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 11,207 篇，第 216 / 225 页
- ICML 2023SpotEM: Efficient Video Search for Episodic Memory
- ICML 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapse
- ICML 2023Statistical Learning under Heterogenous Distribution Shift
- ICML 2023Structure-informed Language Models Are Protein Designers
- ICML 2023Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction
- ICML 2023SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
- ICML 2023Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization
- ICML 2023Temporally Consistent Transformers for Video Generation
- ICML 2023Tight Data Access Bounds for Private Top-$k$ Selection
- ICML 2023Tighter Analysis for ProxSkip
- ICML 2023Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
- ICML 2023Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks
- ICML 2023Towards Omni-generalizable Neural Methods for Vehicle Routing Problems
- ICML 2023Tractable Control for Autoregressive Language Generation
- ICML 2023TRAK: Attributing Model Behavior at Scale
- ICML 2023Traversing Between Modes in Function Space for Fast Ensembling
- ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
- ICML 2023Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
- ICML 2023Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions
- ICML 2023UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
- ICML 2023VIMA: Robot Manipulation with Multimodal Prompts
- ICML 2023Whose Opinions Do Language Models Reflect?
- ICML 2023Why do Nearest Neighbor Language Models Work?
- ICML 2023Why Is Public Pretraining Necessary for Private Model Training?
- NeurIPS 20233D-LLM: Injecting the 3D World into Large Language Models
- NeurIPS 20234M: Massively Multimodal Masked Modeling
- NeurIPS 2023A case for reframing automated medical image classification as segmentation
- NeurIPS 2023A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
- NeurIPS 2023A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem
- NeurIPS 2023A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
- NeurIPS 2023A Theory of Multimodal Learning
- NeurIPS 2023A Unified Framework for U-Net Design and Analysis
- NeurIPS 2023Achieving Cross Modal Generalization with Multimodal Unified Representation
- NeurIPS 2023Active Reasoning in an Open-World Environment
- NeurIPS 2023Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels
- NeurIPS 2023AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix
- NeurIPS 2023AiluRus: A Scalable ViT Framework for Dense Prediction
- NeurIPS 2023AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
- NeurIPS 2023ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers
- NeurIPS 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
- NeurIPS 2023Aligning Gradient and Hessian for Neural Signed Distance Function
- NeurIPS 2023Aligning Language Models with Human Preferences via a Bayesian Approach
- NeurIPS 2023Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
- NeurIPS 2023Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction
- NeurIPS 2023Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
- NeurIPS 2023Alternating Updates for Efficient Transformers
- NeurIPS 2023AmadeusGPT: a natural language interface for interactive animal behavioral analysis
- NeurIPS 2023An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
- NeurIPS 2023An Inverse Scaling Law for CLIP Training
- NeurIPS 2023An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement
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。