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 5,190 篇，第 7 / 104 页
- CVPR 2026Distributed Image Compression with Multimodal Side Information at Extremely Low
- CVPR 2026Distribution-Aligned Multimodal Fusion for Robust Object Detection
- CVPR 2026Divide then Ground Adapting Frame Selection to Query Types for
- CVPR 2026Do Vision-Language Models Leak What They Learn Adaptive Token-Weighted Model
- CVPR 2026Do Vision-Language Models Measure Up Benchmarking Visual Measurement Reading with
- CVPR 2026Do VLMs Perceive or Recall Probing Visual Perception vs. Memory
- CVPR 2026Do You See What I Am Pointing At Gesture-Based Egocentric
- CVPR 2026DocPrune Efficient Document Question Answering via Background Question and Comprehension-aware
- CVPR 2026Does YOLO Really Need to See Every Training Image in
- CVPR 2026Downscaling Intelligence Exploring Perception and Reasoning Bottlenecks in Small Multimodal
- CVPR 2026DPL Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers
- CVPR 2026Dr. Seg Revisiting GRPO Training for Visual Large Language Models
- CVPR 2026DreamOmni2 Multimodal Instruction-based Generation and Editing
- CVPR 2026DreamStyle A Unified Framework for Video Stylization
- CVPR 2026Drive My Way Preference Alignment of Vision-Language-Action Model for Personalized
- CVPR 2026DriveCombo Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
- CVPR 2026DriveMoE Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
- CVPR 2026DrivePI Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding Perception
- CVPR 2026DrivePTS A Progressive Learning Framework with Textual and Structural Enhancement
- CVPR 2026DRM Diffusion-based Reward Model With Step-wise Guidance
- CVPR 2026DSCA Dynamic Subspace Concept Alignment for Lifelong VLM Editing
- CVPR 2026DSO Direct Steering Optimization for Bias Mitigation
- CVPR 2026Dual-Level Hypergraph Generation for Addressing Feature Scarcity in Whole-Slide Image
- CVPR 2026DualMirage Hunting Stealthy Multimodal LLM Agents via CAPTCHAs with Contour
- CVPR 2026DUET-VLM Dual stage Unified Efficient Token reduction for VLM Training
- CVPR 2026DuetSVG Unified Multimodal SVG Generation with Internal Visual Guidance
- CVPR 2026DuoGen Towards Autonomous Interleaved Multimodal Generation
- CVPR 2026DVAR Dynamic Visual Autoregressive Modeling for Image Super-Resolution
- CVPR 2026DyFCLT Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object
- CVPR 2026Dynamic Exposure Burst Image Restoration
- CVPR 2026Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision
- CVPR 2026Dynamic Token Reweighting for Robust Vision-Language Models
- CVPR 2026DynamicGTR Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities
- CVPR 2026Dynamics Language-Based Representation for Inferring Rigid-Body Dynamics From Videos
- CVPR 2026Dynamics-Aware Preference Optimization for Vision-Language Models
- CVPR 2026DynamicsBoost Dynamic Plausible Video Generation via Annotation-Free Continuation Preference Optimization
- CVPR 2026E3AD An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
- CVPR 2026EagleNet Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval
- CVPR 2026EagleVision A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
- CVPR 2026EarlyTom Early Token Compression Completes Fast Video Understanding
- CVPR 2026Easy2Hard From Partially to Fully Unmatched Modalities as Negative Samples
- CVPR 2026Echoes of Ownership Adversarial-Guided Dual Injection for Copyright Protection in
- CVPR 2026EchoPOSE 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D
- CVPR 2026EcoAlign An Economically Rational Framework for Efficient LVLM Alignment
- CVPR 2026Edge-RecViT Efficient Vision Transformer via Semantic-Refined Dynamic Recursion
- CVPR 2026EditCtrl Disentangled Local and Global Control for Real-Time Generative Video
- CVPR 2026EduDiag A Benchmark for Educational Diagnostic Reasoning with Error Tracing
- CVPR 2026EE-RL Vision Language Guided Reinforcement Learning with Explorer and Expert
- CVPR 2026EEGiT Teaching Vision Transformers to Understand the EEG signal
- CVPR 2026EffectErase Joint Video Object Removal and Insertion for High-Quality Effect
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。