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 133 / 225 页
- ICLR 2025SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
- ICLR 2025Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
- ICLR 2025SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
- ICLR 2025SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
- ICLR 2025SBSC: Step-by-Step Coding for Improving Mathematical Olympiad Performance
- ICLR 2025Scaling Laws for Downstream Task Performance in Machine Translation
- ICLR 2025Scaling Laws for Precision
- ICLR 2025Scaling Long Context Training Data by Long-Distance Referrals
- ICLR 2025Scaling Optimal LR Across Token Horizons
- ICLR 2025Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study
- ICLR 2025Scaling Wearable Foundation Models
- ICLR 2025SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
- ICLR 2025ScImage: How good are multimodal large language models at scientific text-to-image generation?
- ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
- ICLR 2025See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
- ICLR 2025See What You Are Told: Visual Attention Sink in Large Multimodal Models
- ICLR 2025SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
- ICLR 2025SegLLM: Multi-round Reasoning Segmentation with Large Language Models
- ICLR 2025Segment Any 3D Object with Language
- ICLR 2025Selective Attention Improves Transformer
- ICLR 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
- ICLR 2025Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
- ICLR 2025Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
- ICLR 2025Self-Updatable Large Language Models by Integrating Context into Model Parameters
- ICLR 2025Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
- ICLR 2025Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning
- ICLR 2025Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
- ICLR 2025Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency
- ICLR 2025Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
- ICLR 2025Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity
- ICLR 2025Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
- ICLR 2025Should VLMs be Pre-trained with Image Data?
- ICLR 2025Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
- ICLR 2025SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments
- ICLR 2025Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches
- ICLR 2025SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal Coordination
- ICLR 2025SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
- ICLR 2025Small Models are LLM Knowledge Triggers for Medical Tabular Prediction
- ICLR 2025Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
- ICLR 2025Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises
- ICLR 2025SMT: Fine-Tuning Large Language Models with Sparse Matrices
- ICLR 2025Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
- ICLR 2025SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
- ICLR 2025SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
- ICLR 2025Sparse autoencoders reveal selective remapping of visual concepts during adaptation
- ICLR 2025Specialized Foundation Models Struggle to Beat Supervised Baselines
- ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
- ICLR 2025SpinQuant: LLM Quantization with Learned Rotations
- ICLR 2025SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
- ICLR 2025STAR: Synthesis of Tailored Architectures
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。