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 3,302 篇，第 28 / 67 页
- CVPR 2026Where Does Vision Meet Language Understanding and Refining Visual Fusion
- CVPR 2026Where MLLMs Attend and What They Rely On Explaining Autoregressive
- CVPR 2026Which Concepts to Forget and How to Refuse Decomposing Concepts
- CVPR 2026White-Balance First Adjust Later Cross-Camera Color Constancy via Vision-Language Evaluation
- CVPR 2026Why Does RL Generalize Better Than SFT A Data-Centric Perspective
- CVPR 2026Widget2Code From Visual Widgets to UI Code via Multimodal LLMs
- CVPR 2026WildCap Facial Albedo Capture in the Wild via Hybrid Inverse
- CVPR 2026WildPose A Unified Framework for Robust Pose Estimation in the
- CVPR 2026Will Multimodal Models Be Dazzled by Multi-Image Visual Puzzles
- CVPR 2026WISER Wider Search Deeper Thinking and Adaptive Fusion for Training-Free
- CVPR 2026World in a Frame Understanding Culture Mixing as a New
- CVPR 2026WorldMM Dynamic Multimodal Memory Agent for Long Video Reasoning
- CVPR 2026X-PCR A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic
- CVPR 2026x2-Fusion Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space
- CVPR 2026XPaintNet An eXtreme Lightweight Framework for Stereoscopic Conversion without Inpainting
- CVPR 2026YieldSAT A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction
- CVPR 2026YOSE You Only Select Essential Tokens for Efficient DiT-based Video
- CVPR 2026Your One-Stop Solution for AI-Generated Video Detection
- CVPR 2026Zero-Shot Depth Completion with Vision-Language Model
- CVPR 2026ZINA Multimodal Fine-grained Hallucination Detection and Editing
- CVPR 2026ZOO-Prune Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language
- CVPR 2026ZoomEarth Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks
- CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
- CVPR 20253D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
- CVPR 20253D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
- CVPR 20253D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
- CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
- CVPR 20254Deform: Neural Surface Deformation for Robust Shape Interpolation
- CVPR 2025A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
- CVPR 2025A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
- CVPR 2025A Flag Decomposition for Hierarchical Datasets
- CVPR 2025A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations
- CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
- CVPR 2025A Regularization-Guided Equivariant Approach for Image Restoration
- CVPR 2025A Semantic Knowledge Complementarity based Decoupling Framework for Semi-supervised Class-imbalanced Medical Image Segmentation
- CVPR 2025A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
- CVPR 2025A Unified Image-Dense Annotation Generation Model for Underwater Scenes
- CVPR 2025A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
- CVPR 2025A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts
- CVPR 2025A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment
- CVPR 2025ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects
- CVPR 2025Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
- CVPR 2025ACL: Activating Capability of Linear Attention for Image Restoration
- CVPR 2025Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration
- CVPR 2025Activating Sparse Part Concepts for 3D Class Incremental Learning
- CVPR 2025Active Data Curation Effectively Distills Large-Scale Multimodal Models
- CVPR 2025Active Event-based Stereo Vision
- CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
- CVPR 2025AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
- CVPR 2025Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
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。