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 123 / 225 页
- ICLR 2025Can We Talk Models Into Seeing the World Differently?
- ICLR 2025CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
- ICLR 2025Captured by Captions: On Memorization and its Mitigation in CLIP Models
- ICLR 2025CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling
- ICLR 2025Catastrophic Failure of LLM Unlearning via Quantization
- ICLR 2025Causal Graphical Models for Vision-Language Compositional Understanding
- ICLR 2025Causal Identification for Complex Functional Longitudinal Studies
- ICLR 2025Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
- ICLR 2025Causal Representation Learning from Multimodal Biomedical Observations
- ICLR 2025Causally Motivated Sycophancy Mitigation for Large Language Models
- ICLR 2025CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
- ICLR 2025Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images
- ICLR 2025CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness
- ICLR 2025Certifying Counterfactual Bias in LLMs
- ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
- ICLR 2025Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
- ICLR 2025Chain-of-region: Visual Language Models Need Details for Diagram Analysis
- ICLR 2025ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding
- ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
- ICLR 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
- ICLR 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
- ICLR 2025CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening
- ICLR 2025Class Distribution-induced Attention Map for Open-vocabulary Semantic Segmentations
- ICLR 2025ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension
- ICLR 2025CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
- ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
- ICLR 2025CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
- ICLR 2025COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
- ICLR 2025CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning
- ICLR 2025CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
- ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
- ICLR 2025Combining Induction and Transduction for Abstract Reasoning
- ICLR 2025Composable Interventions for Language Models
- ICLR 2025Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
- ICLR 2025Compositional Entailment Learning for Hyperbolic Vision-Language Models
- ICLR 2025Compute-Constrained Data Selection
- ICLR 2025Concept Bottleneck Language Models For Protein Design
- ICLR 2025Concept Bottleneck Large Language Models
- ICLR 2025CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
- ICLR 2025Conformal Language Model Reasoning with Coherent Factuality
- ICLR 2025Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets
- ICLR 2025Context Steering: Controllable Personalization at Inference Time
- ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
- ICLR 2025Context-aware Dynamic Pruning for Speech Foundation Models
- ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
- ICLR 2025Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
- ICLR 2025Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs
- ICLR 2025Controllable Generation via Locally Constrained Resampling
- ICLR 2025Controlled LLM Decoding via Discrete Auto-regressive Biasing
- ICLR 2025Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
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。