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 2,676 篇，第 52 / 54 页
- ICLR 2023Basic Binary Convolution Unit for Binarized Image Restoration Network
- ICLR 2023Boosting Adversarial Transferability using Dynamic Cues
- ICLR 2023Budgeted Training for Vision Transformer
- ICLR 2023Can CNNs Be More Robust Than Transformers?
- ICLR 2023ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length
- ICLR 2023CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
- ICLR 2023CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
- ICLR 2023CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
- ICLR 2023Complexity-Based Prompting for Multi-step Reasoning
- ICLR 2023Composing Ensembles of Pre-trained Models via Iterative Consensus
- ICLR 2023Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
- ICLR 2023Conditional Positional Encodings for Vision Transformers
- ICLR 2023Contextual Convolutional Networks
- ICLR 2023Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining
- ICLR 2023Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning
- ICLR 2023Corrupted Image Modeling for Self-Supervised Visual Pre-Training
- ICLR 2023Cross-Layer Retrospective Retrieving via Layer Attention
- ICLR 2023Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- ICLR 2023Diagnosing and Rectifying Vision Models using Language
- ICLR 2023DINO as a von Mises-Fisher mixture model
- ICLR 2023Discovering Informative and Robust Positives for Video Domain Adaptation
- ICLR 2023DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
- ICLR 2023Dual Student Networks for Data-Free Model Stealing
- ICLR 2023Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning
- ICLR 2023Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
- ICLR 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement
- ICLR 2023Energy-Inspired Self-Supervised Pretraining for Vision Models
- ICLR 2023Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification
- ICLR 2023Exploring Temporally Dynamic Data Augmentation for Video Recognition
- ICLR 2023Faster Gradient-Free Methods for Escaping Saddle Points
- ICLR 2023Fundamental limits on the robustness of image classifiers
- ICLR 2023GAMR: A Guided Attention Model for (visual) Reasoning
- ICLR 2023Generalization and Estimation Error Bounds for Model-based Neural Networks
- ICLR 2023Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
- ICLR 2023GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
- ICLR 2023HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention
- ICLR 2023HiViT: A Simpler and More Efficient Design of Hierarchical Vision Transformer
- ICLR 2023Human MotionFormer: Transferring Human Motions with Vision Transformers
- ICLR 2023Identifiability Results for Multimodal Contrastive Learning
- ICLR 2023Image as Set of Points
- ICLR 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
- ICLR 2023Interactive Portrait Harmonization
- ICLR 2023ISAAC Newton: Input-based Approximate Curvature for Newton's Method
- ICLR 2023Iterative Patch Selection for High-Resolution Image Recognition
- ICLR 2023Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
- ICLR 2023Large Language Models are Human-Level Prompt Engineers
- ICLR 2023Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
- ICLR 2023Learning Iterative Neural Optimizers for Image Steganography
- ICLR 2023Learning Multimodal Data Augmentation in Feature Space
- ICLR 2023Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
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。