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 1,716 篇，第 9 / 35 页
- CVPR 2024Open-Vocabulary Object 6D Pose Estimation
- CVPR 2024Osprey: Pixel Understanding with Visual Instruction Tuning
- CVPR 2024OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
- CVPR 2024OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation
- CVPR 2024Overcoming Generic Knowledge Loss with Selective Parameter Update
- CVPR 2024OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation
- CVPR 2024OVMR: Open-Vocabulary Recognition with Multi-Modal References
- CVPR 2024PairAug: What Can Augmented Image-Text Pairs Do for Radiology?
- CVPR 2024Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
- CVPR 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
- CVPR 2024PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
- CVPR 2024PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
- CVPR 2024PELA: Learning Parameter-Efficient Models with Low-Rank Approximation
- CVPR 2024PEM: Prototype-based Efficient MaskFormer for Image Segmentation
- CVPR 2024PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
- CVPR 2024PIGEON: Predicting Image Geolocations
- CVPR 2024PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs
- CVPR 2024Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
- CVPR 2024Pixel-Aligned Language Model
- CVPR 2024PixelLM: Pixel Reasoning with Large Multimodal Model
- CVPR 2024PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis
- CVPR 2024PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos
- CVPR 2024Point Segment and Count: A Generalized Framework for Object Counting
- CVPR 2024PointBeV: A Sparse Approach for BeV Predictions
- CVPR 2024PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting
- CVPR 2024Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
- CVPR 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
- CVPR 2024Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
- CVPR 2024Pre-training Vision Models with Mandelbulb Variations
- CVPR 2024Previously on ... From Recaps to Story Summarization
- CVPR 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
- CVPR 2024Projecting Trackable Thermal Patterns for Dynamic Computer Vision
- CVPR 2024Prompt Highlighter: Interactive Control for Multi-Modal LLMs
- CVPR 2024Prompt Learning via Meta-Regularization
- CVPR 2024Prompt-Driven Referring Image Segmentation with Instance Contrasting
- CVPR 2024Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
- CVPR 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
- CVPR 2024Prompting Vision Foundation Models for Pathology Image Analysis
- CVPR 2024PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
- CVPR 2024PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation
- CVPR 2024Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity
- CVPR 2024PTQ4SAM: Post-Training Quantization for Segment Anything
- CVPR 2024Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
- CVPR 2024QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction
- CVPR 2024Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
- CVPR 2024Question Aware Vision Transformer for Multimodal Reasoning
- CVPR 2024Random Entangled Tokens for Adversarially Robust Vision Transformer
- CVPR 2024Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels
- CVPR 2024REACTO: Reconstructing Articulated Objects from a Single Video
- CVPR 2024Region-Based Representations Revisited
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。