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 146 篇，第 3 / 3 页

101. ICML 2023Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist
102. ICML 2023Provable Dynamic Fusion for Low-Quality Multimodal Data
103. ICML 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
104. ICML 2023Random Shuffle Transformer for Image Restoration
105. ICML 2023Regret-Minimizing Double Oracle for Extensive-Form Games
106. ICML 2023Reparameterized Policy Learning for Multimodal Trajectory Optimization
107. ICML 2023Representer Point Selection for Explaining Regularized High-dimensional Models
108. ICML 2023Retrieval-Augmented Multimodal Language Modeling
109. ICML 2023Revisiting Simple Regret: Fast Rates for Returning a Good Arm
110. ICML 2023RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation
111. ICML 2023Robustness in Multimodal Learning under Train-Test Modality Mismatch
112. ICML 2023Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
113. ICML 2023Scaling Laws for Generative Mixed-Modal Language Models
114. ICML 2023Scaling Vision Transformers to 22 Billion Parameters
115. ICML 2023SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
116. ICML 2023Shapley Based Residual Decomposition for Instance Analysis
117. ICML 2023SinFusion: Training Diffusion Models on a Single Image or Video
118. ICML 2023Sketch-Flip-Merge: Mergeable Sketches for Private Distinct Counting
119. ICML 2023Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
120. ICML 2023Smart Initial Basis Selection for Linear Programs
121. ICML 2023SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
122. ICML 2023SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference
123. ICML 2023SpotEM: Efficient Video Search for Episodic Memory
124. ICML 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapse
125. ICML 2023Statistical Learning under Heterogenous Distribution Shift
126. ICML 2023Structure-informed Language Models Are Protein Designers
127. ICML 2023Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction
128. ICML 2023SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
129. ICML 2023Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization
130. ICML 2023Temporally Consistent Transformers for Video Generation
131. ICML 2023Tight Data Access Bounds for Private Top-$k$ Selection
132. ICML 2023Tighter Analysis for ProxSkip
133. ICML 2023Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
134. ICML 2023Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks
135. ICML 2023Towards Omni-generalizable Neural Methods for Vehicle Routing Problems
136. ICML 2023Tractable Control for Autoregressive Language Generation
137. ICML 2023TRAK: Attributing Model Behavior at Scale
138. ICML 2023Traversing Between Modes in Function Space for Fast Ensembling
139. ICML 2023Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
140. ICML 2023Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
141. ICML 2023Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions
142. ICML 2023UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
143. ICML 2023VIMA: Robot Manipulation with Multimodal Prompts
144. ICML 2023Whose Opinions Do Language Models Reflect?
145. ICML 2023Why do Nearest Neighbor Language Models Work?
146. ICML 2023Why Is Public Pretraining Necessary for Private Model Training?

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。