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 11 / 104 页
- CVPR 2026GuardTrace-VL Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision
- CVPR 2026GUIDE A Benchmark for Understanding and Assisting Users in Open-Ended
- CVPR 2026Gyro-based Deep Video Deblurring
- CVPR 2026H2-Surv Hierarchical Hyperbolic Multimodal Representation Learning for Survival Prediction
- CVPR 2026HalluGen Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration
- CVPR 2026HAMMER Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance
- CVPR 2026HandVQA Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in
- CVPR 2026HanDyVQA A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
- CVPR 2026Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face
- CVPR 2026Harnessing the Power of Foundation Models for Accurate Material Classification
- CVPR 2026HATS Hardness-Aware Trajectory Synthesis for GUI Agents
- CVPR 2026HAVE-Bench Hierarchical Audio-Visual Evaluation from Perception to Interaction
- CVPR 2026HAWK Head Importance-Aware Visual Token Pruning in Multimodal Models
- CVPR 2026HBridge H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding
- CVPR 2026HCL-FF Hierarchical and Contrastive Learning for Forward-Forward Algorithm
- CVPR 2026HDR-VLM HDR-Domain Adaptation of VLMs and Preference-Aligned Quality Assessment for
- CVPR 2026Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
- CVPR 2026Hear you are Teaching LLMs Spatial Reasoning with Vision and
- CVPR 2026HERBench A Benchmark for Multi-Evidence Integration in Video Question Answering
- CVPR 2026HeSS Head Sensitivity Score for Sparsity Redistribution in VGGT
- CVPR 2026Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection
- CVPR 2026HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly
- CVPR 2026Hg-I2P Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs
- CVPR 2026Hi-Lo Prune Look at What Youll Lose before Pruning with
- CVPR 2026Hierarchical Concept Embedding Pursuit for Interpretable Image Classification
- CVPR 2026Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic
- CVPR 2026Hierarchically Robust Zero-shot Vision-language Models
- CVPR 2026HierUQ Hierarchical Uncertainty Quantification with Adaptive Granularity Reconciliation for Degraded
- CVPR 2026HiF-VLA Hindsight Insight and Foresight through Motion Representation for Vision-Language-Action
- CVPR 2026HiFICL High-Fidelity In-Context Learning for Multimodal Tasks
- CVPR 2026High-Fidelity Mobile Avatars with Pruned Local Blendshapes
- CVPR 2026Hilbert Curve-Based Attention Enabling Topology-Preserving Image Tensor Representation for Semantic
- CVPR 2026Hilbert-Geo Solving Solid Geometric Problems by Neural-Symbolic Reasoning
- CVPR 2026Hint2Gen Bridging Understanding and Generation via Code-structured Hints
- CVPR 2026HiSpatial Taming Hierarchical 3D Spatial Understanding in Vision-Language Models
- CVPR 2026Hist2Style Histogram-Guided Stylization with Bilateral Grids
- CVPR 2026HOG-Layout Hierarchical 3D Scene Generation Optimization and Editing via Vision-Language
- CVPR 2026Hoi - A Multimodal Dataset for Force-Grounded Cross-View Articulated Manipulation
- CVPR 2026Homaloidal parametrization for detecting critical two-view configurations
- CVPR 2026HoneyBee Data Recipes for Vision-Language Reasoners
- CVPR 2026HOPS Hierarchical Open-vocabulary Part Segmentation with Attention-Aware Filtering and Affinity-Guided
- CVPR 2026How Much 3D Do Video Foundation Models Encode
- CVPR 2026How to Take a Memorable Picture Empowering Users with Actionable
- CVPR 2026HP-Edit A Human-Preference Post-Training Framework for Image Editing
- CVPR 2026HTTM Head-wise Temporal Token Merging for Faster VGGT
- CVPR 2026Hugging Visual Prompt and Segmentation Tokens Consistency Learning for Fine-Grained
- CVPR 2026HulluEdit Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large
- CVPR 2026Human-like Abstract Visual Reasoning via Understanding and Solving Reasoning Loop
- CVPR 2026HumanVBench Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized
- CVPR 2026HUMAPS-4D A Multimodal Dataset for HUman Motion Analysis with Physiological
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。