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 2,676 篇，第 11 / 54 页
- ICLR 2026Histopathology-Genomics Multi-modal Structural Representation Learning for Data-Efficient Precision Oncology
- ICLR 2026HiTeA: Hierarchical Temporal Alignment for Training-Free Long-Video Temporal Grounding
- ICLR 2026HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming
- ICLR 2026Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning
- ICLR 2026Hourglass Persistence for Graphs, Simplices, and Cells
- ICLR 2026Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence Modeling
- ICLR 2026How Base Frequency Shapes RoPE: An Analytical Study of Frequency-Band Formation
- ICLR 2026How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
- ICLR 2026How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining
- ICLR 2026How Reliable is Language Model Micro-Benchmarking?
- ICLR 2026How Text Quality Interventions Reshape Neural Scaling Laws for LLMs: Empirical Study
- ICLR 2026How to train data-efficient LLMs
- ICLR 2026How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
- ICLR 2026HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
- ICLR 2026Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
- ICLR 2026Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering
- ICLR 2026Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models
- ICLR 2026Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy
- ICLR 2026Hybrid Training for Vision-Language-Action Models
- ICLR 2026HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
- ICLR 2026Ice Cream Doesn’t Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference
- ICLR 2026IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs
- ICLR 2026ICPO: Provable and Practical In-Context Policy Optimization for Test-Time Scaling
- ICLR 2026ICYM2I: The illusion of multimodal informativeness under missingness
- ICLR 2026Identifying and Evaluating Inactive Heads in Pretrained LLMs
- ICLR 2026Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models
- ICLR 2026IF-VidCap: Can Video Caption Models Follow Instructions?
- ICLR 2026iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
- ICLR 2026Image is All You Need: Towards Efficient and Effective Large Language Model-Based Recommender Systems
- ICLR 2026Image Quality Assessment for Embodied AI
- ICLR 2026ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
- ICLR 2026ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
- ICLR 2026ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
- ICLR 2026Imagine How To Change: Explicit Procedure Modeling for Change Captioning
- ICLR 2026Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language Models
- ICLR 2026Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization
- ICLR 2026Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
- ICLR 2026In Good GRACES: Principled Teacher Selection for Knowledge Distillation
- ICLR 2026In-Context Algorithm Emulation in Fixed-Weight Transformers
- ICLR 2026In-Context Watermarks for Large Language Models
- ICLR 2026In-Place Test-Time Training
- ICLR 2026Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
- ICLR 2026InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion
- ICLR 2026IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs
- ICLR 2026Inducing Dyslexia in Vision Language Models
- ICLR 2026Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
- ICLR 2026Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
- ICLR 2026Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value Imputation
- ICLR 2026Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuning
- ICLR 2026InfoDet: A Dataset for Infographic Element Detection
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。