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 27 / 225 页
- CVPR 2026Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
- CVPR 2026Vision-Language Model Guided Source-Free Domain Adaptation via Optimal Transport
- CVPR 2026Vision-Speech Models Teaching Speech Models to Converse about Images
- CVPR 2026VisionDirector Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis
- CVPR 2026VisionLeaf Entropy-Guided Leaf-First Reasoning for Efficient and Accurate Think-with-Image
- CVPR 2026VisMem Latent Vision Memory Unlocks Potential of Vision-Language Models
- CVPR 2026VisPlay Self-Evolving Vision-Language Models
- CVPR 2026VisRes Bench On Evaluating the Visual Reasoning Capabilities of VLMs
- CVPR 2026ViStoryBench Comprehensive Benchmark Suite for Story Visualization
- CVPR 2026Visual Document Understanding and Reasoning A Multi-Agent Collaboration Framework with
- CVPR 2026Visual Personalization Turing Test
- CVPR 2026VisualAD Language-Free Zero-Shot Anomaly Detection via Vision Transformer
- CVPR 2026ViT3 Unlocking Test-Time Training in Vision
- CVPR 2026VITAL Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment
- CVPR 2026ViTPrompt Training-Free Prompt Refinement with Visual Tokens for Open-Vocabulary Detection
- CVPR 2026VIVA VLM-Guided Instruction-Based Video Editing with Reward Optimization
- CVPR 2026VKG-QA Visual Knowledge Graph-based Question Answer for Large Multimodal Models
- CVPR 2026VL-Eraser Vacuum Distillation for Machine Unlearning in Vision-Language Models
- CVPR 2026VL-RouterBench A Benchmark for Vision-Language Model Routing
- CVPR 2026VLA Models Are More Generalizable Than You Think Revisiting Physical
- CVPR 2026VLIC Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
- CVPR 2026VLM-3R Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
- CVPR 2026VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery
- CVPR 2026VLM-Loc Localization in Point Cloud Maps via Vision-Language Models
- CVPR 2026VLM-Pruner Buffering for Spatial Sparsity in an Efficient VLM Centrifugal
- CVPR 2026VLM-PTQ Efficient Post-Training Quantization for Large Vision-Language Models
- CVPR 2026VLM4RSDet Collaborative Optimization with Vision-Language Model for Enhancing Remote Sensing
- CVPR 2026VMD-FACT A New Video Dataset and MLLM-based method for Detecting
- CVPR 2026Vocabulary Scaling Law Tuning Open-vocabulary Predictors for Their Openness
- CVPR 2026VOLD Reasoning Transfer from LLMs to Vision-Language Models via On-Policy
- CVPR 2026VoxTell Free-Text Promptable Universal 3D Medical Image Segmentation
- CVPR 2026VQRAE Representation Quantization Autoencoders for Multimodal Understanding Generation and Reconstruction
- CVPR 2026VRCLIP Multimodal Canonical Correlation Alignment for CLIP-Driven Vision-Radio Person Re-Identification
- CVPR 2026VRR-QA Visual Relational Reasoning in Videos Beyond Explicit Cues
- CVPR 2026VS-Bench Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
- CVPR 2026VSRELL A Simple Baseline for Video Super-Resolution and Enhancement in
- CVPR 2026VULCAN Tool-Augmented Multi Agents for Iterative 3D Object Arrangement
- CVPR 2026WAM-Flow Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for
- CVPR 2026Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video
- CVPR 2026WEAVE Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
- CVPR 2026WeaveTime Streaming from Earlier Frames into Emergent Memory in VideoLLMs
- CVPR 2026WebGym Scaling Training Environments for Long-Horizon Visual Web Agents with
- CVPR 2026WeMMU Enhanced Bridging of Vision-Language Models and Diffusion Models via
- CVPR 2026What Do Visual Tokens Really Encode Uncovering Sparsity and Redundancy
- CVPR 2026What Your Features Reveal Data-Efficient Black-Box Feature Inversion Attack for
- CVPR 2026When AVSR Meets Video Conferencing Dataset Degradation and the Hidden
- CVPR 2026When CLIP Sees More It Fights Back Harder Multi-View Guided
- CVPR 2026When Robots Obey the Patch Universal Transferable Patch Attacks on
- CVPR 2026When to Think and When to Look Uncertainty-Guided Lookback
- CVPR 2026When Transformers Meet Mamba A Hybrid Transformer-Mamba Network for Video
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。