicit Video Representation?
- ICML 2023Large Language Models Can Be Easily Distracted by Irrelevant Context
- ICML 2023Learnability and Algorithm for Continual Learning
- ICML 2023Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
- ICML 2023LegendreTron: Uprising Proper Multiclass Loss Learning
- ICML 2023Less is More: Task-aware Layer-wise Distillation for Language Model Compression
- ICML 2023LIV: Language-Image Representations and Rewards for Robotic Control
- ICML 2023LongCoder: A Long-Range Pre-trained Language Model for Code Completion
- ICML 2023Magneto: A Foundation Transformer
- ICML 2023MEWL: Few-shot multimodal word learning with referential uncertainty
- ICML 2023Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
- ICML 2023ModelDiff: A Framework for Comparing Learning Algorithms
- ICML 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
- ICML 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
- ICML 2023Neural Prediction Errors enable Analogical Visual Reasoning in Human Standard Intelligence Tests
- ICML 2023Nonparametric Extensions of Randomized Response for Private Confidence Sets
- ICML 2023On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
- ICML 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantification
- ICML 2023On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
- ICML 2023On the Power of Foundation Models
- ICML 2023On the Role of Attention in Prompt-tuning
- ICML 2023One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill
- ICML 2023Optimal No-Regret Learning for One-Sided Lipschitz Functions
- ICML 2023Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion
- ICML 2023Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
- ICML 2023Optimizing Mode Connectivity for Class Incremental Learning
- ICML 2023Oscillation-free Quantization for Low-bit Vision Transformers
- ICML 2023PAC Prediction Sets for Large Language Models of Code
- ICML 2023PaLM-E: An Embodied Multimodal Language Model
- ICML 2023Poisoning Language Models During Instruction Tuning
- ICML 2023Polynomial Preconditioning for Gradient Methods
- ICML 2023POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models
- ICML 2023Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
- ICML 2023Predictive Flows for Faster Ford-Fulkerson
- ICML 2023Pretraining Language Models with Human Preferences
- ICML 2023Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
- ICML 2023Progressive Purification for Instance-Dependent Partial Label Learning
- ICML 2023Projected Tensor Power Method for Hypergraph Community Recovery
- ICML 2023Proper Scoring Rules for Survival Analysis
- ICML 2023Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist
- ICML 2023Provable Dynamic Fusion for Low-Quality Multimodal Data
- ICML 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
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。