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 11,207 篇，第 20 / 225 页
- CVPR 2026ReMoT Reinforcement Learning with Motion Contrast Triplets
- CVPR 2026Remote Sensing Image Super-Resolution for Imbalanced Textures A Texture-Aware Diffusion
- CVPR 2026Residual Decoding Mitigating Hallucinations in Large Vision-Language Models via History-Aware
- CVPR 2026Residual Diffusion Bridge Model for Image Restoration
- CVPR 2026ResiHMR Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals
- CVPR 2026Resolving Evidence Sparsity Agentic Context Engineering for Long-Document Understanding
- CVPR 2026Restore Assess Repeat A Unified Framework for Iterative Image Restoration
- CVPR 2026RetFormer Multimodal Retrieval for Enhancing Image Recognition
- CVPR 2026Rethinking Asymmetric Quantization Hidden Symmetry in Vision Model Weights
- CVPR 2026Rethinking BCE Loss for Multi-Label Image Recognition with Fine-Tuning
- CVPR 2026Rethinking Concept Bottleneck Models From Pitfalls to Solutions
- CVPR 2026Rethinking Intermediate Representation for VLM-based Robot Manipulation
- CVPR 2026Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein
- CVPR 2026Rethinking Token Reduction for Large Vision-Language Models
- CVPR 2026RetouchIQ MLLM Agents for Instruction-Based Image Retouching with Generalist Reward
- CVPR 2026Retrieve and Segment Are a Few Examples Enough to Bridge
- CVPR 2026Retrieving Counterfactuals Improves Visual In-Context Learning
- CVPR 2026Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification
- CVPR 2026Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image
- CVPR 2026Revisiting Model Stitching In the Foundation Model Era
- CVPR 2026Revisiting Multimodal KV Cache Compression A Frequency-Domain-Guided Outlier-KV-Aware Approach
- CVPR 2026Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization
- CVPR 2026Revisiting Visual Corruptions in LVLMs A Shape-Texture Perspective on Model
- CVPR 2026REVISOR Beyond Textual Reflection Towards Multimodal Introspective Reasoning in Long-Form
- CVPR 2026REVIVE 3D Refinement via Encoded Voluminous Inflated prior for Volume
- CVPR 2026Reward Forcing Efficient Streaming Video Generation with Rewarded Distribution Matching
- CVPR 2026RMIR A Benchmark Dataset for Reasoning-Intensive Multimodal Image Retrieval
- CVPR 2026RNED Rotary Number Encoding and Decoding for Medical VLMs
- CVPR 2026RoadSceneBench A Lightweight Benchmark for Mid-Level Road Scene Understanding
- CVPR 2026RoboAgent Chaining Basic Capabilities for Embodied Task Planning
- CVPR 2026RobotSeg A Model and Dataset for Segmenting Robots in Image
- CVPR 2026RoboWheel A Data Engine from Real-World Human Demonstrations for Cross-Embodiment
- CVPR 2026RobustVisRAG Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
- CVPR 2026RoMo A Large-Scale Richly Organized Dataset and Semantic Taxonomy for
- CVPR 2026ROSE Rotate Your Large Language Model to See
- CVPR 2026Rosetta Stone For Unified MLLMs A Unified Tokenizer to Decipher
- CVPR 2026Rounded or Streamlined Head Bridging Concept Bottleneck Models and Attribute-Described
- CVPR 2026rPPG-VQA A Video Quality Assessment Framework for Unsupervised rPPG Training
- CVPR 2026RS-SSM Refining Forgotten Specifics in State Space Model for Video
- CVPR 2026RunawayEvil Jailbreaking the Image-to-Video Generative Models
- CVPR 2026S2C2Seg Semantic-Spatial Consistency and Category Optimization for Open-Vocabulary Segmentation
- CVPR 2026S2D Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations
- CVPR 2026SafeGRPO Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
- CVPR 2026SafeLogo Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial
- CVPR 2026Saliency-Driven Token Merging for Vision Transformers
- CVPR 2026Saliency-R1 Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment
- CVPR 2026SALMUBench A Benchmark for Sensitive Association-Level Multimodal Unlearning
- CVPR 2026Same Attention Different Truths Put Logit-Lens over Visual Attention to
- CVPR 2026Same or Not Enhancing Visual Perception in Vision-Language Models
- CVPR 2026SANER Switchable Adapter with Non-parametric Enhanced Routing for Person De-Reidentification
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。