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 2 / 22 页

51. NeurIPS 2025AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
52. NeurIPS 2025ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
53. NeurIPS 2025Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process
54. NeurIPS 2025An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination
55. NeurIPS 2025An Information-theoretical Framework for Understanding Out-of-distribution Detection with Pretrained Vision-Language Models
56. NeurIPS 2025Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
57. NeurIPS 2025AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models
58. NeurIPS 2025AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
59. NeurIPS 2025Approximate Domain Unlearning for Vision-Language Models
60. NeurIPS 2025Approximately Aligned Decoding
61. NeurIPS 2025ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
62. NeurIPS 2025Asymmetric Dual-Lens Video Deblurring
63. NeurIPS 2025Atom of Thoughts for Markov LLM Test-Time Scaling
64. NeurIPS 2025Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
65. NeurIPS 2025Attention! Your Vision Language Model Could Be Maliciously Manipulated
66. NeurIPS 2025Automated Model Discovery via Multi-modal & Multi-step Pipeline
67. NeurIPS 2025Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
68. NeurIPS 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
69. NeurIPS 2025Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
70. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
71. NeurIPS 2025AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web
72. NeurIPS 2025Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
73. NeurIPS 2025BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
74. NeurIPS 2025Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
75. NeurIPS 2025Balancing Multimodal Training Through Game-Theoretic Regularization
76. NeurIPS 2025BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
77. NeurIPS 2025BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation
78. NeurIPS 2025Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents
79. NeurIPS 2025Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
80. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
81. NeurIPS 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
82. NeurIPS 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
83. NeurIPS 2025Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
84. NeurIPS 2025Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
85. NeurIPS 2025Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
86. NeurIPS 2025Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation
87. NeurIPS 2025Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs
88. NeurIPS 2025Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
89. NeurIPS 2025Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
90. NeurIPS 2025Bio-Inspired Image Restoration
91. NeurIPS 2025BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
92. NeurIPS 2025BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
93. NeurIPS 2025Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
94. NeurIPS 2025Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs
95. NeurIPS 2025Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
96. NeurIPS 2025BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
97. NeurIPS 2025Block-Biased Mamba for Long-Range Sequence Processing
98. NeurIPS 2025BlockScan: Detecting Anomalies in Blockchain Transactions
99. NeurIPS 2025BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
100. NeurIPS 2025BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

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。