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 321 篇，第 3 / 7 页

101. ICLR 2024Faithful Vision-Language Interpretation via Concept Bottleneck Models
102. ICLR 2024Fast-ELECTRA for Efficient Pre-training
103. ICLR 2024FasterViT: Fast Vision Transformers with Hierarchical Attention
104. ICLR 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolution
105. ICLR 2024Federated Text-driven Prompt Generation for Vision-Language Models
106. ICLR 2024FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
107. ICLR 2024Ferret: Refer and Ground Anything Anywhere at Any Granularity
108. ICLR 2024Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
109. ICLR 2024Finite Scalar Quantization: VQ-VAE Made Simple
110. ICLR 2024FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
111. ICLR 2024Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
112. ICLR 2024Frequency-Aware Transformer for Learned Image Compression
113. ICLR 2024FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
114. ICLR 2024Frozen Transformers in Language Models Are Effective Visual Encoder Layers
115. ICLR 2024Fully Hyperbolic Convolutional Neural Networks for Computer Vision
116. ICLR 2024Functional Interpolation for Relative Positions improves Long Context Transformers
117. ICLR 2024GAIA: a benchmark for General AI Assistants
118. ICLR 2024GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
119. ICLR 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
120. ICLR 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
121. ICLR 2024Grounding Multimodal Large Language Models to the World
122. ICLR 2024Guiding Instruction-based Image Editing via Multimodal Large Language Models
123. ICLR 2024Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
124. ICLR 2024Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
125. ICLR 2024How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
126. ICLR 2024Hypothesis Search: Inductive Reasoning with Language Models
127. ICLR 2024Identifying Representations for Intervention Extrapolation
128. ICLR 2024Image Background Serves as Good Proxy for Out-of-distribution Data
129. ICLR 2024Image Clustering Conditioned on Text Criteria
130. ICLR 2024Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
131. ICLR 2024Implicit Neural Representations and the Algebra of Complex Wavelets
132. ICLR 2024Improved algorithm and bounds for successive projection
133. ICLR 2024Improved Probabilistic Image-Text Representations
134. ICLR 2024In-context Autoencoder for Context Compression in a Large Language Model
135. ICLR 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
136. ICLR 2024Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction
137. ICLR 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
138. ICLR 2024InstructDET: Diversifying Referring Object Detection with Generalized Instructions
139. ICLR 2024InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
140. ICLR 2024INViTE: INterpret and Control Vision-Language Models with Text Explanations
141. ICLR 2024Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
142. ICLR 2024It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
143. ICLR 2024Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
144. ICLR 2024Jointly Training Large Autoregressive Multimodal Models
145. ICLR 2024Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
146. ICLR 2024Knowledge Fusion of Large Language Models
147. ICLR 2024Kosmos-G: Generating Images in Context with Multimodal Large Language Models
148. ICLR 2024Label-free Node Classification on Graphs with Large Language Models (LLMs)
149. ICLR 2024Language-Informed Visual Concept Learning
150. ICLR 2024LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

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。