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 40 / 67 页
- CVPR 2025ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
- CVPR 2025Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
- CVPR 2025Rethinking Query-based Transformer for Continual Image Segmentation
- CVPR 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
- CVPR 2025Reversible Decoupling Network for Single Image Reflection Removal
- CVPR 2025Reversing Flow for Image Restoration
- CVPR 2025ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
- CVPR 2025Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
- CVPR 2025Revisiting MAE Pre-training for 3D Medical Image Segmentation
- CVPR 2025ReWind: Understanding Long Videos with Instructed Learnable Memory
- CVPR 2025RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement
- CVPR 2025RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
- CVPR 2025RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
- CVPR 2025RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
- CVPR 2025Robotic Visual Instruction
- CVPR 2025RobSense: A Robust Multi-modal Foundation Model for Remote Sensing with Static, Temporal, and Incomplete Data Adaptability
- CVPR 2025Robust Message Embedding via Attention Flow-Based Steganography
- CVPR 2025Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder
- CVPR 2025ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
- CVPR 2025RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
- CVPR 2025S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Model with Spatio-Temporal Visual Representation
- CVPR 2025SACB-Net: Spatial-awareness Convolutions for Medical Image Registration
- CVPR 2025SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining
- CVPR 2025Saliuitl: Ensemble Salience Guided Recovery of Adversarial Patches against CNNs
- CVPR 2025SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost
- CVPR 2025SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model
- CVPR 2025SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer
- CVPR 2025SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
- CVPR 2025SapiensID: Foundation for Human Recognition
- CVPR 2025SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
- CVPR 2025Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
- CVPR 2025SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
- CVPR 2025SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
- CVPR 2025SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
- CVPR 2025SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures
- CVPR 2025SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction
- CVPR 2025SEAL: Semantic Attention Learning for Long Video Representation
- CVPR 2025SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
- CVPR 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
- CVPR 2025Seeing More with Less: Human-like Representations in Vision Models
- CVPR 2025Seeing the Abstract: Translating the Abstract Language for Vision Language Models
- CVPR 2025Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition
- CVPR 2025SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection
- CVPR 2025Self-Evolving Visual Concept Library using Vision-Language Critics
- CVPR 2025Semantic and Expressive Variations in Image Captions Across Languages
- CVPR 2025Semantic and Sequential Alignment for Referring Video Object Segmentation
- CVPR 2025Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining
- CVPR 2025SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation
- CVPR 2025Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
- CVPR 2025SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
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。