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 321 篇，第 2 / 7 页
- ICLR 2024Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
- ICLR 2024Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
- ICLR 2024Circuit Component Reuse Across Tasks in Transformer Language Models
- ICLR 2024CLEX: Continuous Length Extrapolation for Large Language Models
- ICLR 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
- ICLR 2024CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
- ICLR 2024CoBIT: A Contrastive Bi-directional Image-Text Generation Model
- ICLR 2024Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
- ICLR 2024Compressing LLMs: The Truth is Rarely Pure and Never Simple
- ICLR 2024Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
- ICLR 2024Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
- ICLR 2024Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
- ICLR 2024Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- ICLR 2024Consistency-guided Prompt Learning for Vision-Language Models
- ICLR 2024Constrained Decoding for Cross-lingual Label Projection
- ICLR 2024ContextRef: Evaluating Referenceless Metrics for Image Description Generation
- ICLR 2024Controlling Vision-Language Models for Multi-Task Image Restoration
- ICLR 2024Coordinate-Aware Modulation for Neural Fields
- ICLR 2024COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
- ICLR 2024CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
- ICLR 2024CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
- ICLR 2024DAM: Towards a Foundation Model for Forecasting
- ICLR 2024Data-independent Module-aware Pruning for Hierarchical Vision Transformers
- ICLR 2024Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders
- ICLR 2024Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
- ICLR 2024Democratizing Fine-grained Visual Recognition with Large Language Models
- ICLR 2024Demystifying CLIP Data
- ICLR 2024DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
- ICLR 2024DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
- ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
- ICLR 2024Does CLIP’s generalization performance mainly stem from high train-test similarity?
- ICLR 2024Don't Judge by the Look: Towards Motion Coherent Video Representation
- ICLR 2024Doubly Robust Proximal Causal Learning for Continuous Treatments
- ICLR 2024DreamLLM: Synergistic Multimodal Comprehension and Creation
- ICLR 2024Dual Associated Encoder for Face Restoration
- ICLR 2024Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
- ICLR 2024DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
- ICLR 2024ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
- ICLR 2024Efficient Modulation for Vision Networks
- ICLR 2024Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
- ICLR 2024Emu: Generative Pretraining in Multimodality
- ICLR 2024Enhanced Face Recognition using Intra-class Incoherence Constraint
- ICLR 2024Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
- ICLR 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
- ICLR 2024Ensemble Distillation for Unsupervised Constituency Parsing
- ICLR 2024EQA-MX: Embodied Question Answering using Multimodal Expression
- ICLR 2024EventRPG: Event Data Augmentation with Relevance Propagation Guidance
- ICLR 2024Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
- ICLR 2024Exploring Target Representations for Masked Autoencoders
- ICLR 2024FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
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。