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 3,319 篇，第 60 / 67 页
- NeurIPS 2023Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
- NeurIPS 2023Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models
- NeurIPS 2023CLadder: Assessing Causal Reasoning in Language Models
- NeurIPS 2023CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection
- NeurIPS 2023COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs
- NeurIPS 2023Cola: A Benchmark for Compositional Text-to-image Retrieval
- NeurIPS 2023Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
- NeurIPS 2023Compact Neural Volumetric Video Representations with Dynamic Codebooks
- NeurIPS 2023Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
- NeurIPS 2023Compositional Foundation Models for Hierarchical Planning
- NeurIPS 2023Computational Guarantees for Doubly Entropic Wasserstein Barycenters
- NeurIPS 2023Computing a human-like reaction time metric from stable recurrent vision models
- NeurIPS 2023Consensus and Subjectivity of Skin Tone Annotation for ML Fairness
- NeurIPS 2023Context-PIPs: Persistent Independent Particles Demands Spatial Context Features
- NeurIPS 2023Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels
- NeurIPS 2023Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
- NeurIPS 2023Convolutional State Space Models for Long-Range Spatiotemporal Modeling
- NeurIPS 2023Counterfactual Memorization in Neural Language Models
- NeurIPS 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
- NeurIPS 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
- NeurIPS 2023CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss
- NeurIPS 2023D4: Improving LLM Pretraining via Document De-Duplication and Diversification
- NeurIPS 2023DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
- NeurIPS 2023Data Portraits: Recording Foundation Model Training Data
- NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
- NeurIPS 2023DataComp: In search of the next generation of multimodal datasets
- NeurIPS 2023DataPerf: Benchmarks for Data-Centric AI Development
- NeurIPS 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
- NeurIPS 2023Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
- NeurIPS 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
- NeurIPS 2023Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
- NeurIPS 2023DesCo: Learning Object Recognition with Rich Language Descriptions
- NeurIPS 2023Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents
- NeurIPS 2023Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
- NeurIPS 2023DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
- NeurIPS 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization
- NeurIPS 2023Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones
- NeurIPS 2023Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning
- NeurIPS 2023DISCOVER: Making Vision Networks Interpretable via Competition and Dissection
- NeurIPS 2023Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
- NeurIPS 2023Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering
- NeurIPS 2023Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models
- NeurIPS 2023Diverse Shape Completion via Style Modulated Generative Adversarial Networks
- NeurIPS 2023Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation
- NeurIPS 2023Diversifying Spatial-Temporal Perception for Video Domain Generalization
- NeurIPS 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- NeurIPS 2023Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization
- NeurIPS 2023DVSOD: RGB-D Video Salient Object Detection
- NeurIPS 2023Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
- NeurIPS 2023DynPoint: Dynamic Neural Point For View Synthesis
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。