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 795 篇，第 10 / 16 页
- CVPR 2025MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments
- CVPR 2025MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
- CVPR 2025MMRL: Multi-Modal Representation Learning for Vision-Language Models
- CVPR 2025MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception
- CVPR 2025MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
- CVPR 2025Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
- CVPR 2025ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling
- CVPR 2025MoEdit: On Learning Quantity Perception for Multi-object Image Editing
- CVPR 2025Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
- CVPR 2025MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation
- CVPR 2025Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
- CVPR 2025MonSter: Marry Monodepth to Stereo Unleashes Power
- CVPR 2025Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning
- CVPR 2025Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
- CVPR 2025Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
- CVPR 2025MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
- CVPR 2025MotionPro: A Precise Motion Controller for Image-to-Video Generation
- CVPR 2025MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
- CVPR 2025MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
- CVPR 2025Multi-Group Proportional Representations for Text-to-Image Models
- CVPR 2025Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
- CVPR 2025Multi-modal Knowledge Distillation-based Human Trajectory Forecasting
- CVPR 2025Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation
- CVPR 2025Multi-modal Vision Pre-training for Medical Image Analysis
- CVPR 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
- CVPR 2025Multimodal Autoregressive Pre-training of Large Vision Encoders
- CVPR 2025MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval
- CVPR 2025MuTri: Multi-view Tri-alignment for OCT to OCTA 3D Image Translation
- CVPR 2025MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
- CVPR 2025Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions
- CVPR 2025Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features
- CVPR 2025Neural Hierarchical Decomposition for Single Image Plant Modeling
- CVPR 2025NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
- CVPR 2025nnWNet: Rethinking the Use of Transformers in Biomedical Image Segmentation and Calling for a Unified Evaluation Benchmark
- CVPR 2025No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition
- CVPR 2025Noise Calibration and Spatial-Frequency Interactive Network for STEM Image Enhancement
- CVPR 2025Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis
- CVPR 2025Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
- CVPR 2025Non-Natural Image Understanding with Advancing Frequency-based Vision Encoders
- CVPR 2025Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
- CVPR 2025Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
- CVPR 2025Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering
- CVPR 2025NSD-Imagery: A Benchmark Dataset for Extending fMRI Vision Decoding Methods to Mental Imagery
- CVPR 2025Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
- CVPR 2025Number it: Temporal Grounding Videos like Flipping Manga
- CVPR 2025O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models
- CVPR 2025Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation
- CVPR 2025Object-Shot Enhanced Grounding Network for Egocentric Video
- CVPR 2025Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
- CVPR 2025ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models
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。