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 11,207 篇，第 2 / 225 页

51. CVPR 2026Anchor-Guided Gradient Alignment for Incomplete Multimodal Learning
52. CVPR 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
53. CVPR 2026ApET Approximation-Error Guided Token Compression for Efficient VLMs
54. CVPR 2026APEX A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal
55. CVPR 2026APPO Attention-guided Perception Policy Optimization for Video Reasoning
56. CVPR 2026AR2-4FV Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View
57. CVPR 2026Ar2Can An Architect and an Artist Leveraging a Canvas for
58. CVPR 2026Arcadia Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
59. CVPR 2026Archon A Unified Multimodal Model for Holistic Digital Human Generation
60. CVPR 2026ArchSym Detecting 3D-Grounded Architectural Symmetries in the Wild
61. CVPR 2026AREA3D Active Reconstruction Agent with Unified Feed-Forward 3D Perception and
62. CVPR 2026ARES Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimation
63. CVPR 2026ARGUS Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following
64. CVPR 2026ARM-Thinker Reinforcing Multimodal Generative Reward Models with Agentic Tool Use
65. CVPR 2026ArtHOI Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object
66. CVPR 2026ArtiMuse Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level
67. CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
68. CVPR 2026Asynchronous Temporal Modeling with Two-Agent Framework for Streaming Dense Video
69. CVPR 2026AT-VLA Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action
70. CVPR 2026AToken A Unified Tokenizer for Vision
71. CVPR 2026Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
72. CVPR 2026AURA Multi-modal Shared Autonomy for Urban Navigation
73. CVPR 2026Authorize-on-Demand Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
74. CVPR 2026AutoCut End-to-end advertisement video editing based on multimodal discretization and
75. CVPR 2026AutoTraces Autoregressive Trajectory Forecasting via Multimodal Large Language Models
76. CVPR 2026AVA-Bench Atomic Visual Ability Benchmark for Vision Foundation Models
77. CVPR 2026AVA-VLA Improving Vision-Language-Action models with Active Visual Attention
78. CVPR 2026AVFakeBench A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs
79. CVPR 2026AVGGT Rethinking Global Attention for Accelerating VGGT
80. CVPR 2026AVION Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network
81. CVPR 2026AwareVLN Reasoning with Self-awareness for Vision-Language Navigation
82. CVPR 2026AXG-Reasoner Error Detection and Explanation in Long Task Videos with
83. CVPR 2026b-CLIP Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
84. CVPR 2026BabyVLM-V2 Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation
85. CVPR 2026Back to Point Exploring Point-Language Models for Zero-Shot 3D Anomaly
86. CVPR 2026BALM A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced
87. CVPR 2026Batch Loss Score for Dynamic Data Pruning
88. CVPR 2026Best Segmentation Buddies for Image-Shape Correspondence
89. CVPR 2026Better Stronger Faster Tackling the Trilemma in MLLM-based Segmentation with
90. CVPR 2026Beyond 3D VQAs Injecting 3D Spatial Priors into Vision-Language Models
91. CVPR 2026Beyond CLS Token Query-Driven Token-Level Forgery Purification for Generalizable Deepfake
92. CVPR 2026Beyond Explicit Language Plug-and-Play Visual-to-Linguistic Modeling Toward General Object Tracking
93. CVPR 2026Beyond Global Similarity Multi-Conditional Retrieval for Fine-Grained Cross-Modal Understanding
94. CVPR 2026Beyond Graph Model Reliable VLM Fine-Tuning via Random Graph Adapter
95. CVPR 2026Beyond Ground-Truth Leveraging Image Quality Priors for Real-World Image Restoration
96. CVPR 2026Beyond Heuristic Prompting A Concept-Guided Bayesian Framework for Zero-Shot Image
97. CVPR 2026Beyond Layer-Wise Merging Chain-of-Merging for Vision-Language Models
98. CVPR 2026Beyond Multiple Choice Verifiable OpenQA for Robust Vision-Language RFT
99. CVPR 2026Beyond Patches Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
100. CVPR 2026Beyond Perceptual Shortcuts Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning

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。