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 22 / 25 页
- NeurIPS 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Models
- NeurIPS 2023Mask Propagation for Efficient Video Semantic Segmentation
- NeurIPS 2023Masked Image Residual Learning for Scaling Deeper Vision Transformers
- NeurIPS 2023Mass-Producing Failures of Multimodal Systems with Language Models
- NeurIPS 2023Mathematical Capabilities of ChatGPT
- NeurIPS 2023MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
- NeurIPS 2023Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
- NeurIPS 2023Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
- NeurIPS 2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
- NeurIPS 2023MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
- NeurIPS 2023Mitigating Test-Time Bias for Fair Image Retrieval
- NeurIPS 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
- NeurIPS 2023Module-wise Adaptive Distillation for Multimodality Foundation Models
- NeurIPS 2023MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
- NeurIPS 2023Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization
- NeurIPS 2023MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
- NeurIPS 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
- NeurIPS 2023Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine
- NeurIPS 2023Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice
- NeurIPS 2023MultiVENT: Multilingual Videos of Events and Aligned Natural Text
- NeurIPS 2023NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation
- NeurIPS 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
- NeurIPS 2023NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
- NeurIPS 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
- NeurIPS 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
- NeurIPS 2023On Evaluating Adversarial Robustness of Large Vision-Language Models
- NeurIPS 2023On the choice of Perception Loss Function for Learned Video Compression
- NeurIPS 2023On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets
- NeurIPS 2023On the Planning Abilities of Large Language Models - A Critical Investigation
- NeurIPS 2023On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
- NeurIPS 2023On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models
- NeurIPS 2023OpenDataVal: a Unified Benchmark for Data Valuation
- NeurIPS 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
- NeurIPS 2023Operation-Level Early Stopping for Robustifying Differentiable NAS
- NeurIPS 2023Optimal approximation using complex-valued neural networks
- NeurIPS 2023Optimal Learners for Realizable Regression: PAC Learning and Online Learning
- NeurIPS 2023Order Matters in the Presence of Dataset Imbalance for Multilingual Learning
- NeurIPS 2023PaintSeg: Painting Pixels for Training-free Segmentation
- NeurIPS 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
- NeurIPS 2023Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
- NeurIPS 2023Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
- NeurIPS 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
- NeurIPS 2023Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
- NeurIPS 2023Parts of Speech–Grounded Subspaces in Vision-Language Models
- NeurIPS 2023Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
- NeurIPS 2023Paxion: Patching Action Knowledge in Video-Language Foundation Models
- NeurIPS 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Models
- NeurIPS 2023Personalized Dictionary Learning for Heterogeneous Datasets
- NeurIPS 2023PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
- NeurIPS 2023PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
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。