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 2 / 67 页

51. NeurIPS 2026AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
52. NeurIPS 2026Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models
53. NeurIPS 2026Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
54. NeurIPS 2026AeroMosaic:Transport-Aware Multimodal Evidence Fusion for Atmospheric Pollution Risk Inference
55. NeurIPS 2026AesGI-Bench: Benchmarking and Evaluating the Aesthetic Quality of AI-Generated Images via Large Multimodal Models
56. NeurIPS 2026Affine-Image Propagation for Tight and Scalable $\ell_{2}$ Neural Network Verification
57. NeurIPS 2026AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation
58. NeurIPS 2026Agent Explorative Policy Optimization for Agentic Multimodal Reasoning
59. NeurIPS 2026Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
60. NeurIPS 2026AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?
61. NeurIPS 2026Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection
62. NeurIPS 2026AgentVista: Evaluating Multimodal Agent in Ultra-Challenging Realistic Visual Scenarios
63. NeurIPS 2026Agree to Disagree: Multimodal Autonomous Negotiation and Calibration for Entity Representation Learning
64. NeurIPS 2026AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning
65. NeurIPS 2026AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference
66. NeurIPS 2026AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space
67. NeurIPS 2026AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection
68. NeurIPS 2026ALAM: Algebraically Consistent Latent Transitions for Vision-Language-Action Models
69. NeurIPS 2026Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
70. NeurIPS 2026Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
71. NeurIPS 2026Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHF
72. NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
73. NeurIPS 2026Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
74. NeurIPS 2026ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs
75. NeurIPS 2026AMARIS: Merging Generalist and Specialist LLMs via Adaptive Subspace Inheritance
76. NeurIPS 2026AmbientFM: A Foundation Model for Ambient Sensing
77. NeurIPS 2026AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
78. NeurIPS 2026An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection
79. NeurIPS 2026An Open-Source Training Dataset for Foundation Models for Black-box Optimization
80. NeurIPS 2026Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training
81. NeurIPS 2026Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation
82. NeurIPS 2026AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
83. NeurIPS 2026Angular Networks: Low-Bit Learning from Randomized Similarity Estimators
84. NeurIPS 2026Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
85. NeurIPS 2026Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
86. NeurIPS 2026APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
87. NeurIPS 2026Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
88. NeurIPS 2026Approaching Effective Merging in Model Embedding Space
89. NeurIPS 2026Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
90. NeurIPS 2026Approximation Algorithms for GPU Pricing under Finite Capacity
91. NeurIPS 2026Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
92. NeurIPS 2026Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
93. NeurIPS 2026Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
94. NeurIPS 2026Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Rewards
95. NeurIPS 2026Argus: A Cross-Regime Benchmark for the Transferability of Uncertainty Quantification in Computer-Use Agents
96. NeurIPS 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
97. NeurIPS 2026As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
98. NeurIPS 2026ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
99. NeurIPS 2026ASAP: Attention Sink Anchored Pruning
100. NeurIPS 2026ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations

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。