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 390 篇，第 4 / 8 页
- ICML 2025HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
- ICML 2025HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
- ICML 2025HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
- ICML 2025HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion
- ICML 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
- ICML 2025Hidden No More: Attacking and Defending Private Third-Party LLM Inference
- ICML 2025High-Fidelity Simultaneous Speech-To-Speech Translation
- ICML 2025How Effective Can Dropout Be in Multiple Instance Learning ?
- ICML 2025Hypo3D: Exploring Hypothetical Reasoning in 3D
- ICML 2025I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
- ICML 2025Imagine While Reasoning in Space: Multimodal Visualization-of-Thought
- ICML 2025Improving LLM Video Understanding with 16 Frames Per Second
- ICML 2025Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
- ICML 2025Improving Multimodal Learning Balance and Sufficiency through Data Remixing
- ICML 2025Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
- ICML 2025In-Context Fine-Tuning for Time-Series Foundation Models
- ICML 2025Instruction-Following Pruning for Large Language Models
- ICML 2025Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
- ICML 2025Interpreting CLIP with Hierarchical Sparse Autoencoders
- ICML 2025Interpreting the Repeated Token Phenomenon in Large Language Models
- ICML 2025Investigating the Overlooked Hessian Structure: From CNNs to LLMs
- ICML 2025Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
- ICML 2025LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
- ICML 2025LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
- ICML 2025Large Language Models are Demonstration Pre-Selectors for Themselves
- ICML 2025Layer by Layer: Uncovering Hidden Representations in Language Models
- ICML 2025Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
- ICML 2025Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
- ICML 2025Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control
- ICML 2025Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
- ICML 2025Learning Dynamics in Continual Pre-Training for Large Language Models
- ICML 2025Learning Event Completeness for Weakly Supervised Video Anomaly Detection
- ICML 2025Learning Invariant Causal Mechanism from Vision-Language Models
- ICML 2025Learning Optimal Multimodal Information Bottleneck Representations
- ICML 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
- ICML 2025Learning Vision and Language Concepts for Controllable Image Generation
- ICML 2025LEMoN: Label Error Detection using Multimodal Neighbors
- ICML 2025Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation
- ICML 2025LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
- ICML 2025Lightweight Online Adaption for Time Series Foundation Model Forecasts
- ICML 2025Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge
- ICML 2025LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
- ICML 2025LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
- ICML 2025LLMs can see and hear without any training
- ICML 2025LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
- ICML 2025LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
- ICML 2025Long-Short Alignment for Effective Long-Context Modeling in LLMs
- ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
- ICML 2025Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
- ICML 2025LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
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。