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 1,074 篇，第 6 / 22 页
- NeurIPS 2025egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks
- NeurIPS 2025EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
- NeurIPS 2025EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
- NeurIPS 2025Elastic ViTs from Pretrained Models without Retraining
- NeurIPS 2025ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
- NeurIPS 2025Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
- NeurIPS 2025EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition
- NeurIPS 2025Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
- NeurIPS 2025End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWs
- NeurIPS 2025End-to-End Vision Tokenizer Tuning
- NeurIPS 2025Enhanced Expert Merging for Mixture-of-Experts in Graph Foundation Models
- NeurIPS 2025Enhancing CLIP Robustness via Cross-Modality Alignment
- NeurIPS 2025Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
- NeurIPS 2025Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator
- NeurIPS 2025Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark
- NeurIPS 2025Enhancing Privacy in Multimodal Federated Learning with Information Theory
- NeurIPS 2025Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
- NeurIPS 2025Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- NeurIPS 2025Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
- NeurIPS 2025EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
- NeurIPS 2025EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning
- NeurIPS 2025EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models
- NeurIPS 2025Epistemic Uncertainty for Generated Image Detection
- NeurIPS 2025Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
- NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
- NeurIPS 2025Escaping Collapse: The Strength of Weak Data for Large Language Model Training
- NeurIPS 2025Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
- NeurIPS 2025Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
- NeurIPS 2025EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution
- NeurIPS 2025ExAct: A Video-Language Benchmark for Expert Action Analysis
- NeurIPS 2025ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
- NeurIPS 2025Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
- NeurIPS 2025Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior
- NeurIPS 2025Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
- NeurIPS 2025Exploring and Leveraging Class Vectors for Classifier Editing
- NeurIPS 2025Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining
- NeurIPS 2025Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
- NeurIPS 2025Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
- NeurIPS 2025EyeBench: Predictive Modeling from Eye Movements in Reading
- NeurIPS 2025Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
- NeurIPS 2025FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training
- NeurIPS 2025Fairshare Data Pricing via Data Valuation for Large Language Models
- NeurIPS 2025Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
- NeurIPS 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
- NeurIPS 2025FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
- NeurIPS 2025FastJAM: a Fast Joint Alignment Model for Images
- NeurIPS 2025FastVID: Dynamic Density Pruning for Fast Video Large Language Models
- NeurIPS 2025FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
- NeurIPS 2025Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities
- NeurIPS 2025FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
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。