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 626 篇，第 11 / 13 页
- CVPR 2024SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection
- CVPR 2024SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
- CVPR 2024SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge
- CVPR 2024Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers
- CVPR 2024SonicVisionLM: Playing Sound with Vision Language Models
- CVPR 2024SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
- CVPR 2024Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
- CVPR 2024Sparse Global Matching for Video Frame Interpolation with Large Motion
- CVPR 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
- CVPR 2024SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction
- CVPR 2024Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset
- CVPR 2024SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing
- CVPR 2024SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks
- CVPR 2024Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
- CVPR 2024SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation
- CVPR 2024State Space Models for Event Cameras
- CVPR 2024Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements
- CVPR 2024StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
- CVPR 2024Step Differences in Instructional Video
- CVPR 2024Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
- CVPR 2024Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation
- CVPR 2024Super-Resolution Reconstruction from Bayer-Pattern Spike Streams
- CVPR 2024SURE: SUrvey REcipes for building reliable and robust deep networks
- CVPR 2024SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction
- CVPR 2024SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
- CVPR 2024Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding
- CVPR 2024Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
- CVPR 2024Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification
- CVPR 2024Task-Aware Encoder Control for Deep Video Compression
- CVPR 2024Task-Customized Mixture of Adapters for General Image Fusion
- CVPR 2024Test-Time Zero-Shot Temporal Action Localization
- CVPR 2024Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval
- CVPR 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection
- CVPR 2024Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis
- CVPR 2024Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
- CVPR 2024Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion
- CVPR 2024TexTile: A Differentiable Metric for Texture Tileability
- CVPR 2024The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
- CVPR 2024The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding
- CVPR 2024The Manga Whisperer: Automatically Generating Transcriptions for Comics
- CVPR 2024The Neglected Tails in Vision-Language Models
- CVPR 2024The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement
- CVPR 2024Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts
- CVPR 2024Three Pillars Improving Vision Foundation Model Distillation for Lidar
- CVPR 2024THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models
- CVPR 2024TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
- CVPR 2024TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing
- CVPR 2024Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
- CVPR 2024Towards 3D Vision with Low-Cost Single-Photon Cameras
- CVPR 2024Towards Better Vision-Inspired Vision-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。