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 10 / 25 页
- CVPR 2023Task Residual for Tuning Vision-Language Models
- CVPR 2023Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification
- CVPR 2023Teaching Structured Vision & Language Concepts to Vision & Language Models
- CVPR 2023Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation
- CVPR 2023Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields
- CVPR 2023Texts as Images in Prompt Tuning for Multi-Label Image Recognition
- CVPR 2023The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
- CVPR 2023TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
- CVPR 2023TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models
- CVPR 2023Top-Down Visual Attention From Analysis by Synthesis
- CVPR 2023TopNet: Transformer-Based Object Placement Network for Image Compositing
- CVPR 2023Toward Accurate Post-Training Quantization for Image Super Resolution
- CVPR 2023Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
- CVPR 2023Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
- CVPR 2023Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method
- CVPR 2023Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval
- CVPR 2023Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
- CVPR 2023Towards Scalable Neural Representation for Diverse Videos
- CVPR 2023Towards Universal Fake Image Detectors That Generalize Across Generative Models
- CVPR 2023Train-Once-for-All Personalization
- CVPR 2023Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer
- CVPR 2023TransFlow: Transformer As Flow Learner
- CVPR 2023Trap Attention: Monocular Depth Estimation With Manual Traps
- CVPR 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
- CVPR 2023TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization
- CVPR 2023Two-View Geometry Scoring Without Correspondences
- CVPR 2023ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
- CVPR 2023Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity
- CVPR 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
- CVPR 2023Uncertainty-Aware Vision-Based Metric Cross-View Geolocalization
- CVPR 2023Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
- CVPR 2023Unicode Analogies: An Anti-Objectivist Visual Reasoning Challenge
- CVPR 2023Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
- CVPR 2023Unifying Vision, Text, and Layout for Universal Document Processing
- CVPR 2023Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation
- CVPR 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
- CVPR 2023Video Event Restoration Based on Keyframes for Video Anomaly Detection
- CVPR 2023Video Test-Time Adaptation for Action Recognition
- CVPR 2023VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining
- CVPR 2023VindLU: A Recipe for Effective Video-and-Language Pretraining
- CVPR 2023Virtual Sparse Convolution for Multimodal 3D Object Detection
- CVPR 2023Vision Transformers Are Good Mask Auto-Labelers
- CVPR 2023Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves
- CVPR 2023Visual Programming: Compositional Visual Reasoning Without Training
- CVPR 2023Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning
- CVPR 2023Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery
- CVPR 2023Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting
- CVPR 2023ViTs for SITS: Vision Transformers for Satellite Image Time Series
- CVPR 2023VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
- CVPR 2023VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval
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。