多模态大模型论文趋势 2023–2026

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。

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 390 篇，第 3 / 8 页

101. ICML 2025Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
102. ICML 2025Enhancing Target-unspecific Tasks through a Features Matrix
103. ICML 2025EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
104. ICML 2025ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
105. ICML 2025Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
106. ICML 2025Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
107. ICML 2025Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
108. ICML 2025Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs
109. ICML 2025Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
110. ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
111. ICML 2025FairPFN: A Tabular Foundation Model for Causal Fairness
112. ICML 2025Fast Exact Unlearning for In-Context Learning Data for LLMs
113. ICML 2025FeatSharp: Your Vision Model Features, Sharper
114. ICML 2025Feature out! Let Raw Image as Your Condition for Blind Face Restoration
115. ICML 2025Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation
116. ICML 2025FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning
117. ICML 2025FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
118. ICML 2025FG-CLIP: Fine-Grained Visual and Textual Alignment
119. ICML 2025Fine-Grained Captioning of Long Videos through Scene Graph Consolidation
120. ICML 2025FLAM: Frame-Wise Language-Audio Modeling
121. ICML 2025FlipAttack: Jailbreak LLMs via Flipping
122. ICML 2025Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency
123. ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
124. ICML 2025FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
125. ICML 2025Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
126. ICML 2025Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
127. ICML 2025FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
128. ICML 2025Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
129. ICML 2025From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
130. ICML 2025From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
131. ICML 2025From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
132. ICML 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
133. ICML 2025Function-to-Style Guidance of LLMs for Code Translation
134. ICML 2025Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
135. ICML 2025Gandalf the Red: Adaptive Security for LLMs
136. ICML 2025GaussMark: A Practical Approach for Structural Watermarking of Language Models
137. ICML 2025Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
138. ICML 2025Generative Data Mining with Longtail-Guided Diffusion
139. ICML 2025GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
140. ICML 2025GMAIL: Generative Modality Alignment for generated Image Learning
141. ICML 2025GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
142. ICML 2025Gradient Inversion of Multimodal Models
143. ICML 2025Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
144. ICML 2025Graph4MM: Weaving Multimodal Learning with Structural Information
145. ICML 2025GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
146. ICML 2025GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
147. ICML 2025GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
148. ICML 2025GSM-$\infty$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?
149. ICML 2025HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
150. ICML 2025Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

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。