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 10 / 35 页
- CVPR 2024RegionGPT: Towards Region Understanding Vision Language Model
- CVPR 2024RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
- CVPR 2024Regressor-Segmenter Mutual Prompt Learning for Crowd Counting
- CVPR 2024Relightable and Animatable Neural Avatar from Sparse-View Video
- CVPR 2024Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision
- CVPR 2024RepViT: Revisiting Mobile CNN From ViT Perspective
- CVPR 2024Resource-Efficient Transformer Pruning for Finetuning of Large Models
- CVPR 2024Rethinking FID: Towards a Better Evaluation Metric for Image Generation
- CVPR 2024Rethinking Inductive Biases for Surface Normal Estimation
- CVPR 2024Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
- CVPR 2024Retrieval-Augmented Open-Vocabulary Object Detection
- CVPR 2024Revisiting Sampson Approximations for Geometric Estimation Problems
- CVPR 2024Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion
- CVPR 2024Robust Noisy Correspondence Learning with Equivariant Similarity Consistency
- CVPR 2024Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
- CVPR 2024Rotation-Agnostic Image Representation Learning for Digital Pathology
- CVPR 2024S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes
- CVPR 2024S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data
- CVPR 2024SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training
- CVPR 2024SAI3D: Segment Any Instance in 3D Scenes
- CVPR 2024SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
- CVPR 2024Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic
- CVPR 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
- CVPR 2024ScanFormer: Referring Expression Comprehension by Iteratively Scanning
- CVPR 2024SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation
- CVPR 2024SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
- CVPR 2024SeD: Semantic-Aware Discriminator for Image Super-Resolution
- CVPR 2024See Say and Segment: Teaching LMMs to Overcome False Premises
- CVPR 2024SEED-Bench: Benchmarking Multimodal Large Language Models
- CVPR 2024Seeing the Unseen: Visual Common Sense for Semantic Placement
- CVPR 2024Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
- CVPR 2024Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
- CVPR 2024Semantics-aware Motion Retargeting with Vision-Language Models
- CVPR 2024Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation
- CVPR 2024Sequential Modeling Enables Scalable Learning for Large Vision Models
- CVPR 2024Shadow-Enlightened Image Outpainting
- CVPR 2024Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
- CVPR 2024Sheared Backpropagation for Fine-tuning Foundation Models
- CVPR 2024Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding
- CVPR 2024Sieve: Multimodal Dataset Pruning using Image Captioning Models
- CVPR 2024SimDA: Simple Diffusion Adapter for Efficient Video Generation
- CVPR 2024Single-Model and Any-Modality for Video Object Tracking
- CVPR 2024Situational Awareness Matters in 3D Vision Language Reasoning
- CVPR 2024SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
- CVPR 2024SLICE: Stabilized LIME for Consistent Explanations for Image Classification
- CVPR 2024SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers
- CVPR 2024SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
- CVPR 2024SnAG: Scalable and Accurate Video Grounding
- CVPR 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
- CVPR 2024Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction
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。