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 80 / 104 页
- NeurIPS 2026Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
- NeurIPS 2026Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
- NeurIPS 2026BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
- NeurIPS 2026BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
- NeurIPS 2026Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
- NeurIPS 2026Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood
- NeurIPS 2026Behavior Pack Optimization for Video MLLM Post-Training
- NeurIPS 2026Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
- NeurIPS 2026Benchmark for Assessing Olfactory Perception of Large Language Models
- NeurIPS 2026Benchmark Recovery Does Not Certify a Frozen Tool-Trigger Contract After Quantization
- NeurIPS 2026Benchmark Shadows: How Data Regimes Shape Parameter Footprints and Generalization
- NeurIPS 2026Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
- NeurIPS 2026Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
- NeurIPS 2026Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
- NeurIPS 2026Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
- NeurIPS 2026Benchmarking Optimizers for Large Language Model Pretraining
- NeurIPS 2026Benchmarking Risk Attitudes of LLMs
- NeurIPS 2026BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
- NeurIPS 2026Better Language Models Require Better Domain-Specific Inductive Biases
- NeurIPS 2026Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept
- NeurIPS 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
- NeurIPS 2026Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
- NeurIPS 2026Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models
- NeurIPS 2026Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting
- NeurIPS 2026Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping
- NeurIPS 2026Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models
- NeurIPS 2026Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs
- NeurIPS 2026Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery
- NeurIPS 2026Beyond Flat Frames: Hierarchical Graph Reasoning for Long Video Understanding
- NeurIPS 2026Beyond Flat Gossip: Tiered Gossip Learning for Scalable Collaborative AI
- NeurIPS 2026Beyond Global Alignment: Structured Compositional Reasoning for Vision-Language Models
- NeurIPS 2026Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness
- NeurIPS 2026Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
- NeurIPS 2026Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms
- NeurIPS 2026Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
- NeurIPS 2026Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment
- NeurIPS 2026Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
- NeurIPS 2026Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
- NeurIPS 2026Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment
- NeurIPS 2026Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
- NeurIPS 2026Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
- NeurIPS 2026Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology
- NeurIPS 2026Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
- NeurIPS 2026Beyond Stabilization: Dual-EMA Teachers for Global–Local Semantic Learning in Semi-Supervised Medical Image Segmentation
- NeurIPS 2026Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image Enhancement
- NeurIPS 2026Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
- NeurIPS 2026BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors
- NeurIPS 2026Bidirectional Sparse Attention for Faster Video Diffusion Training
- NeurIPS 2026BigCell: Generating Gigapixel Whole-Slide Images
- NeurIPS 2026Biomedical Acquisition-induced Style Shifts as Mixture Shifts: Style-aware Mixture-of-Experts Multimodal Prompt Learning
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。