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 181 / 225 页
- ICLR 2024FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
- ICLR 2024Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
- ICLR 2024Frequency-Aware Transformer for Learned Image Compression
- ICLR 2024FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
- ICLR 2024Frozen Transformers in Language Models Are Effective Visual Encoder Layers
- ICLR 2024Fully Hyperbolic Convolutional Neural Networks for Computer Vision
- ICLR 2024Functional Interpolation for Relative Positions improves Long Context Transformers
- ICLR 2024GAIA: a benchmark for General AI Assistants
- ICLR 2024GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
- ICLR 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
- ICLR 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
- ICLR 2024Grounding Multimodal Large Language Models to the World
- ICLR 2024Guiding Instruction-based Image Editing via Multimodal Large Language Models
- ICLR 2024Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
- ICLR 2024Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
- ICLR 2024How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
- ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
- ICLR 2024Identifying Representations for Intervention Extrapolation
- ICLR 2024Image Background Serves as Good Proxy for Out-of-distribution Data
- ICLR 2024Image Clustering Conditioned on Text Criteria
- ICLR 2024Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
- ICLR 2024Implicit Neural Representations and the Algebra of Complex Wavelets
- ICLR 2024Improved algorithm and bounds for successive projection
- ICLR 2024Improved Probabilistic Image-Text Representations
- ICLR 2024In-context Autoencoder for Context Compression in a Large Language Model
- ICLR 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
- ICLR 2024Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction
- ICLR 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
- ICLR 2024InstructDET: Diversifying Referring Object Detection with Generalized Instructions
- ICLR 2024InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
- ICLR 2024INViTE: INterpret and Control Vision-Language Models with Text Explanations
- ICLR 2024Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
- ICLR 2024It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
- ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
- ICLR 2024Jointly Training Large Autoregressive Multimodal Models
- ICLR 2024Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
- ICLR 2024Knowledge Fusion of Large Language Models
- ICLR 2024Kosmos-G: Generating Images in Context with Multimodal Large Language Models
- ICLR 2024Label-free Node Classification on Graphs with Large Language Models (LLMs)
- ICLR 2024Language-Informed Visual Concept Learning
- ICLR 2024LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
- ICLR 2024Large Language Models as Automated Aligners for benchmarking Vision-Language Models
- ICLR 2024Large Language Models as Tool Makers
- ICLR 2024Large Language Models Cannot Self-Correct Reasoning Yet
- ICLR 2024Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
- ICLR 2024Learning Hierarchical Image Segmentation For Recognition and By Recognition
- ICLR 2024Learning Interactive Real-World Simulators
- ICLR 2024Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
- ICLR 2024Let's Verify Step by Step
- ICLR 2024Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
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。