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 3,319 篇，第 65 / 67 页
- NeurIPS 2023PromptIR: Prompting for All-in-One Image Restoration
- NeurIPS 2023ProPILE: Probing Privacy Leakage in Large Language Models
- NeurIPS 2023Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
- NeurIPS 2023PTQD: Accurate Post-Training Quantization for Diffusion Models
- NeurIPS 2023PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
- NeurIPS 2023Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models
- NeurIPS 2023QLoRA: Efficient Finetuning of Quantized LLMs
- NeurIPS 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework
- NeurIPS 2023Quilt-1M: One Million Image-Text Pairs for Histopathology
- NeurIPS 2023QuIP: 2-Bit Quantization of Large Language Models With Guarantees
- NeurIPS 2023RaLEs: a Benchmark for Radiology Language Evaluations
- NeurIPS 2023Random-Access Infinite Context Length for Transformers
- NeurIPS 2023Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
- NeurIPS 2023RECKONING: Reasoning through Dynamic Knowledge Encoding
- NeurIPS 2023RegBN: Batch Normalization of Multimodal Data with Regularization
- NeurIPS 2023Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”
- NeurIPS 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
- NeurIPS 2023Reusing Pretrained Models by Multi-linear Operators for Efficient Training
- NeurIPS 2023Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective
- NeurIPS 2023Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations
- NeurIPS 2023Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
- NeurIPS 2023RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy
- NeurIPS 2023RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments
- NeurIPS 2023Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks
- NeurIPS 2023Robust Mean Estimation Without Moments for Symmetric Distributions
- NeurIPS 2023rPPG-Toolbox: Deep Remote PPG Toolbox
- NeurIPS 2023Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field
- NeurIPS 2023RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
- NeurIPS 2023S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
- NeurIPS 2023SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection
- NeurIPS 2023SatLM: Satisfiability-Aided Language Models Using Declarative Prompting
- NeurIPS 2023Scale-Space Hypernetworks for Efficient Biomedical Image Analysis
- NeurIPS 2023Scaling laws for language encoding models in fMRI
- NeurIPS 2023Scaling Open-Vocabulary Object Detection
- NeurIPS 2023Scattering Vision Transformer: Spectral Mixing Matters
- NeurIPS 2023SceneScape: Text-Driven Consistent Scene Generation
- NeurIPS 2023Scientific Document Retrieval using Multi-level Aspect-based Queries
- NeurIPS 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
- NeurIPS 2023Segment Everything Everywhere All at Once
- NeurIPS 2023Self-Chained Image-Language Model for Video Localization and Question Answering
- NeurIPS 2023Self-Evaluation Guided Beam Search for Reasoning
- NeurIPS 2023Self-Refine: Iterative Refinement with Self-Feedback
- NeurIPS 2023Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots
- NeurIPS 2023Skill-it! A data-driven skills framework for understanding and training language models
- NeurIPS 2023SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
- NeurIPS 2023Spatio-Angular Convolutions for Super-resolution in Diffusion MRI
- NeurIPS 2023SQ Lower Bounds for Learning Mixtures of Linear Classifiers
- NeurIPS 2023Stability Guarantees for Feature Attributions with Multiplicative Smoothing
- NeurIPS 2023Stable and low-precision training for large-scale vision-language models
- NeurIPS 2023StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
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。