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 17 / 225 页
- CVPR 2026One Token Two Fates A Unified Framework via Vision Token
- CVPR 2026OneCAT Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
- CVPR 2026OneSparse A Unified Framework for Sparse Activation Layers in Vision
- CVPR 2026OneThinker All-in-one Reasoning Model for Image and Video
- CVPR 2026Online Data Curation for Object Detection via Marginal Contributions to
- CVPR 2026OnlinePG Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting
- CVPR 2026OntoAug Rethinking Generative Data Augmentation via Ontology Guidance
- CVPR 2026Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
- CVPR 2026OpenDance Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
- CVPR 2026OpenDPR Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for
- CVPR 2026OpenMarcie Dataset for Multimodal Action Recognition in Industrial Environments
- CVPR 2026OpenMMReasoner Pushing the Frontiers in Multimodal Reasoning with an Open
- CVPR 2026OpenVision 2 A Family of Generative Pretrained Visual Encoders for
- CVPR 2026OpenVoxel Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene
- CVPR 2026OralGPT-Plus Learning to Use Visual Tools via Reinforcement Learning for
- CVPR 2026OraPO Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report
- CVPR 2026ORBIT Benchmarking SfM in the Wild with 360deg Video
- CVPR 2026ORIC Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language
- CVPR 2026OrienPose Orientation-Guided Novel View Synthesis for Single-Image Unseen Object Pose
- CVPR 2026ORION ORthonormal Text Encoding for Universal VLM AdaptatION
- CVPR 2026OrionEdit Bridging Reference and Source Images for Generalized Cross-Image Editing
- CVPR 2026ORSATR-X A Foundation Model based on Differential-and-Excitation Networks for Optical
- CVPR 2026OSMO Open-vocabulary Self-eMOtion Tracking
- CVPR 2026OVI-MAP Open-Vocabulary Instance-Semantic Mapping
- CVPR 2026OVOD-Agent A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving
- CVPR 2026P-Flow Prompting Visual Effects Generation
- CVPR 2026PA-Attack Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes
- CVPR 2026PACT Phase-Like Transition Constraints in Adapter-Based Continual Learning of Vision-Language
- CVPR 2026PAI-Bench A Comprehensive Benchmark For Physical AI
- CVPR 2026PALM Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic
- CVPR 2026PanDA Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in
- CVPR 2026Pano360 Perspective to Panoramic Vision with Geometric Consistency
- CVPR 2026PanoEnv Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement
- CVPR 2026Parallax to Align Them All An OmniParallax Attention Mechanism for
- CVPR 2026Parallel Jacobi Decoding for Fast Autoregressive Image Generation
- CVPR 2026ParaUni Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical
- CVPR 2026PAS A Training-Free Stabilizer for Temporal Encoding in Video LLMs
- CVPR 2026PAS Prelim Attention Score for Detecting Object Hallucinations in Large
- CVPR 2026PatchAlign3D Local Feature Alignment for Dense 3D Shape Understanding
- CVPR 2026PAVAS Physics-Aware Video-to-Audio Synthesis
- CVPR 2026PCA-Seg Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation
- CVPR 2026PDCR Perception-Decomposed Confidence Reward for Vision-Language Reasoning
- CVPR 2026Percept-WAM Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
- CVPR 2026Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
- CVPR 2026PercHead Perceptual Head Model for Single-Image 3D Head Reconstruction
- CVPR 2026PerformRecast Expression and Head Pose Disentanglement for Portrait Video Editing
- CVPR 2026PersonaLive Expressive Portrait Image Animation for Live Streaming
- CVPR 2026Personalized Image Descriptions from Attention Sequences
- CVPR 2026PersonaVLM Long-Term Personalized Multimodal LLMs
- CVPR 2026PETAR Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET
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。