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 795 篇，第 14 / 16 页
- CVPR 2025Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis
- CVPR 2025Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models
- CVPR 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models
- CVPR 2025Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
- CVPR 2025SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception
- CVPR 2025Spk2SRImgNet: Super-Resolve Dynamic Scene from Spike Stream via Motion Aligned Collaborative Filtering
- CVPR 2025Split Adaptation for Pre-trained Vision Transformers
- CVPR 2025Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence
- CVPR 2025Star with Bilinear Mapping
- CVPR 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction
- CVPR 2025Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
- CVPR 2025Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
- CVPR 2025Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
- CVPR 2025STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
- CVPR 2025STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
- CVPR 2025STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection
- CVPR 2025Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target.
- CVPR 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
- CVPR 2025STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
- CVPR 2025STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding
- CVPR 2025Structure-Aware Correspondence Learning for Relative Pose Estimation
- CVPR 2025Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection
- CVPR 2025Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning
- CVPR 2025Sufficient Invariant Learning for Distribution Shift
- CVPR 2025SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation
- CVPR 2025SVFR: A Unified Framework for Generalized Video Face Restoration
- CVPR 2025SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
- CVPR 2025Symbolic Representation for Any-to-Any Generative Tasks
- CVPR 2025SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
- CVPR 2025SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
- CVPR 2025Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
- CVPR 2025SynTab-LLaVA: Enhancing Multimodal Table Understanding with Decoupled Synthesis
- CVPR 2025Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
- CVPR 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
- CVPR 2025T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
- CVPR 2025T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
- CVPR 2025Taming Teacher Forcing for Masked Autoregressive Video Generation
- CVPR 2025TANGO: Training-free Embodied AI Agents for Open-world Tasks
- CVPR 2025TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
- CVPR 2025Targeted Forgetting of Image Subgroups in CLIP Models
- CVPR 2025Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics
- CVPR 2025Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
- CVPR 2025Task-Aware Clustering for Prompting Vision-Language Models
- CVPR 2025TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation
- CVPR 2025Taxonomy-Aware Evaluation of Vision-Language Models
- CVPR 2025TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering
- CVPR 2025Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation
- CVPR 2025The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
- CVPR 2025The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation
- CVPR 2025The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers
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。