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 626 篇，第 7 / 13 页
- CVPR 2024Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
- CVPR 2024Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
- CVPR 2024Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
- CVPR 2024LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation
- CVPR 2024Link-Context Learning for Multimodal LLMs
- CVPR 2024LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge
- CVPR 2024LISA: Reasoning Segmentation via Large Language Model
- CVPR 2024LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning
- CVPR 2024LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction
- CVPR 2024LLMs are Good Action Recognizers
- CVPR 2024LLMs are Good Sign Language Translators
- CVPR 2024Logarithmic Lenses: Exploring Log RGB Data for Image Classification
- CVPR 2024Look-Up Table Compression for Efficient Image Restoration
- CVPR 2024Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation
- CVPR 2024Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs
- CVPR 2024Low-Rank Knowledge Decomposition for Medical Foundation Models
- CVPR 2024Low-Resource Vision Challenges for Foundation Models
- CVPR 2024LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction
- CVPR 2024LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation
- CVPR 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content
- CVPR 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
- CVPR 2024MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
- CVPR 2024MAFA: Managing False Negatives for Vision-Language Pre-training
- CVPR 2024Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
- CVPR 2024Making Vision Transformers Truly Shift-Equivariant
- CVPR 2024Making Visual Sense of Oracle Bones for You and Me
- CVPR 2024ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation
- CVPR 2024MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
- CVPR 2024MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding
- CVPR 2024MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation
- CVPR 2024Mask Grounding for Referring Image Segmentation
- CVPR 2024Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
- CVPR 2024MeaCap: Memory-Augmented Zero-shot Image Captioning
- CVPR 2024MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation
- CVPR 2024MESA: Matching Everything by Segmenting Anything
- CVPR 2024Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
- CVPR 2024MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
- CVPR 2024Minimal Perspective Autocalibration
- CVPR 2024Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities
- CVPR 2024Misalignment-Robust Frequency Distribution Loss for Image Transformation
- CVPR 2024Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
- CVPR 2024Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
- CVPR 2024MLP Can Be A Good Transformer Learner
- CVPR 2024MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning
- CVPR 2024MMA: Multi-Modal Adapter for Vision-Language Models
- CVPR 2024MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
- CVPR 2024MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos
- CVPR 2024MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors
- CVPR 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
- CVPR 2024Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration
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。