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 323 篇，第 2 / 7 页

51. ICML 2024Coactive Learning for Large Language Models using Implicit User Feedback
52. ICML 2024COALA: A Practical and Vision-Centric Federated Learning Platform
53. ICML 2024Code as Reward: Empowering Reinforcement Learning with VLMs
54. ICML 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
55. ICML 2024Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
56. ICML 2024Compositional Curvature Bounds for Deep Neural Networks
57. ICML 2024Conditional Common Entropy for Instrumental Variable Testing and Partial Identification
58. ICML 2024Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
59. ICML 2024ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
60. ICML 2024Copyright Traps for Large Language Models
61. ICML 2024Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
62. ICML 2024CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection
63. ICML 2024CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
64. ICML 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
65. ICML 2024Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
66. ICML 2024Debating with More Persuasive LLMs Leads to More Truthful Answers
67. ICML 2024DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
68. ICML 2024Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
69. ICML 2024Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
70. ICML 2024DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
71. ICML 2024Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
72. ICML 2024Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA
73. ICML 2024Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View
74. ICML 2024diff History for Neural Language Agents
75. ICML 2024Differentially private exact recovery for stochastic block models
76. ICML 2024Differentially Private Representation Learning via Image Captioning
77. ICML 2024Distinguishing the Knowable from the Unknowable with Language Models
78. ICML 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)
79. ICML 2024Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
80. ICML 2024eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data
81. ICML 2024Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
82. ICML 2024Efficient Exploration for LLMs
83. ICML 2024Eluder-based Regret for Stochastic Contextual MDPs
84. ICML 2024Emergent Equivariance in Deep Ensembles
85. ICML 2024Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models
86. ICML 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
87. ICML 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
88. ICML 2024ERQ: Error Reduction for Post-Training Quantization of Vision Transformers
89. ICML 2024Estimating Barycenters of Distributions with Neural Optimal Transport
90. ICML 2024Estimating Canopy Height at Scale
91. ICML 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models
92. ICML 2024Evaluating Quantized Large Language Models
93. ICML 2024Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
94. ICML 2024Evolving Subnetwork Training for Large Language Models
95. ICML 2024EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
96. ICML 2024Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
97. ICML 2024Exploiting Code Symmetries for Learning Program Semantics
98. ICML 2024Exploring Intrinsic Dimension for Vision-Language Model Pruning
99. ICML 2024Extracting Training Data From Document-Based VQA Models
100. ICML 2024Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and 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。