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 816 篇，第 3 / 17 页

101. ICLR 2025Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control
102. ICLR 2025Calibrating LLMs with Information-Theoretic Evidential Deep Learning
103. ICLR 2025CAMEx: Curvature-aware Merging of Experts
104. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
105. ICLR 2025Can Knowledge Editing Really Correct Hallucinations?
106. ICLR 2025Can Large Language Models Understand Symbolic Graphics Programs?
107. ICLR 2025Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
108. ICLR 2025Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
109. ICLR 2025Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
110. ICLR 2025Can LLMs Solve Longer Math Word Problems Better?
111. ICLR 2025Can LLMs Understand Time Series Anomalies?
112. ICLR 2025Can One Modality Model Synergize Training of Other Modality Models?
113. ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
114. ICLR 2025Can Watermarked LLMs be Identified by Users via Crafted Prompts?
115. ICLR 2025Can Watermarks be Used to Detect LLM IP Infringement For Free?
116. ICLR 2025Can We Talk Models Into Seeing the World Differently?
117. ICLR 2025CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
118. ICLR 2025Captured by Captions: On Memorization and its Mitigation in CLIP Models
119. ICLR 2025CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling
120. ICLR 2025Catastrophic Failure of LLM Unlearning via Quantization
121. ICLR 2025Causal Graphical Models for Vision-Language Compositional Understanding
122. ICLR 2025Causal Identification for Complex Functional Longitudinal Studies
123. ICLR 2025Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
124. ICLR 2025Causal Representation Learning from Multimodal Biomedical Observations
125. ICLR 2025Causally Motivated Sycophancy Mitigation for Large Language Models
126. ICLR 2025CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
127. ICLR 2025Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images
128. ICLR 2025CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness
129. ICLR 2025Certifying Counterfactual Bias in LLMs
130. ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
131. ICLR 2025Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
132. ICLR 2025Chain-of-region: Visual Language Models Need Details for Diagram Analysis
133. ICLR 2025ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding
134. ICLR 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
135. ICLR 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
136. ICLR 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
137. ICLR 2025CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening
138. ICLR 2025Class Distribution-induced Attention Map for Open-vocabulary Semantic Segmentations
139. ICLR 2025ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension
140. ICLR 2025CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
141. ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
142. ICLR 2025CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
143. ICLR 2025COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
144. ICLR 2025CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning
145. ICLR 2025CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
146. ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
147. ICLR 2025Combining Induction and Transduction for Abstract Reasoning
148. ICLR 2025Composable Interventions for Language Models
149. ICLR 2025Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
150. ICLR 2025Compositional Entailment Learning for Hyperbolic Vision-Language Models

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。