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 3,075 篇，第 35 / 62 页
- ICML 2025Efficient Multi-modal Long Context Learning for Training-free Adaptation
- ICML 2025Efficient Quantification of Multimodal Interaction at Sample Level
- ICML 2025Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
- ICML 2025Efficiently Serving Large Multimodal Models Using EPD Disaggregation
- ICML 2025ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
- ICML 2025ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
- ICML 2025Elucidating the design space of language models for image generation
- ICML 2025Elucidating the Design Space of Multimodal Protein Language Models
- ICML 2025Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
- ICML 2025Emergent Response Planning in LLMs
- ICML 2025Empowering World Models with Reflection for Embodied Video Prediction
- ICML 2025Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
- ICML 2025Enhancing Target-unspecific Tasks through a Features Matrix
- ICML 2025EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
- ICML 2025ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
- ICML 2025Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
- ICML 2025Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
- ICML 2025Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
- ICML 2025Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs
- ICML 2025Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
- ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
- ICML 2025FairPFN: A Tabular Foundation Model for Causal Fairness
- ICML 2025Fast Exact Unlearning for In-Context Learning Data for LLMs
- ICML 2025FeatSharp: Your Vision Model Features, Sharper
- ICML 2025Feature out! Let Raw Image as Your Condition for Blind Face Restoration
- ICML 2025Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation
- ICML 2025FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning
- ICML 2025FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
- ICML 2025FG-CLIP: Fine-Grained Visual and Textual Alignment
- ICML 2025Fine-Grained Captioning of Long Videos through Scene Graph Consolidation
- ICML 2025FLAM: Frame-Wise Language-Audio Modeling
- ICML 2025FlipAttack: Jailbreak LLMs via Flipping
- ICML 2025Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency
- ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
- ICML 2025FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
- ICML 2025Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
- ICML 2025Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
- ICML 2025FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
- ICML 2025Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
- ICML 2025From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
- ICML 2025From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
- ICML 2025From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
- ICML 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
- ICML 2025Function-to-Style Guidance of LLMs for Code Translation
- ICML 2025Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
- ICML 2025Gandalf the Red: Adaptive Security for LLMs
- ICML 2025GaussMark: A Practical Approach for Structural Watermarking of Language Models
- ICML 2025Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
- ICML 2025Generative Data Mining with Longtail-Guided Diffusion
- ICML 2025GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
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。