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 1,051 篇，第 2 / 22 页

51. ICML 2026AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
52. ICML 2026Antidistillation Fingerprinting
53. ICML 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
54. ICML 2026AnyCanvas: Potential Field Guidance for Training-Free Spatial Control in Text-to-Image Diffusion
55. ICML 2026AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
56. ICML 2026AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
57. ICML 2026AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
58. ICML 2026API: Adaptive Prototype Imputation for Incomplete Multimodal Sentiment Analysis
59. ICML 2026ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
60. ICML 2026ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
61. ICML 2026Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
62. ICML 2026Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
63. ICML 2026Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
64. ICML 2026Ask Less, See More: Communication-Conditioned Token Pruning for Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models
65. ICML 2026ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
66. ICML 2026Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial Alignment
67. ICML 2026Attend to Anything: Foundation Model for Unified Human Attention Modeling
68. ICML 2026Attention with Routed-Memory for Learnable Sparse Control
69. ICML 2026Attentive Multi-Layer Fusion for Vision Transformers
70. ICML 2026AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving
71. ICML 2026AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
72. ICML 2026Automated Formal Proofs of Combinatorial Identities via Wilf–Zeilberger Guidance and LLMs
73. ICML 2026AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving
74. ICML 2026AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic
75. ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
76. ICML 2026Awakening Visual Reasoning: Mitigating Post-Training Failure in Vision-Text Compression
77. ICML 2026BabyVision: Visual Reasoning Beyond Language
78. ICML 2026Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
79. ICML 2026BEAR: Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
80. ICML 2026BEDTime: A Unified Benchmark for Automatically Describing Time Series
81. ICML 2026Benchmarking and Enhancing VLM for Compressed Image Understanding
82. ICML 2026Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
83. ICML 2026Benchmarking Dense and Indiscernible Object Counting with Blueberries
84. ICML 2026Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
85. ICML 2026Benchmarking the Scientific Mind: A Pathology-Derived Biomedical VQA Benchmark for Complex Scientific Reasoning
86. ICML 2026Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration
87. ICML 2026Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
88. ICML 2026Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
89. ICML 2026Beyond Blind Noising: Disentangled Visual Rectification for Hallucination Mitigation in MLLMs
90. ICML 2026Beyond Description: Federated Adaptation via Semantic-Visual Prototype Alignment
91. ICML 2026Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality Conflicts
92. ICML 2026Beyond Language Modeling: An Exploration of Multimodal Pretraining
93. ICML 2026Beyond Logits: Coherent Hallucination Mitigation via Attention Contrastive Decoding
94. ICML 2026Beyond Logits: Metastable Latent Dynamics for Sample-Efficient Best-of-N Selection in LLMs
95. ICML 2026Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
96. ICML 2026Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning
97. ICML 2026Beyond Single-View Indexing: Structure-Aware Multi-View Retrieval for Knowledge-Based VQA
98. ICML 2026Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?
99. ICML 2026Beyond Unidirectional Bias: Reciprocal Perspective Calibration in Scene Graph Generation
100. ICML 2026Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

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。