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 1,716 篇，第 22 / 35 页
- ICML 2024Flexible Residual Binarization for Image Super-Resolution
- ICML 2024Flextron: Many-in-One Flexible Large Language Model
- ICML 2024Fool Your (Vision and) Language Model with Embarrassingly Simple Permutations
- ICML 2024FrameQuant: Flexible Low-Bit Quantization for Transformers
- ICML 2024FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
- ICML 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
- ICML 2024Gambling-Based Confidence Sequences for Bounded Random Vectors
- ICML 2024GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
- ICML 2024Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis
- ICML 2024Generalized Neural Collapse for a Large Number of Classes
- ICML 2024Generalizing Orthogonalization for Models with Non-Linearities
- ICML 2024Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
- ICML 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
- ICML 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
- ICML 2024GPT-4V(ision) is a Generalist Web Agent, if Grounded
- ICML 2024Gradient-based Visual Explanation for Transformer-based CLIP
- ICML 2024Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
- ICML 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
- ICML 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
- ICML 2024Harmonizing Generalization and Personalization in Federated Prompt Learning
- ICML 2024Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning
- ICML 2024High-Order Contrastive Learning with Fine-grained Comparative Levels for Sparse Ordinal Tensor Completion
- ICML 2024How Flawed Is ECE? An Analysis via Logit Smoothing
- ICML 2024Image Fusion via Vision-Language Model
- ICML 2024Image Hijacks: Adversarial Images can Control Generative Models at Runtime
- ICML 2024Implicit meta-learning may lead language models to trust more reliable sources
- ICML 2024Implicit Representations for Constrained Image Segmentation
- ICML 2024Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning
- ICML 2024Improving Factuality and Reasoning in Language Models through Multiagent Debate
- ICML 2024Improving fine-grained understanding in image-text pre-training
- ICML 2024Improving Interpretation Faithfulness for Vision Transformers
- ICML 2024In-Context Principle Learning from Mistakes
- ICML 2024Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
- ICML 2024Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
- ICML 2024Interpretable Deep Clustering for Tabular Data
- ICML 2024IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
- ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs
- ICML 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- ICML 2024KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
- ICML 2024Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
- ICML 2024Language Models Represent Beliefs of Self and Others
- ICML 2024Language Models with Conformal Factuality Guarantees
- ICML 2024Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition
- ICML 2024Large Language Models are Geographically Biased
- ICML 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
- ICML 2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
- ICML 2024Latent variable model for high-dimensional point process with structured missingness
- ICML 2024LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
- ICML 2024Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
- ICML 2024Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
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。