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 199 / 225 页
- NeurIPS 2024The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data
- NeurIPS 2024Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
- NeurIPS 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
- NeurIPS 2024TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
- NeurIPS 2024TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
- NeurIPS 2024Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models
- NeurIPS 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
- NeurIPS 2024Towards Calibrated Robust Fine-Tuning of Vision-Language Models
- NeurIPS 2024Towards Flexible Visual Relationship Segmentation
- NeurIPS 2024Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
- NeurIPS 2024Towards Robust Multimodal Sentiment Analysis with Incomplete Data
- NeurIPS 2024Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
- NeurIPS 2024TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning
- NeurIPS 2024Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
- NeurIPS 2024TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
- NeurIPS 2024TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
- NeurIPS 2024UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
- NeurIPS 2024UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
- NeurIPS 2024Understanding Information Storage and Transfer in Multi-Modal Large Language Models
- NeurIPS 2024UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
- NeurIPS 2024Unified Generative and Discriminative Training for Multi-modal Large Language Models
- NeurIPS 2024UNIT: Unifying Image and Text Recognition in One Vision Encoder
- NeurIPS 2024Unity by Diversity: Improved Representation Learning for Multimodal VAEs
- NeurIPS 2024Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
- NeurIPS 2024Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
- NeurIPS 2024Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
- NeurIPS 2024Unveiling Encoder-Free Vision-Language Models
- NeurIPS 2024Unveiling the Tapestry of Consistency in Large Vision-Language Models
- NeurIPS 2024UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
- NeurIPS 2024UrbanDataLayer: A Unified Data Pipeline for Urban Science
- NeurIPS 2024USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
- NeurIPS 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
- NeurIPS 2024VastTrack: Vast Category Visual Object Tracking
- NeurIPS 2024VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
- NeurIPS 2024VHELM: A Holistic Evaluation of Vision Language Models
- NeurIPS 2024Video Token Merging for Long Video Understanding
- NeurIPS 2024VideoGUI: A Benchmark for GUI Automation from Instructional Videos
- NeurIPS 2024VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
- NeurIPS 2024ViLCo-Bench: VIdeo Language COntinual learning Benchmark
- NeurIPS 2024Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
- NeurIPS 2024Vision-Language Models are Strong Noisy Label Detectors
- NeurIPS 2024Vision-Language Navigation with Energy-Based Policy
- NeurIPS 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
- NeurIPS 2024VisMin: Visual Minimal-Change Understanding
- NeurIPS 2024Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
- NeurIPS 2024Visual Perception by Large Language Model’s Weights
- NeurIPS 2024Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
- NeurIPS 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
- NeurIPS 2024Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
- NeurIPS 2024VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
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。