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 3,319 篇，第 3 / 67 页

101. NeurIPS 2026ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?
102. NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
103. NeurIPS 2026Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
104. NeurIPS 2026Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
105. NeurIPS 2026Attention Alignment Between Humans and Vision-Language Models
106. NeurIPS 2026Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
107. NeurIPS 2026Attention Transfer Is Not Universally Effective for Vision Transformers
108. NeurIPS 2026Attention-based PCA
109. NeurIPS 2026Attention-based Routing for Interpretable Multimodal Brain Encoding
110. NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
111. NeurIPS 2026Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
112. NeurIPS 2026Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
113. NeurIPS 2026Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
114. NeurIPS 2026Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
115. NeurIPS 2026Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria
116. NeurIPS 2026Automatically Refining Coding Rules for AI Coding Agents
117. NeurIPS 2026Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments
118. NeurIPS 2026Auxiliary Clues Aware’s Geometry Problem Solving
119. NeurIPS 2026AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
120. NeurIPS 2026AVIS: Adaptive Test-Time Scaling for Vision–Language Models
121. NeurIPS 2026AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
122. NeurIPS 2026BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone
123. NeurIPS 2026Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
124. NeurIPS 2026BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
125. NeurIPS 2026Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
126. NeurIPS 2026BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition
127. NeurIPS 2026Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
128. NeurIPS 2026Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
129. NeurIPS 2026BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
130. NeurIPS 2026BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
131. NeurIPS 2026Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
132. NeurIPS 2026Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood
133. NeurIPS 2026Behavior Pack Optimization for Video MLLM Post-Training
134. NeurIPS 2026Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
135. NeurIPS 2026Benchmark for Assessing Olfactory Perception of Large Language Models
136. NeurIPS 2026Benchmark Recovery Does Not Certify a Frozen Tool-Trigger Contract After Quantization
137. NeurIPS 2026Benchmark Shadows: How Data Regimes Shape Parameter Footprints and Generalization
138. NeurIPS 2026Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
139. NeurIPS 2026Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
140. NeurIPS 2026Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
141. NeurIPS 2026Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
142. NeurIPS 2026Benchmarking Optimizers for Large Language Model Pretraining
143. NeurIPS 2026Benchmarking Risk Attitudes of LLMs
144. NeurIPS 2026BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability
145. NeurIPS 2026Better Language Models Require Better Domain-Specific Inductive Biases
146. NeurIPS 2026Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept
147. NeurIPS 2026Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
148. NeurIPS 2026Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
149. NeurIPS 2026Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models
150. NeurIPS 2026Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting

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。