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 128 / 225 页
- ICLR 2025Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
- ICLR 2025Latent Action Pretraining from Videos
- ICLR 2025Layerwise Recurrent Router for Mixture-of-Experts
- ICLR 2025LeanAgent: Lifelong Learning for Formal Theorem Proving
- ICLR 2025Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion
- ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
- ICLR 2025Learning Dynamics of LLM Finetuning
- ICLR 2025Learning Gain Map for Inverse Tone Mapping
- ICLR 2025Learning Harmonized Representations for Speculative Sampling
- ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
- ICLR 2025Learning Mask Invariant Mutual Information for Masked Image Modeling
- ICLR 2025Learning Spatial-Semantic Features for Robust Video Object Segmentation
- ICLR 2025Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
- ICLR 2025LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
- ICLR 2025Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction
- ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
- ICLR 2025LICO: Large Language Models for In-Context Molecular Optimization
- ICLR 2025Lightweight Neural App Control
- ICLR 2025LiveBench: A Challenging, Contamination-Limited LLM Benchmark
- ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- ICLR 2025LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
- ICLR 2025LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
- ICLR 2025LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
- ICLR 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
- ICLR 2025LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases
- ICLR 2025LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
- ICLR 2025LLMs Can Plan Only If We Tell Them
- ICLR 2025LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
- ICLR 2025Local Patterns Generalize Better for Novel Anomalies
- ICLR 2025Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
- ICLR 2025Locality Alignment Improves Vision-Language Models
- ICLR 2025Logically Consistent Language Models via Neuro-Symbolic Integration
- ICLR 2025Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
- ICLR 2025LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
- ICLR 2025Long Context Compression with Activation Beacon
- ICLR 2025Longhorn: State Space Models are Amortized Online Learners
- ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
- ICLR 2025Looking Inward: Language Models Can Learn About Themselves by Introspection
- ICLR 2025LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models
- ICLR 2025LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
- ICLR 2025Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
- ICLR 2025MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
- ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
- ICLR 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
- ICLR 2025MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
- ICLR 2025Matryoshka Multimodal Models
- ICLR 2025MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
- ICLR 2025MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
- ICLR 2025Measuring And Improving Engagement of Text-to-Image Generation Models
- ICLR 2025Measuring And Improving Persuasiveness Of Large 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。