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 1,074 篇，第 3 / 22 页

101. NeurIPS 2025Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
102. NeurIPS 2025Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens
103. NeurIPS 2025Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
104. NeurIPS 2025Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
105. NeurIPS 2025Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
106. NeurIPS 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
107. NeurIPS 2025Bridging the gap to real-world language-grounded visual concept learning
108. NeurIPS 2025Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation
109. NeurIPS 2025BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
110. NeurIPS 2025Building 3D Representations and Generating Motions From a Single Image via Video-Generation
111. NeurIPS 2025BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes
112. NeurIPS 2025C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
113. NeurIPS 2025C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
114. NeurIPS 2025Calibrating Translation Decoding with Quality Estimation on LLMs
115. NeurIPS 2025CAMILA: Context-Aware Masking for Image Editing with Language Alignment
116. NeurIPS 2025Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
117. NeurIPS 2025Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind
118. NeurIPS 2025Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
119. NeurIPS 2025Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
120. NeurIPS 2025Can We Infer Confidential Properties of Training Data from LLMs?
121. NeurIPS 2025CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
122. NeurIPS 2025Caption This, Reason That: VLMs Caught in the Middle
123. NeurIPS 2025CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
124. NeurIPS 2025Cascaded Language Models for Cost-Effective Human–AI Decision-Making
125. NeurIPS 2025CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers
126. NeurIPS 2025CAT: Content-Adaptive Image Tokenization
127. NeurIPS 2025Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
128. NeurIPS 2025Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration
129. NeurIPS 2025Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door Intervention
130. NeurIPS 2025CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference
131. NeurIPS 2025CellVerse: Do Large Language Models Really Understand Cell Biology?
132. NeurIPS 2025CF-VLM：CounterFactual Vision-Language Fine-tuning
133. NeurIPS 2025CG-SSL: Concept-Guided Self-Supervised Learning
134. NeurIPS 2025ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
135. NeurIPS 2025Chain-of-Model Learning for Language Model
136. NeurIPS 2025Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
137. NeurIPS 2025ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models
138. NeurIPS 2025ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
139. NeurIPS 2025CHASM: Unveiling Covert Advertisements on Chinese Social Media
140. NeurIPS 2025ChatbotID: Identifying Chatbots with Granger Causality Test
141. NeurIPS 2025ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
142. NeurIPS 2025ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions
143. NeurIPS 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search
144. NeurIPS 2025CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
145. NeurIPS 2025ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
146. NeurIPS 2025CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs
147. NeurIPS 2025CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
148. NeurIPS 2025CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
149. NeurIPS 2025CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation
150. NeurIPS 2025CMoB: Modality Valuation via Causal Effect for Balanced Multimodal Learning

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。