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 66 / 67 页
- NeurIPS 2023StressID: a Multimodal Dataset for Stress Identification
- NeurIPS 2023Structured Semidefinite Programming for Recovering Structured Preconditioners
- NeurIPS 2023SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
- NeurIPS 2023SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models
- NeurIPS 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
- NeurIPS 2023Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
- NeurIPS 2023Symbolic Discovery of Optimization Algorithms
- NeurIPS 2023Systematic Visual Reasoning through Object-Centric Relational Abstraction
- NeurIPS 2023T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
- NeurIPS 2023TART: A plug-and-play Transformer module for task-agnostic reasoning
- NeurIPS 2023Test-Time Distribution Normalization for Contrastively Learned Visual-language Models
- NeurIPS 2023Test-time Training for Matching-based Video Object Segmentation
- NeurIPS 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
- NeurIPS 2023Text Promptable Surgical Instrument Segmentation with Vision-Language Models
- NeurIPS 2023Text-to-Image Diffusion Models are Zero Shot Classifiers
- NeurIPS 2023Textually Pretrained Speech Language Models
- NeurIPS 2023The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
- NeurIPS 2023The Learnability of In-Context Learning
- NeurIPS 2023The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification
- NeurIPS 2023The ToMCAT Dataset
- NeurIPS 2023Three Towers: Flexible Contrastive Learning with Pretrained Image Models
- NeurIPS 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Series
- NeurIPS 2023Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
- NeurIPS 2023Toolbox for Multimodal Learn (scikit-multimodallearn)
- NeurIPS 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
- NeurIPS 2023ToolQA: A Dataset for LLM Question Answering with External Tools
- NeurIPS 2023Topology-Aware Uncertainty for Image Segmentation
- NeurIPS 2023Towards Efficient Image Compression Without Autoregressive Models
- NeurIPS 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
- NeurIPS 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
- NeurIPS 2023Towards Label-free Scene Understanding by Vision Foundation Models
- NeurIPS 2023Towards Optimal Caching and Model Selection for Large Model Inference
- NeurIPS 2023Training Transitive and Commutative Multimodal Transformers with LoReTTa
- NeurIPS 2023TransHP: Image Classification with Hierarchical Prompting
- NeurIPS 2023Transition-constant Normalization for Image Enhancement
- NeurIPS 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- NeurIPS 2023TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
- NeurIPS 2023Type-to-Track: Retrieve Any Object via Prompt-based Tracking
- NeurIPS 2023Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval
- NeurIPS 2023Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
- NeurIPS 2023Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
- NeurIPS 2023Understanding Social Reasoning in Language Models with Language Models
- NeurIPS 2023Universality laws for Gaussian mixtures in generalized linear models
- NeurIPS 2023Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval
- NeurIPS 2023UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
- NeurIPS 2023Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
- NeurIPS 2023Validated Image Caption Rating Dataset
- NeurIPS 2023VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
- NeurIPS 2023VidChapters-7M: Video Chapters at Scale
- NeurIPS 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
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。