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 31 / 35 页
- NeurIPS 2024Mars: Situated Inductive Reasoning in an Open-World Environment
- NeurIPS 2024MathPile: A Billion-Token-Scale Pretraining Corpus for Math
- NeurIPS 2024Matryoshka Query Transformer for Large Vision-Language Models
- NeurIPS 2024MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
- NeurIPS 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
- NeurIPS 2024Measuring Dejavu Memorization Efficiently
- NeurIPS 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
- NeurIPS 2024MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
- NeurIPS 2024MedCalc-Bench: Evaluating Large Language Models for Medical Calculations
- NeurIPS 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
- NeurIPS 2024Membership Inference Attacks against Large Vision-Language Models
- NeurIPS 2024MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
- NeurIPS 2024MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
- NeurIPS 2024MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
- NeurIPS 2024Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
- NeurIPS 2024Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding
- NeurIPS 2024Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
- NeurIPS 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
- NeurIPS 2024MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
- NeurIPS 2024Mitigating Object Hallucination via Concentric Causal Attention
- NeurIPS 2024MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
- NeurIPS 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
- NeurIPS 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
- NeurIPS 2024MmCows: A Multimodal Dataset for Dairy Cattle Monitoring
- NeurIPS 2024MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
- NeurIPS 2024MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
- NeurIPS 2024MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation
- NeurIPS 2024MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
- NeurIPS 2024MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
- NeurIPS 2024MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
- NeurIPS 2024MoVA: Adapting Mixture of Vision Experts to Multimodal Context
- NeurIPS 2024MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
- NeurIPS 2024Multi-modal Situated Reasoning in 3D Scenes
- NeurIPS 2024Multilingual Diversity Improves Vision-Language Representations
- NeurIPS 2024Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
- NeurIPS 2024Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
- NeurIPS 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
- NeurIPS 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
- NeurIPS 2024NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
- NeurIPS 2024Needle In A Multimodal Haystack
- NeurIPS 2024Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction
- NeurIPS 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
- NeurIPS 2024No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
- NeurIPS 2024NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
- NeurIPS 2024Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
- NeurIPS 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
- NeurIPS 2024Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
- NeurIPS 2024OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
- NeurIPS 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
- NeurIPS 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
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。