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 12 / 225 页
- CVPR 2026HUMORCHAIN Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation
- CVPR 2026Hunting Normality from Query Sample via Residual Learning for Generalist
- CVPR 2026Hybrid Agents for Image Restoration
- CVPR 2026Hybrid Token Compression for Vision-Language Models
- CVPR 2026HybridDriveVLA Vision-Language-Action Model with Visual CoT reasoning and ToT Evaluation
- CVPR 2026HyCal A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental
- CVPR 2026Hyperbolic Busemann Neural Networks
- CVPR 2026Hyperbolic Gramian Volumes for Multimodal Alignment
- CVPR 2026Hyperbolic Relational Prompts for Intersectional Fairness in Medical VLMs
- CVPR 2026Hypergraph-State Collaborative Reasoning for Multi-Object Tracking
- CVPR 2026I-Scene 3D Instance Models are Implicit Generalizable Spatial Learners
- CVPR 2026I2I-Bench A Comprehensive Benchmark Suite for Image-to-Image Editing Models
- CVPR 2026IAG Input-aware Backdoor Attack on VLM-based Visual Grounding
- CVPR 2026ID-Crafter VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
- CVPR 2026IF-Bench Benchmarking and Enhancing MLLMs for Infrared Images with Generative
- CVPR 2026IF-Prune Information-Flow Guided Token Pruning for Efficient Vision-Language Models
- CVPR 2026IGen Scalable Data Generation for Robot Learning from Open-World Images
- CVPR 2026Illuminating Visual Identity in Universal Multimodal Embeddings
- CVPR 2026Illustrators Depth Monocular Layer Index Prediction for Image Decomposition
- CVPR 2026Image Guides Images Consistent Video Amodal Completion with Rectified In-Context
- CVPR 2026Image-to-Point Cloud Feature Back-Projection for Multimodal Training of 3D Semantic
- CVPR 2026IMAIA Interactive Maps AI Assistant for Travel Planning and Geo-Spatial
- CVPR 2026Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via
- CVPR 2026Improving Vision-language Models with Perception-centric Process Reward Models
- CVPR 2026IMU-HOI A Symbiotic Framework for Coherent Human-Object Interaction and Motion
- CVPR 2026InfiniBench Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene
- CVPR 2026Information-Theoretic Decomposition for Multimodal Interaction Learning
- CVPR 2026InsCal Calibrated Multi-Source Fully Test-Time Prompt Tuning for Object Detection
- CVPR 2026INSIGHT Bench Towards Grounded IN-SItu Guidance for Robotic ManipulaTion
- CVPR 2026InstAP Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
- CVPR 2026Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale
- CVPR 2026Interactive Episodic Memory with User Feedback
- CVPR 2026Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
- CVPR 2026Interpretable Debiasing of Vision-Language Models for Social Fairness
- CVPR 2026Interpretable Prompts made Edit-Friendly Token-to-Token Similarity Reduction in dLLMs for
- CVPR 2026Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
- CVPR 2026IntroSVG Learning from Rendering Feedback for Text-to-SVG Generation via an
- CVPR 2026IPR-1 Interactive Physical Reasoner
- CVPR 2026Is your VLM Sky-Ready A Comprehensive Spatial Intelligence Benchmark for
- CVPR 2026IsoCLIP Decomposing CLIP Projectors for Efficient Intra-modal Alignment
- CVPR 2026It Takes Two A Duet of Periodicity and Directionality for
- CVPR 2026IVAAN Instance-level Vision-Language Alignment via Attribute-Guided Text Prompts Generation for
- CVPR 2026Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection
- CVPR 2026JANUS A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution
- CVPR 2026Joint-Aligned Latent Action Towards Scalable VLA Pretraining in the Wild
- CVPR 2026JoPPO Hierarchical Photography Assessment via Contrastive Joint Conditional Probabilistic Reinforcement
- CVPR 2026Kaleidoscopic Scintillation Event Imaging
- CVPR 2026KaLOS finds Consensus A Meta-Algorithm for Evaluating Inter-Annotator Agreement in
- CVPR 2026KAMP Knowledge-Anchored Multimodal Pretraining Framework for Medical Image Representation
- CVPR 2026Keep It Frozen Domain-Routed Conditional Residual Modulation for Multi-Domain Vision
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。