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 3,075 篇，第 3 / 62 页

101. CVPR 2025Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs
102. CVPR 2025Building Vision Models upon Heat Conduction
103. CVPR 2025CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
104. CVPR 2025Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
105. CVPR 2025Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding
106. CVPR 2025CARL: A Framework for Equivariant Image Registration
107. CVPR 2025CASP: Compression of Large Multimodal Models Based on Attention Sparsity
108. CVPR 2025CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
109. CVPR 2025CCIN: Compositional Conflict Identification and Neutralization for Composed Image Retrieval
110. CVPR 2025Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
111. CVPR 2025Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
112. CVPR 2025Charm: The Missing Piece in ViT Fine-Tuning for Image Aesthetic Assessment
113. CVPR 2025ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
114. CVPR 2025CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
115. CVPR 2025CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
116. CVPR 2025Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable
117. CVPR 2025Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
118. CVPR 2025ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models
119. CVPR 2025CLIP-driven Coarse-to-fine Semantic Guidance for Fine-grained Open-set Semi-supervised Learning
120. CVPR 2025Closest Neighbors are Harmful for Lightweight Masked Auto-encoders
121. CVPR 2025Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
122. CVPR 2025CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition
123. CVPR 2025Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
124. CVPR 2025CoLLM: A Large Language Model for Composed Image Retrieval
125. CVPR 2025CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
126. CVPR 2025Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning
127. CVPR 2025Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
128. CVPR 2025Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
129. CVPR 2025Complexity Experts are Task-Discriminative Learners for Any Image Restoration
130. CVPR 2025Compositional Caching for Training-free Open-vocabulary Attribute Detection
131. CVPR 2025Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
132. CVPR 2025Conformal Prediction for Zero-Shot Models
133. CVPR 2025Conical Visual Concentration for Efficient Large Vision-Language Models
134. CVPR 2025Consistency Posterior Sampling for Diverse Image Synthesis
135. CVPR 2025Context-Aware Multimodal Pretraining
136. CVPR 2025ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
137. CVPR 2025Contextual AD Narration with Interleaved Multimodal Sequence
138. CVPR 2025Continual SFT Matches Multimodal RLHF with Negative Supervision
139. CVPR 2025ControlFace: Harnessing Facial Parametric Control for Face Rigging
140. CVPR 2025Convex Combination Star Shape Prior for Data-driven Image Semantic Segmentation
141. CVPR 2025Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World
142. CVPR 2025Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning
143. CVPR 2025CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
144. CVPR 2025COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation
145. CVPR 2025COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
146. CVPR 2025CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
147. CVPR 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
148. CVPR 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
149. CVPR 2025COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts
150. CVPR 2025CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology

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。